lusxvr/nanoVLM-222M
Image-Text-to-Text • 0.2B • Updated • 421 • 99
Library
-
-
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
Paper • 2503.09516 • Published • 39 -
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper • 2505.24863 • Published • 97 -
QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
Paper • 2505.17667 • Published • 88 -
ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
Paper • 2505.24864 • Published • 146 -
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
Paper • 2505.24298 • Published • 34 -
GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning
Paper • 2505.20355 • Published • 36 -
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Paper • 2505.19640 • Published • 15 -
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
Paper • 2505.17399 • Published • 14 -
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Paper • 2505.19914 • Published • 46 -
One RL to See Them All: Visual Triple Unified Reinforcement Learning
Paper • 2505.18129 • Published • 62 -
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models
Paper • 2505.14810 • Published • 62 -
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper • 2505.16410 • Published • 58 -
JULI: Jailbreak Large Language Models by Self-Introspection
Paper • 2505.11790 • Published • 1 -
Optimizing Anytime Reasoning via Budget Relative Policy Optimization
Paper • 2505.13438 • Published • 36 -
Reward Reasoning Model
Paper • 2505.14674 • Published • 37 -
RM-R1: Reward Modeling as Reasoning
Paper • 2505.02387 • Published • 81 -
CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models
Paper • 2505.12504 • Published • 24 -
Neuro-Symbolic Query Compiler
Paper • 2505.11932 • Published • 18 -
Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
Paper • 2506.01320 • Published • 16 -
Aligning Latent Spaces with Flow Priors
Paper • 2506.05240 • Published • 27 -
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
Paper • 2506.00070 • Published • 29 -
A Controllable Examination for Long-Context Language Models
Paper • 2506.02921 • Published • 34 -
MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
Paper • 2506.01674 • Published • 28 -
CodeContests+: High-Quality Test Case Generation for Competitive Programming
Paper • 2506.05817 • Published • 9 -
FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion
Paper • 2506.01111 • Published • 31 -
Reinforcement Pre-Training
Paper • 2506.08007 • Published • 265 -
GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
Paper • 2506.08012 • Published • 7 -
Dreamland: Controllable World Creation with Simulator and Generative Models
Paper • 2506.08006 • Published • 7 -
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance
Paper • 2506.06444 • Published • 73 -
BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
Paper • 2506.07530 • Published • 20 -
Solving Inequality Proofs with Large Language Models
Paper • 2506.07927 • Published • 20 -
Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
Paper • 2506.09040 • Published • 34 -
Through the Valley: Path to Effective Long CoT Training for Small Language Models
Paper • 2506.07712 • Published • 18 -
Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework
Paper • 2506.02454 • Published • 7 -
Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
Paper • 2506.04614 • Published • 19 -
Astra: Toward General-Purpose Mobile Robots via Hierarchical Multimodal Learning
Paper • 2506.06205 • Published • 30 -
Magistral
Paper • 2506.10910 • Published • 68 -
Xolver: Multi-Agent Reasoning with Holistic Experience Learning Just Like an Olympiad Team
Paper • 2506.14234 • Published • 41 -
Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers
Paper • 2506.14702 • Published • 3 -
AR-RAG: Autoregressive Retrieval Augmentation for Image Generation
Paper • 2506.06962 • Published • 28 -
DoTA-RAG: Dynamic of Thought Aggregation RAG
Paper • 2506.12571 • Published • 50 -
syftr: Pareto-Optimal Generative AI
Paper • 2505.20266 • Published -
Scaling Test-time Compute for LLM Agents
Paper • 2506.12928 • Published • 63 -
LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
Paper • 2506.10082 • Published • 8 -
General-Reasoner: Advancing LLM Reasoning Across All Domains
Paper • 2505.14652 • Published • 24 -
Optimizing Length Compression in Large Reasoning Models
Paper • 2506.14755 • Published • 10 -
UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation
Paper • 2506.17202 • Published • 10 -
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
Paper • 2506.18896 • Published • 29 -
Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
Paper • 2506.16035 • Published • 89 -
Robust Reward Modeling via Causal Rubrics
Paper • 2506.16507 • Published • 9 -
LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
Paper • 2507.02813 • Published • 60 -
FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model
Paper • 2507.01953 • Published • 18 -
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
Paper • 2506.17930 • Published • 19 -
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
Paper • 2506.24119 • Published • 51 -
katanemo/Arch-Router-1.5B
Text Generation • 2B • Updated • 5.07k • • 249 -
Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky
Paper • 2507.03336 • Published • 7 -
SingLoRA: Low Rank Adaptation Using a Single Matrix
Paper • 2507.05566 • Published • 116 -
CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Paper • 2507.06181 • Published • 45 -
AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs
Paper • 2507.05687 • Published • 31 -
Coding Triangle: How Does Large Language Model Understand Code?
