A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL Paper • 2606.02398 • Published 4 days ago • 26
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 8 days ago • 188
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction Paper • 2605.26230 • Published 11 days ago • 41
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models Paper • 2605.26632 • Published 10 days ago • 16
MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems Paper • 2605.28732 • Published 9 days ago • 39
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published 17 days ago • 185
ACC: Compiling Agent Trajectories for Long-Context Training Paper • 2605.21850 • Published 15 days ago • 59
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards Paper • 2605.21467 • Published 16 days ago • 204
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization Paper • 2605.17757 • Published 18 days ago • 64
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining Paper • 2605.14747 • Published 22 days ago • 145
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence Paper • 2605.12882 • Published 23 days ago • 270
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance Paper • 2605.00553 • Published May 1 • 17