GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
Paper • 2503.14734 • Published • 7
papers
-
-
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
Paper • 2401.02117 • Published • 33 -
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Paper • 2506.01844 • Published • 158 -
Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
Paper • 2506.16035 • Published • 89 -
Deep Researcher with Test-Time Diffusion
Paper • 2507.16075 • Published • 68 -
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
Paper • 2507.18553 • Published • 41 -
MMBench-GUI: Hierarchical Multi-Platform Evaluation Framework for GUI Agents
Paper • 2507.19478 • Published • 33 -
CLEAR: Error Analysis via LLM-as-a-Judge Made Easy
Paper • 2507.18392 • Published • 20 -
PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving
Paper • 2507.17596 • Published • 7 -
Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement
Paper • 2507.18742 • Published • 6 -
Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI
Paper • 2507.10510 • Published • 5 -
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Paper • 2507.19457 • Published • 30 -
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report
Paper • 2507.16534 • Published • 9 -
A Survey of Context Engineering for Large Language Models
Paper • 2507.13334 • Published • 263 -
GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
Paper • 2507.01006 • Published • 254 -
Group Sequence Policy Optimization
Paper • 2507.18071 • Published • 320 -
Scaling RL to Long Videos
Paper • 2507.07966 • Published • 162 -
MemOS: A Memory OS for AI System
Paper • 2507.03724 • Published • 166 -
Kwai Keye-VL Technical Report
Paper • 2507.01949 • Published • 132 -
GUI-G^2: Gaussian Reward Modeling for GUI Grounding
Paper • 2507.15846 • Published • 135 -
Beyond Context Limits: Subconscious Threads for Long-Horizon Reasoning
Paper • 2507.16784 • Published • 123 -
T-LoRA: Single Image Diffusion Model Customization Without Overfitting
Paper • 2507.05964 • Published • 121 -
MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization
Paper • 2507.14683 • Published • 136 -
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
Paper • 2410.10813 • Published • 16 -
LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?
Paper • 2506.11928 • Published • 25 -
Defeating Prompt Injections by Design
Paper • 2503.18813 • Published • 25 -
Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents
Paper • 2505.22954 • Published • 15 -
Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis
Paper • 2505.11581 • Published • 3 -
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
Paper • 2408.06292 • Published • 128 -
Evaluating Large Language Models Trained on Code
Paper • 2107.03374 • Published • 10 -
Self-Refine: Iterative Refinement with Self-Feedback
Paper • 2303.17651 • Published • 2 -
Gorilla: Large Language Model Connected with Massive APIs
Paper • 2305.15334 • Published • 6 -
HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in HuggingFace
Paper • 2303.17580 • Published • 15 -
Communicative Agents for Software Development
Paper • 2307.07924 • Published • 6 -
AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Paper • 2308.08155 • Published • 11 -
The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
Paper • 2509.09677 • Published • 37 -
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
Paper • 2510.05592 • Published • 110 -
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Paper • 2505.03335 • Published • 191 -
Inference-Time Scaling for Generalist Reward Modeling
Paper • 2504.02495 • Published • 58 -
BAP v2: An Enhanced Task Framework for Instruction Following in Minecraft Dialogues
Paper • 2501.10836 • Published • 1 -
Executable Code Actions Elicit Better LLM Agents
Paper • 2402.01030 • Published • 192 -
DynaSaur: Large Language Agents Beyond Predefined Actions
Paper • 2411.01747 • Published • 37 -
If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents
Paper • 2401.00812 • Published • 12 -
Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents
Paper • 2510.24702 • Published • 31 -
Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLM
Paper • 2509.18058 • Published • 12 -
Speculative Safety-Aware Decoding
Paper • 2508.17739 • Published -
Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
Paper • 2508.10029 • Published -
Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
Paper • 2508.10031 • Published -
Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
Paper • 2508.20333 • Published -
Mitigating Jailbreaks with Intent-Aware LLMs
Paper • 2508.12072 • Published -
D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models
Paper • 2509.17938 • Published • 4 -
A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
Paper • 2509.14297 • Published -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 513 -
HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation
Paper • 2412.21199 • Published • 13 -
Solving Inequality Proofs with Large Language Models
Paper • 2506.07927 • Published • 20 -
ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
Paper • 2510.24592 • Published • 17 -
FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language
Paper • 2506.20920 • Published • 78 -
GAIA: a benchmark for General AI Assistants
Paper • 2311.12983 • Published • 247 -
AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance
Paper • 2506.03828 • Published • 20 -
MMGR: Multi-Modal Generative Reasoning
Paper • 2512.14691 • Published • 121 -
Next-Embedding Prediction Makes Strong Vision Learners
Paper • 2512.16922 • Published • 89 -
mHC: Manifold-Constrained Hyper-Connections
Paper • 2512.24880 • Published • 322 -
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Paper • 2502.02737 • Published • 258 -
Helios: Real Real-Time Long Video Generation Model
Paper • 2603.04379 • Published • 186 -
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
Paper • 2604.11804 • Published • 69 -
ATANT: An Evaluation Framework for AI Continuity
Paper • 2604.06710 • Published • 1 -
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
Paper • 2604.10539 • Published • 2 -
SHARE: Social-Humanities AI for Research and Education
Paper • 2604.11152 • Published • 1 -
How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models
Paper • 2604.04385 • Published • 1 -
SPASM: Stable Persona-driven Agent Simulation for Multi-turn Dialogue Generation
Paper • 2604.09212 • Published • 3 -
Counting to Four is still a Chore for VLMs
Paper • 2604.10039 • Published • 2 -
ADD for Multi-Bit Image Watermarking
Paper • 2604.11491 • Published • 3 -
Continuous Adversarial Flow Models
Paper • 2604.11521 • Published • 8 -
Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data Generation
Paper • 2604.11290 • Published • 2 -
CocoaBench: Evaluating Unified Digital Agents in the Wild
Paper • 2604.11201 • Published • 33 -
CodeTracer: Towards Traceable Agent States
Paper • 2604.11641 • Published • 38 -
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Paper • 2604.10949 • Published • 38 -
Zero-shot World Models Are Developmentally Efficient Learners
Paper • 2604.10333 • Published • 7 -
Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
Paper • 2604.02340 • Published • 7 -
General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
Paper • 2604.11778 • Published • 8 -
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
Paper • 2604.09557 • Published • 10 -
Efficient RL Training for LLMs with Experience Replay
Paper • 2604.08706 • Published • 17 -
From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
Paper • 2604.09459 • Published • 12 -
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator
Paper • 2604.08121 • Published • 42 -
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
Paper • 2604.09132 • Published • 50 -
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation
Paper • 2604.10098 • Published • 74 -
Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
Paper • 2604.11259 • Published • 12 -
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
Paper • 2604.11753 • Published • 14 -
TRACE: Capability-Targeted Agentic Training
Paper • 2604.05336 • Published • 13 -
Panoptic Pairwise Distortion Graph
Paper • 2604.11004 • Published • 2 -
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Paper • 2604.11544 • Published • 3 -
TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
Paper • 2604.08921 • Published • 2 -
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
Paper • 2604.10718 • Published • 4 -
DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain
Paper • 2604.10425 • Published • 3 -
BMdataset: A Musicologically Curated LilyPond Dataset
Paper • 2604.10628 • Published • 2 -
Learning Long-term Motion Embeddings for Efficient Kinematics Generation
Paper • 2604.11737 • Published • 6 -
Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
Paper • 2604.11446 • Published • 4 -
SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Paper • 2604.11716 • Published • 4 -
Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind
Paper • 2604.11666 • Published • 4 -
Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series
Paper • 2604.10799 • Published • 6 -
Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
Paper • 2604.11547 • Published • 5 -
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
Paper • 2604.10784 • Published • 6 -
SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
Paper • 2604.10688 • Published • 25 -
Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation
Paper • 2604.10030 • Published • 14 -
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
Paper • 2604.11805 • Published • 16 -
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
Paper • 2604.10480 • Published • 20 -
Introspective Diffusion Language Models
Paper • 2604.11035 • Published • 20 -
Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
Paper • 2604.10905 • Published • 26 -
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Paper • 2604.11297 • Published • 135 -
QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation
Paper • 2604.08570 • Published • 121