Paper • 2507.06138 • Published • 22 -
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
Paper • 2507.05920 • Published • 12 -
RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
Paper • 2507.03253 • Published • 19 -
Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Paper • 2507.07996 • Published • 36 -
Lumos-1: On Autoregressive Video Generation from a Unified Model Perspective
Paper • 2507.08801 • Published • 32 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 263 -
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
Paper • 2507.15061 • Published • 60 -
AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning
Paper • 2507.12841 • Published • 42 -
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Paper • 2507.16784 • Published • 123 -
MUR: Momentum Uncertainty guided Reasoning for Large Language Models
Paper • 2507.14958 • Published • 47 -
Does More Inference-Time Compute Really Help Robustness?
Paper • 2507.15974 • Published • 7 -
RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback
Paper • 2507.15024 • Published • 14 -
ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
Paper • 2507.15454 • Published • 7 -
Promptomatix: An Automatic Prompt Optimization Framework for Large Language Models
Paper • 2507.14241 • Published • 18 -
TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
Paper • 2507.18537 • Published • 18 -
Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
Paper • 2507.15597 • Published • 34 -
A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
Paper • 2507.14295 • Published • 14 -
SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction
Paper • 2507.15852 • Published • 38 -
FLEXITOKENS: Flexible Tokenization for Evolving Language Models
Paper • 2507.12720 • Published • 10 -
RiemannLoRA: A Unified Riemannian Framework for Ambiguity-Free LoRA Optimization
Paper • 2507.12142 • Published • 36 -
Replacing thinking with tool usage enables reasoning in small language models
Paper • 2507.05065 • Published • 16 -
Lizard: An Efficient Linearization Framework for Large Language Models
Paper • 2507.09025 • Published • 19 -
MemOS: A Memory OS for AI System
Paper • 2507.03724 • Published • 166 -
Agentic Reinforced Policy Optimization
Paper • 2507.19849 • Published • 161 -
Deep Researcher with Test-Time Diffusion
Paper • 2507.16075 • Published • 68 -
SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment
Paper • 2507.20984 • Published • 58 -
MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
Paper • 2507.19478 • Published • 33 -
Geometric-Mean Policy Optimization
Paper • 2507.20673 • Published • 32 -
UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities
Paper • 2507.19766 • Published • 15 -
VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning
Paper • 2507.22607 • Published • 47 -
Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models
Paper • 2508.00819 • Published • 63 -
Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Models' Instruction Following
Paper • 2508.02150 • Published • 37 -
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
Paper • 2508.00414 • Published • 94 -
On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective
Paper • 2507.23632 • Published • 6 -
Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
Paper • 2507.23726 • Published • 115 -
SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension
Paper • 2508.01959 • Published • 60 -
Tool-integrated Reinforcement Learning for Repo Deep Search
Paper • 2508.03012 • Published • 20 -
InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization
Paper • 2508.05731 • Published • 27 -
MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
Paper • 2508.01242 • Published • 11 -
Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
Paper • 2508.08221 • Published • 50 -
Reinforcement Learning in Vision: A Survey
Paper • 2508.08189 • Published • 30 -
Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents
Paper • 2508.05954 • Published • 6 -
Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
Paper • 2508.08791 • Published • 16 -
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Paper • 2508.03501 • Published • 59 -
Complex Logical Instruction Generation
Paper • 2508.09125 • Published • 40 -
Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery
Paper • 2508.08401 • Published • 42 -
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Paper • 2508.09192 • Published • 30 -
Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping
Paper • 2508.12466 • Published • 8 -
Has GPT-5 Achieved Spatial Intelligence? An Empirical Study
Paper • 2508.13142 • Published • 34 -
VertexRegen: Mesh Generation with Continuous Level of Detail
Paper • 2508.09062 • Published • 38 -
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
Paper • 2508.10395 • Published • 42 -
STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
Paper • 2508.10893 • Published • 31 -
FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction
Paper • 2508.11987 • Published • 72 -
MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
Paper • 2508.13186 • Published • 20 -
Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
Paper • 2508.10751 • Published • 29 -
UI-Venus Technical Report: Building High-performance UI Agents with RFT
Paper • 2508.10833 • Published • 45 -
Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
Paper • 2508.09968 • Published • 15 -
CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search
Paper • 2508.02091 • Published • 13 -
LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries
Paper • 2508.15760 • Published • 47 -
Deep Think with Confidence
Paper • 2508.15260 • Published • 90 -
DuPO: Enabling Reliable LLM Self-Verification via Dual Preference Optimization
Paper • 2508.14460 • Published • 85 -
Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Paper • 2508.14896 • Published • 22 -
PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs
Paper • 2508.17188 • Published • 17 -
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Paper • 2508.16949 • Published • 24 -
Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
