PAPER·July 31, 2026ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its ShadowHugging Face Papers
PAPER·July 31, 2026AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion RecognitionHugging Face Papers
PAPER·July 31, 2026LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence LedgerHugging Face Papers
PAPER·July 31, 2026Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End GenerationHugging Face Papers
PAPER·July 31, 2026Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure ModesHugging Face Papers
PAPER·July 31, 2026Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing EvaluationHugging Face Papers
PAPER·July 31, 2026MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction EditingHugging Face Papers
PAPER·July 31, 2026Memory Decoder at Scale: A Pretrained, Parametric Long-Term MemoryHugging Face Papers
PAPER·July 31, 2026Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI AgentsHugging Face Papers
