sigma

sigma7863's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 1 day ago

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Paper • 2604.11297 • Published 3 days ago • 91

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation

Paper • 2604.08570 • Published 22 days ago • 120

upvoted 6 papers 5 days ago

OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks

Paper • 2604.08539 • Published 7 days ago • 48

ClawBench: Can AI Agents Complete Everyday Online Tasks?

Paper • 2604.08523 • Published 7 days ago • 254

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Paper • 2604.08364 • Published 7 days ago • 95

Automating Database-Native Function Code Synthesis with LLMs

Paper • 2604.06231 • Published 14 days ago • 17

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 8 days ago • 310

SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Paper • 2604.08377 • Published 7 days ago • 276

upvoted 2 papers 6 days ago

RAGEN-2: Reasoning Collapse in Agentic RL

Paper • 2604.06268 • Published 9 days ago • 63

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

Paper • 2604.04746 • Published 8 days ago • 70

upvoted a collection 6 days ago

VRAG

Collection

6 items • Updated 14 days ago • 10

upvoted a collection 11 days ago

UnifoLM_WBT_Dataset

Collection

8 items • Updated 20 days ago • 83

upvoted 2 collections 12 days ago

Gemma 4

Collection

64 items • Updated 13 days ago • 105

GPT-1900

Collection

Pre-1900 LLMs for physics reasoning. RL models are physics-only; use the SFT model for general chat. Tune temperature (0.6-0.7). • 11 items • Updated 13 days ago • 6

upvoted 3 papers 13 days ago

MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome

Paper • 2603.28407 • Published 16 days ago • 68

Terminal Agents Suffice for Enterprise Automation

Paper • 2604.00073 • Published 15 days ago • 94

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Paper • 2603.24414 • Published 21 days ago • 183

upvoted a paper 15 days ago

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Paper • 2603.19312 • Published Mar 13 • 27

upvoted a collection 15 days ago

LeWM

Collection

Official checkpoints and datasets related to LeWM paper. • 9 items • Updated 19 days ago • 23

upvoted a paper 15 days ago

Towards a Medical AI Scientist

Paper • 2603.28589 • Published 16 days ago • 88