Paper • 2508.18032 • Published • 41 -
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
Paper • 2508.16745 • Published • 29 -
UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning
Paper • 2508.18756 • Published • 36 -
Do What? Teaching Vision-Language-Action Models to Reject the Impossible
Paper • 2508.16292 • Published • 9 -
MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting
Paper • 2508.17811 • Published • 7 -
FastMesh:Efficient Artistic Mesh Generation via Component Decoupling
Paper • 2508.19188 • Published • 17 -
Spacer: Towards Engineered Scientific Inspiration
Paper • 2508.17661 • Published • 32 -
ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
Paper • 2508.18773 • Published • 16 -
VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Paper • 2508.19247 • Published • 43 -
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80 -
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 90 -
Provable Benefits of In-Tool Learning for Large Language Models
Paper • 2508.20755 • Published • 11 -
Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Paper • 2508.21365 • Published • 29 -
Efficient Code Embeddings from Code Generation Models
Paper • 2508.21290 • Published • 20 -
CLIPSym: Delving into Symmetry Detection with CLIP
Paper • 2508.14197 • Published • 8 -
Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
Paper • 2509.02522 • Published • 25 -
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
Paper • 2509.02479 • Published • 84 -
Universal Deep Research: Bring Your Own Model and Strategy
Paper • 2509.00244 • Published • 14 -
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 24 -
Open Data Synthesis For Deep Research
Paper • 2509.00375 • Published • 72 -
Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
Paper • 2509.04292 • Published • 58 -
Towards a Unified View of Large Language Model Post-Training
Paper • 2509.04419 • Published • 76 -
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench
Paper • 2508.20931 • Published • 16 -
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Paper • 2509.03059 • Published • 25 -
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
Paper • 2509.04011 • Published • 29 -
Symbolic Graphics Programming with Large Language Models
Paper • 2509.05208 • Published • 47 -
Bootstrapping Task Spaces for Self-Improvement
Paper • 2509.04575 • Published • 6 -
Behavioral Fingerprinting of Large Language Models
Paper • 2509.04504 • Published • 6 -
Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
Paper • 2509.06493 • Published • 12 -
Reinforcement Learning Foundations for Deep Research Systems: A Survey
Paper • 2509.06733 • Published • 32 -
Reconstruction Alignment Improves Unified Multimodal Models
Paper • 2509.07295 • Published • 40 -
Visual Representation Alignment for Multimodal Large Language Models
Paper • 2509.07979 • Published • 84 -
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Paper • 2509.06949 • Published • 57 -
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 105 -
Towards General Agentic Intelligence via Environment Scaling
Paper • 2509.13311 • Published • 72 -
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning
Paper • 2509.13305 • Published • 91 -
SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation
Paper • 2509.10708 • Published • 18 -
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering
Paper • 2509.09713 • Published • 25 -
FlowRL: Matching Reward Distributions for LLM Reasoning
Paper • 2509.15207 • Published • 118 -
Single-stream Policy Optimization
Paper • 2509.13232 • Published • 36 -
World Modeling with Probabilistic Structure Integration
Paper • 2509.09737 • Published • 14 -
Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
Paper • 2509.13755 • Published • 19 -
C2-Evo: Co-Evolving Multimodal Data and Model for Self-Improving Reasoning
Paper • 2507.16518 • Published • 2 -
WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance
Paper • 2509.15130 • Published • 31 -
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
Paper • 2509.15194 • Published • 33 -
THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning
Paper • 2509.13761 • Published • 16 -
A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning
Paper • 2509.15937 • Published • 20 -
BaseReward: A Strong Baseline for Multimodal Reward Model
Paper • 2509.16127 • Published • 21 -
MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
Paper • 2509.14638 • Published • 14 -
Video2Roleplay: A Multimodal Dataset and Framework for Video-Guided Role-playing Agents
Paper • 2509.15233 • Published • 2 -
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Paper • 2509.16197 • Published • 58 -
Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
Paper • 2509.15591 • Published • 45 -
BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
Paper • 2509.15566 • Published • 14 -
Mano Report
Paper • 2509.17336 • Published • 10 -
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback
Paper • 2501.10799 • Published • 15 -
Table as Thought: Exploring Structured Thoughts in LLM Reasoning
Paper • 2501.02152 • Published -
Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning
Paper • 2412.09078 • Published -
TinyThinker: Distilling Reasoning through Coarse-to-Fine Knowledge Internalization with Self-Reflection
Paper • 2412.08024 • Published • 1 -
LLM2: Let Large Language Models Harness System 2 Reasoning
Paper • 2412.20372 • Published -
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
Paper • 2501.11110 • Published • 4 -
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
Paper • 2412.15797 • Published • 18 -
RAG-Star: Enhancing Deliberative Reasoning with Retrieval Augmented Verification and Refinement
Paper • 2412.12881 • Published • 2 -
OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Paper • 2509.17627 • Published • 66 -
Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation
Paper • 2509.18824 • Published • 23 -
Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
Paper • 2509.14662 • Published • 13 -
VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models
Paper • 2509.19803 • Published • 122 -
Tree Search for LLM Agent Reinforcement Learning
Paper • 2509.21240 • Published • 92 -
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
Paper • 2509.24006 • Published • 119 -
Fine-tuning Done Right in Model Editing
Paper • 2509.22072 • Published • 28 -
No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Paper • 2509.21880 • Published • 53 -
LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer
Paper • 2509.22414 • Published • 22 -
Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning
Paper • 2509.22601 • Published • 30 -
EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning
Paper • 2509.22576 • Published • 137 -
Variational Reasoning for Language Models
Paper • 2509.22637 • Published • 69 -
AutoIntent: AutoML for Text Classification
Paper • 2509.21138 • Published • 37 -
TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
Paper • 2509.25760 • Published • 55 -
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Paper • 2509.26628 • Published • 17 -
Sequential Diffusion Language Models
Paper • 2509.24007 • Published • 47 -
ReviewScore: Misinformed Peer Review Detection with Large Language Models
Paper • 2509.21679 • Published • 64 -
ReviewRL: Towards Automated Scientific Review with RL
Paper • 2508.10308 • Published • 1 -
ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks
Paper • 2508.15804 • Published • 15 -
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
Paper • 2509.25454 • Published • 148 -
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper • 2509.25849 • Published • 48 -
BroRL: Scaling Reinforcement Learning via Broadened Exploration
Paper • 2510.01180 • Published • 20 -
GEM: A Gym for Agentic LLMs
Paper • 2510.01051 • Published • 91 -
Interactive Training: Feedback-Driven Neural Network Optimization
Paper • 2510.02297 • Published • 43 -
More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
Paper • 2509.25848 • Published • 81 -
CLUE: Non-parametric Verification from Experience via Hidden-State Clustering
Paper • 2510.01591 • Published • 28 -
LongCodeZip: Compress Long Context for Code Language Models
Paper • 2510.00446 • Published • 108 -
Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
Paper • 2510.00515 • Published • 42 -
Reactive Transformer (RxT) -- Stateful Real-Time Processing for Event-Driven Reactive Language Models
Paper • 2510.03561 • Published • 25 -
Large Language Models as Optimizers
Paper • 2309.03409 • Published • 79 -
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
Paper • 2309.08532 • Published • 53 -
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
Paper • 2307.14936 • Published • 42 -
Factuality Matters: When Image Generation and Editing Meet Structured Visuals
Paper • 2510.05091 • Published • 20 -
Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training
Paper • 2510.04996 • Published • 16 -
Paper2Video: Automatic Video Generation from Scientific Papers
Paper • 2510.05096 • Published • 120 -
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
Paper • 2510.05069 • Published • 13 -
MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
Paper • 2510.03632 • Published • 42 -
Large Reasoning Models Learn Better Alignment from Flawed Thinking
Paper • 2510.00938 • Published • 60 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 513 -
Multi-Agent Tool-Integrated Policy Optimization
Paper • 2510.04678 • Published • 31 -
Agent Learning via Early Experience
Paper • 2510.08558 • Published • 276 -
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Paper • 2510.05034 • Published • 51 -
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper • 2510.03222 • Published • 76 -
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 182 -
PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs
Paper • 2510.09507 • Published • 11 -
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Paper • 2510.04618 • Published • 131 -
Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Paper • 2510.08492 • Published • 10 -
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Paper • 2510.09577 • Published • 8 -
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
Paper • 2510.08697 • Published • 39 -
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
Paper • 2510.09201 • Published • 50 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 170 -
UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning
Paper • 2510.13515 • Published • 12 -
Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training
Paper • 2510.12586 • Published • 115 -
Understanding DeepResearch via Reports
Paper • 2510.07861 • Published • 7 -
RAG-Anything: All-in-One RAG Framework
Paper • 2510.12323 • Published • 73 -
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 33 -
Glyph: Scaling Context Windows via Visual-Text Compression
Paper • 2510.17800 • Published • 69 -
LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts
Paper • 2510.19363 • Published • 63 -
Unified Reinforcement and Imitation Learning for Vision-Language Models
Paper • 2510.19307 • Published • 32 -
Attention Is All You Need for KV Cache in Diffusion LLMs
Paper • 2510.14973 • Published • 42 -
Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents
Paper • 2510.14967 • Published • 34 -
Video Reasoning without Training
Paper • 2510.17045 • Published • 8 -
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
Paper • 2510.19779 • Published • 62 -
Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
Paper • 2510.19304 • Published • 24 -
Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
Paper • 2510.20187 • Published • 19 -
ReCode: Unify Plan and Action for Universal Granularity Control
Paper • 2510.23564 • Published • 123 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 48 -
Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
Paper • 2510.23473 • Published • 86 -
World Simulation with Video Foundation Models for Physical AI
Paper • 2511.00062 • Published • 46 -
OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
Paper • 2510.24411 • Published • 72 -
