PAPER·9 hours agoTILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic RewardHugging Face Papers
PAPER·10 hours agoUltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language ModelsHugging Face Papers
PAPER·11 hours agoWorldDiT: A Unified Diffusion Architecture for World and Action ModelingHugging Face Papers
PAPER·13 hours agoTRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMsHugging Face Papers
PAPER·19 hours agoReasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning ModelsHugging Face Papers
PAPER·19 hours agoSol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention SparsificationHugging Face Papers
PAPER·20 hours agoChamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed SamplingHugging Face Papers
PAPER·21 hours agoCodifying the Judge: Scalable Evaluation via Program DistillationHugging Face Papers
PAPER·22 hours agoThe Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic DistillationHugging Face Papers
PAPER·22 hours agoEvidence Attribution in Visual Document Understanding without Coordinates or Region LabelsHugging Face Papers
