Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning Paper • 2512.24146 • Published 8 days ago • 10 • 2
Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning Paper • 2601.00830 • Published 13 days ago • 2 • 2
DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxies Paper • 2601.02267 • Published 1 day ago • 4 • 2
SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving Paper • 2601.01426 • Published 3 days ago • 16 • 3
GARDO: Reinforcing Diffusion Models without Reward Hacking Paper • 2512.24138 • Published 8 days ago • 25 • 3
InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams Paper • 2601.02281 • Published 1 day ago • 22 • 2
COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs Paper • 2601.01836 • Published 2 days ago • 5 • 2
IMA++: ISIC Archive Multi-Annotator Dermoscopic Skin Lesion Segmentation Dataset Paper • 2512.21472 • Published 13 days ago • 1 • 3
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation Paper • 2601.02204 • Published 2 days ago • 48 • 3
DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer Paper • 2601.01425 • Published 3 days ago • 36 • 3
OpenNovelty: An LLM-powered Agentic System for Verifiable Scholarly Novelty Assessment Paper • 2601.01576 • Published 3 days ago • 2 • 1
Selective Imperfection as a Generative Framework for Analysis, Creativity and Discovery Paper • 2601.00863 • Published 8 days ago • 1 • 3
Project Ariadne: A Structural Causal Framework for Auditing Faithfulness in LLM Agents Paper • 2601.02314 • Published 1 day ago • 2
Prithvi-Complimentary Adaptive Fusion Encoder (CAFE): unlocking full-potential for flood inundation mapping Paper • 2601.02315 • Published 1 day ago • 2
Confidence Estimation for LLMs in Multi-turn Interactions Paper • 2601.02179 • Published 2 days ago • 9 • 2