The End of Manual Decoding: Towards Truly End-to-End Language Models
Paper • 2510.26697 • Published • 119 -
The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms
Paper • 2511.04217 • Published • 17 -
Diffusion Language Models are Super Data Learners
Paper • 2511.03276 • Published • 132 -
Scaling Latent Reasoning via Looped Language Models
Paper • 2510.25741 • Published • 229 -
DRIVE: Data Curation Best Practices for Reinforcement Learning with Verifiable Reward in Competitive Code Generation
Paper • 2511.06307 • Published • 53 -
Black-Box On-Policy Distillation of Large Language Models
Paper • 2511.10643 • Published • 52 -
DoPE: Denoising Rotary Position Embedding
Paper • 2511.09146 • Published • 98 -
Orion: A Unified Visual Agent for Multimodal Perception, Advanced Visual Reasoning and Execution
Paper • 2511.14210 • Published • 21 -
SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
Paper • 2511.15605 • Published • 25 -
Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs
Paper • 2511.16664 • Published • 29 -
TiDAR: Think in Diffusion, Talk in Autoregression
Paper • 2511.08923 • Published • 128 -
MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning
Paper • 2511.06805 • Published • 13 -
The Path Not Taken: RLVR Provably Learns Off the Principals
Paper • 2511.08567 • Published • 35 -
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Paper • 2510.25992 • Published • 48 -
FARMER: Flow AutoRegressive Transformer over Pixels
Paper • 2510.23588 • Published • 59 -
Parallel Loop Transformer for Efficient Test-Time Computation Scaling
Paper • 2510.24824 • Published • 17 -
LLM-guided Hierarchical Retrieval
Paper • 2510.13217 • Published • 21 -
DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning
Paper • 2510.15110 • Published • 18 -
Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
Paper • 2510.20579 • Published • 56 -
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms
Paper • 2511.17592 • Published • 121 -
Virtual Width Networks
Paper • 2511.11238 • Published • 39 -
Flow Map Distillation Without Data
Paper • 2511.19428 • Published • 6 -
Monet: Reasoning in Latent Visual Space Beyond Images and Language
Paper • 2511.21395 • Published • 19 -
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
Paper • 2511.19773 • Published • 10 -
SSA: Sparse Sparse Attention by Aligning Full and Sparse Attention Outputs in Feature Space
Paper • 2511.20102 • Published • 28 -
Architecture Decoupling Is Not All You Need For Unified Multimodal Model
Paper • 2511.22663 • Published • 29 -
SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs
Paper • 2512.00722 • Published • 16 -
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Paper • 2512.01374 • Published • 106 -
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
Paper • 2512.02014 • Published • 74 -
OneThinker: All-in-one Reasoning Model for Image and Video
Paper • 2512.03043 • Published • 34 -
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Paper • 2512.05591 • Published • 17 -
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
Paper • 2512.05150 • Published • 76 -
UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers
Paper • 2512.04504 • Published • 18 -
On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral
Paper • 2512.04220 • Published • 16 -
DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
Paper • 2512.03000 • Published • 37 -
PromptBridge: Cross-Model Prompt Transfer for Large Language Models
Paper • 2512.01420 • Published • 11 -
PretrainZero: Reinforcement Active Pretraining
Paper • 2512.03442 • Published • 49 -
SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
Paper • 2512.02807 • Published • 9 -
Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion
Paper • 2512.04926 • Published • 42 -
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
Paper • 2512.07461 • Published • 79 -
Distribution Matching Variational AutoEncoder
Paper • 2512.07778 • Published • 29 -
TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models
Paper • 2512.08153 • Published • 8 -
InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models
Paper • 2512.08829 • Published • 21 -
Self-Improving VLM Judges Without Human Annotations
Paper • 2512.05145 • Published • 20 -
Rethinking Training Dynamics in Scale-wise Autoregressive Generation
Paper • 2512.06421 • Published • 7 -
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
Paper • 2512.07802 • Published • 46 -
unsloth/Devstral-2-123B-Instruct-2512-GGUF
125B • Updated • 6.05k • 51 -
Achieving Olympia-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Paper • 2512.10534 • Published • 32 -
BEAVER: An Efficient Deterministic LLM Verifier
Paper • 2512.05439 • Published • 36 -
Vector Quantization using Gaussian Variational Autoencoder
Paper • 2512.06609 • Published • 1 -
Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
Paper • 2512.07525 • Published • 60 -
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Paper • 2511.23386 • Published • 16 -
Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving
Paper • 2512.10739 • Published • 47 -
OmniPSD: Layered PSD Generation with Diffusion Transformer
Paper • 2512.09247 • Published • 50 -
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
Paper • 2512.13586 • Published • 93 -
KlingAvatar 2.0 Technical Report
Paper • 2512.13313 • Published • 44 -
Efficient-DLM: From Autoregressive to Diffusion Language Models, and Beyond in Speed
Paper • 2512.14067 • Published • 16 -
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper • 2512.13687 • Published • 106 -
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
Paper • 2512.14052 • Published • 42 -
Universal Reasoning Model
Paper • 2512.14693 • Published • 44 -
Image Diffusion Preview with Consistency Solver
Paper • 2512.13592 • Published • 8 -
End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
Paper • 2512.15702 • Published • 16 -
STeCa: Step-level Trajectory Calibration for LLM Agent Learning
Paper • 2502.14276 • Published • 1 -
Step-GUI Technical Report
Paper • 2512.15431 • Published • 133 -
Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification
Paper • 2512.16921 • Published • 8 -
Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
Paper • 2512.16905 • Published • 32 -
DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders
Paper • 2512.13690 • Published • 3 -
Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
Paper • 2512.13607 • Published • 38 -
Adaptation of Agentic AI
Paper • 2512.16301 • Published • 108 -
QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management
Paper • 2512.12967 • Published • 111 -
CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
Paper • 2512.10342 • Published • 1 -
UAGLNet: Uncertainty-Aggregated Global-Local Fusion Network with Cooperative CNN-Transformer for Building Extraction
Paper • 2512.12941 • Published • 2 -
TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning
Paper • 2512.13106 • Published • 4 -
Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation
Paper • 2512.13655 • Published • 3 -
Janus: Disaggregating Attention and Experts for Scalable MoE Inference
Paper • 2512.13525 • Published • 6 -
RePo: Language Models with Context Re-Positioning
Paper • 2512.14391 • Published • 12 -
VersatileFFN: Achieving Parameter Efficiency in LLMs via Adaptive Wide-and-Deep Reuse
Paper • 2512.14531 • Published • 15 -
ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement
Paper • 2512.13303 • Published • 17 -
Differentiable Evolutionary Reinforcement Learning
Paper • 2512.13399 • Published • 22 -
MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives
Paper • 2512.14699 • Published • 28 -
RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics
Paper • 2512.13660 • Published • 37 -
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 121 -
Hybrid Attribution Priors for Explainable and Robust Model Training
Paper • 2512.14719 • Published • 3 -
WAY: Estimation of Vessel Destination in Worldwide AIS Trajectory
Paper • 2512.13190 • Published • 8 -
The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
Paper • 2512.19693 • Published • 67 -
Reinforcement Learning for Self-Improving Agent with Skill Library
Paper • 2512.17102 • Published • 42 -
google/gemma-scope-2
Updated • 80 -
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Paper • 2512.19673 • Published • 66 -
QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation
Paper • 2512.19134 • Published • 32 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 222 -
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Paper • 2512.16969 • Published • 120 -
LongVideoAgent: Multi-Agent Reasoning with Long Videos
Paper • 2512.20618 • Published • 56 -
Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs
Paper • 2512.17206 • Published • 20 -
Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs
Paper • 2512.17008 • Published • 11 -
InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training
Paper • 2510.15859 • Published • 13 -
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
Paper • 2512.14681 • Published • 42 -
Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
Paper • 2512.17351 • Published • 28 -
Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning
Paper • 2512.15687 • Published • 22 -
SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning
Paper • 2512.13874 • Published • 17 -
SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations
Paper • 2512.14080 • Published • 9 -
Understanding and Improving Hyperbolic Deep Reinforcement Learning
Paper • 2512.14202 • Published • 6 -
SCOPE: Prompt Evolution for Enhancing Agent Effectiveness
Paper • 2512.15374 • Published • 6 -
VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
Paper • 2512.12072 • Published • 18 -
DEER: Draft with Diffusion, Verify with Autoregressive Models
Paper • 2512.15176 • Published • 45 -
TabReX : Tabular Referenceless eXplainable Evaluation
Paper • 2512.15907 • Published • 2 -
Trainable Log-linear Sparse Attention for Efficient Diffusion Transformers
Paper • 2512.16615 • Published • 5 -
AdaTooler-V: Adaptive Tool-Use for Images and Videos
Paper • 2512.16918 • Published • 14 -
REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
Paper • 2512.16636 • Published • 26 -
Kling-Omni Technical Report
Paper • 2512.16776 • Published • 173 -
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
Paper • 2512.20605 • Published • 62 -
Multi-hop Reasoning via Early Knowledge Alignment
Paper • 2512.20144 • Published • 7 -
Schoenfeld's Anatomy of Mathematical Reasoning by Language Models
Paper • 2512.19995 • Published • 16 -
TimeBill: Time-Budgeted Inference for Large Language Models
Paper • 2512.21859 • Published • 25 -
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone
Paper • 2512.22615 • Published • 50 -
Training AI Co-Scientists Using Rubric Rewards
Paper • 2512.23707 • Published • 21 -
Masking Teacher and Reinforcing Student for Distilling Vision-Language Models
Paper • 2512.22238 • Published • 30 -
LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics
Paper • 2512.21010 • Published • 4 -
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Paper • 2512.23447 • Published • 99 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 321 -
Evaluating Parameter Efficient Methods for RLVR
Paper • 2512.23165 • Published • 28 -
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
Paper • 2511.16108 • Published -
The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models
Paper • 2601.03425 • Published • 17 -
MMFormalizer: Multimodal Autoformalization in the Wild
Paper • 2601.03017 • Published • 106 -
DiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs
Paper • 2601.03559 • Published • 14 -
Token-Level LLM Collaboration via FusionRoute
Paper • 2601.05106 • Published • 40 -
VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice
Paper • 2601.05175 • Published • 36 -
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Paper • 2601.06487 • Published • 54 -
Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers
Paper • 2601.04890 • Published • 44 -
