Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 10 days ago • 192
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment Paper • 2605.20834 • Published 18 days ago • 5
On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists Paper • 2605.20668 • Published 18 days ago • 12
Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning Paper • 2605.11458 • Published 26 days ago • 7
DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents Paper • 2605.04808 • Published May 6 • 20
Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 233
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills Paper • 2604.05333 • Published Apr 7 • 22
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 506
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 115
Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells Paper • 2603.25240 • Published Mar 26 • 77