PAPER·May 26, 2026The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT TruncationHugging Face Papers
PAPER·May 25, 2026GenRecon: Bridging Generative Priors for Multi-View 3D Scene ReconstructionHugging Face Papers
PAPER·May 25, 2026SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific ResearchHugging Face Papers
PAPER·May 25, 2026From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language ModelsHugging Face Papers
PAPER·May 25, 2026Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry TransformersHugging Face Papers
PAPER·May 25, 2026The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic ParadigmHugging Face Papers
PAPER·May 25, 2026See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object UnderstandingHugging Face Papers
PAPER·May 25, 2026Geo-Align: Video Generation Alignment via Metric Geometry RewardHugging Face Papers
PAPER·May 25, 2026Rethinking Cross-Layer Information Routing in Diffusion TransformersHugging Face Papers