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Paper • 2601.07832 • Published • 52 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 230 -
RelayLLM: Efficient Reasoning via Collaborative Decoding
Paper • 2601.05167 • Published • 31 -
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
Paper • 2601.10129 • Published • 13 -
Language of Thought Shapes Output Diversity in Large Language Models
Paper • 2601.11227 • Published • 9 -
NAACL: Noise-AwAre Verbal Confidence Calibration for LLMs in RAG Systems
Paper • 2601.11004 • Published • 30 -
Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model
Paper • 2601.15892 • Published • 53 -
The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models
Paper • 2601.15165 • Published • 73 -
Learning to Discover at Test Time
Paper • 2601.16175 • Published • 44 -
ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought
Paper • 2601.23184 • Published • 36 -
AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders
Paper • 2602.05027 • Published • 63 -
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
Paper • 2602.11748 • Published • 35 -
Voxtral Realtime
Paper • 2602.11298 • Published • 24 -
DFlash: Block Diffusion for Flash Speculative Decoding
Paper • 2602.06036 • Published • 46 -
InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions
Paper • 2602.06035 • Published • 23 -
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 72 -
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Paper • 2602.14234 • Published • 26 -
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
Paper • 2602.14080 • Published • 21 -
On Surprising Effectiveness of Masking Updates in Adaptive Optimizers
Paper • 2602.15322 • Published • 10 -
OPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models
Paper • 2305.12001 • Published • 1 -
SELF: Language-Driven Self-Evolution for Large Language Model
Paper • 2310.00533 • Published • 2 -
DINO-SAE: DINO Spherical Autoencoder for High-Fidelity Image Reconstruction and Generation
Paper • 2601.22904 • Published • 15 -
EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots
Paper • 2602.18071 • Published • 22 -
VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation
Paper • 2601.02256 • Published • 33 -
GARDO: Reinforcing Diffusion Models without Reward Hacking
Paper • 2512.24138 • Published • 30 -
Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling
Paper • 2601.02346 • Published • 27 -
Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
Paper • 2512.20578 • Published • 86 -
Recursive Language Models
Paper • 2512.24601 • Published • 94 -
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs
Paper • 2601.01836 • Published • 10 -
Toward Stable Semi-Supervised Remote Sensing Segmentation via Co-Guidance and Co-Fusion
Paper • 2512.23035 • Published • 5 -
Confidence Estimation for LLMs in Multi-turn Interactions
Paper • 2601.02179 • Published • 17 -
SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
Paper • 2601.01426 • Published • 24 -
OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment
Paper • 2601.01576 • Published • 19 -
Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents
Paper • 2601.02314 • Published • 2 -
M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models
Paper • 2512.22877 • Published • 2 -
Nested Learning: The Illusion of Deep Learning Architectures
Paper • 2512.24695 • Published • 45 -
Deep Delta Learning
Paper • 2601.00417 • Published • 34 -
The Reasoning-Creativity Trade-off: Toward Creativity-Driven Problem Solving
Paper • 2601.00747 • Published • 20 -
InfoSynth: Information-Guided Benchmark Synthesis for LLMs
Paper • 2601.00575 • Published • 3 -
Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
Paper • 2512.24617 • Published • 66 -
A unified framework for detecting point and collective anomalies in operating system logs via collaborative transformers
Paper • 2512.23380 • Published • 45 -
Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems
Paper • 2512.24385 • Published • 8 -
Scaling Open-Ended Reasoning to Predict the Future
Paper • 2512.25070 • Published • 20 -
Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process
Paper • 2512.23988 • Published • 19 -
Detecting Anomalies in Machine Learning Infrastructure via Hardware Telemetry
Paper • 2510.26008 • Published -
CodeLSI: Leveraging Foundation Models for Automated Code Generation with Low-Rank Optimization and Domain-Specific Instruction Tuning
Paper • 2509.14373 • Published -
Big data analysis and distributed deep learning for next-generation intrusion detection system optimization
Paper • 2209.13961 • Published -
Qwen/DeepPlanning
Viewer • Updated • 2.14k • 631 • 194 -
ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation
Paper • 2602.20093 • Published • 29 -
tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Paper • 2602.20160 • Published • 10 -
MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training
Paper • 2510.18830 • Published -
Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
Paper • 2603.04257 • Published • 19 -
AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models
Paper • 2603.01236 • Published • 11 -
V_1: Unifying Generation and Self-Verification for Parallel Reasoners
Paper • 2603.04304 • Published • 14 -
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models
Paper • 2603.02482 • Published • 3 -
BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning
Paper • 2603.04124 • Published • 1 -
Specificity-aware reinforcement learning for fine-grained open-world classification
Paper • 2603.03197 • Published • 16 -
FireRedTeam/FireRed-OCR
Image-to-Text • 2B • Updated • 25.5k • 152 -
Dynamic Chunking Diffusion Transformer
Paper • 2603.06351 • Published • 15 -
π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
Paper • 2603.02083 • Published • 9 -
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
Paper • 2603.05890 • Published • 92 -
K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model
Paper • 2602.19128 • Published • 7 -
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Paper • 2603.09206 • Published • 53 -
On-Policy Self-Distillation for Reasoning Compression
