PAPER·yesterdayA Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, ForeverHugging Face Papers
PAPER·yesterdayJarvisHub: An Open Harness for Canvas-Native Multimodal Creative AgentsHugging Face Papers
PAPER·yesterdayDecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data RecipesHugging Face Papers
PAPER·yesterdayFrom Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic SearchHugging Face Papers
PAPER·yesterdayOmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint GenerationHugging Face Papers
PAPER·yesterdayClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical UnderstandingHugging Face Papers
PAPER·yesterdayProgress Reward Modeling for Robotic Learning: A Comprehensive SurveyHugging Face Papers
PAPER·yesterdayDriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style IdentificationHugging Face Papers
PAPER·yesterdayStateAct: Program State, before Pixels, for Long-Horizon Computer-Use AgentsHugging Face Papers
