Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 5 days ago • 406
RankJudge: A Multi-Turn LLM-as-a-Judge Synthetic Benchmark Generator Paper • 2605.21748 • Published 12 days ago • 15
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published 13 days ago • 185
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining Paper • 2605.14747 • Published 18 days ago • 145
Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization Paper • 2605.13641 • Published 19 days ago • 49
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 19 days ago • 269
bihungba1101/grammar-accuracy-qwen3.5-4b-trl-completions Viewer • Updated 13 days ago • 12k • 945 • 1
Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions Paper • 2605.10664 • Published 21 days ago • 9
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 503