Paper • 2603.05433 • Published • 8 -
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
Paper • 2603.09095 • Published • 29 -
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
Paper • 2603.08589 • Published • 38 -
Believe Your Model: Distribution-Guided Confidence Calibration
Paper • 2603.03872 • Published • 40 -
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
Paper • 2603.09117 • Published • 10 -
OpenClaw-RL: Train Any Agent Simply by Talking
Paper • 2603.10165 • Published • 150 -
In-Context Reinforcement Learning for Tool Use in Large Language Models
Paper • 2603.08068 • Published • 43 -
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
Paper • 2603.12267 • Published • 13 -
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Paper • 2603.11593 • Published • 25 -
Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
Paper • 2602.10224 • Published • 19 -
Multimodal OCR: Parse Anything from Documents
Paper • 2603.13032 • Published • 43 -
Guiding a Diffusion Transformer with the Internal Dynamics of Itself
Paper • 2512.24176 • Published • 8 -
PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
Paper • 2602.16745 • Published • 8 -
Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
Paper • 2603.15653 • Published • 12 -
Complementary Reinforcement Learning
Paper • 2603.17621 • Published • 37 -
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Paper • 2603.15557 • Published • 29 -
The Art of Efficient Reasoning: Data, Reward, and Optimization
Paper • 2602.20945 • Published • 7 -
TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents
Paper • 2602.19633 • Published • 8 -
Matryoshka Gaussian Splatting
Paper • 2603.19234 • Published • 11 -
Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer
Paper • 2603.19227 • Published • 42 -
VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining
Paper • 2603.15030 • Published • 21 -
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Paper • 2603.09906 • Published • 75 -
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
Paper • 2603.09200 • Published • 5 -
Multi-Head Low-Rank Attention
Paper • 2603.02188 • Published • 3 -
Mario: Multimodal Graph Reasoning with Large Language Models
Paper • 2603.05181 • Published • 9 -
How Far Can Unsupervised RLVR Scale LLM Training?
Paper • 2603.08660 • Published • 57 -
Heterogeneous Agent Collaborative Reinforcement Learning
Paper • 2603.02604 • Published • 193 -
Alignment Makes Language Models Normative, Not Descriptive
Paper • 2603.17218 • Published • 46 -
Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD
Paper • 2603.20155 • Published • 10 -
mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT
Paper • 2603.21606 • Published • 38 -
Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
Paper • 2603.18004 • Published • 13 -
Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
Paper • 2603.08462 • Published • 22 -
On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
Paper • 2603.22117 • Published • 29 -
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 94 -
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Paper • 2603.22281 • Published • 17 -
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Paper • 2603.23483 • Published • 61 -
Generalized Discrete Diffusion from Snapshots
Paper • 2603.21342 • Published • 11 -
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Paper • 2603.22386 • Published • 54 -
Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought
Paper • 2603.22847 • Published • 25 -
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
Paper • 2603.25804 • Published • 29 -
Natural-Language Agent Harnesses
Paper • 2603.25723 • Published • 24 -
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
Paper • 2603.25730 • Published • 51 -
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 49 -
On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models
Paper • 2603.27481 • Published • 35 -
Make Geometry Matter for Spatial Reasoning
Paper • 2603.26639 • Published • 32 -
TAPS: Task Aware Proposal Distributions for Speculative Sampling
Paper • 2603.27027 • Published • 141 -
Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
Paper • 2603.28376 • Published • 22 -
Embarrassingly Simple Self-Distillation Improves Code Generation
Paper • 2604.01193 • Published • 34 -
CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery
Paper • 2604.01658 • Published • 52 -
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression
Paper • 2604.01609 • Published • 11 -
Communicating about Space: Language-Mediated Spatial Integration Across Partial Views
Paper • 2603.27183 • Published • 20 -
AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks
Paper • 2604.01487 • Published • 9 -
Test-Time Scaling Makes Overtraining Compute-Optimal
Paper • 2604.01411 • Published • 26 -
Self-Distilled RLVR
Paper • 2604.03128 • Published • 154 -
Paper Espresso: From Paper Overload to Research Insight
Paper • 2604.04562 • Published • 9 -
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Paper • 2604.03993 • Published • 39 -
Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies
Paper • 2604.00830 • Published • 14 -
PLUME: Latent Reasoning Based Universal Multimodal Embedding
Paper • 2604.02073 • Published • 15 -
Self-Execution Simulation Improves Coding Models
Paper • 2604.03253 • Published • 30 -
SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Paper • 2604.04804 • Published • 28 -
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Paper • 2604.04921 • Published • 101 -
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Paper • 2604.04771 • Published • 114 -
How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings
Paper • 2604.04323 • Published • 37 -
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 256 -
Experience Transfer for Multimodal LLM Agents in Minecraft Game
Paper • 2604.05533 • Published • 12 -
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Paper • 2604.05404 • Published • 39 -
Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework
Paper • 2604.06170 • Published • 24