about 2 months agoHugging Face Daily PapersReward Models Enable Scalable Code Verification by Trading Accuracy for Throughput
about 2 months agoHugging Face Daily PapersInterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions
about 2 months agoHugging Face Daily PapersV-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
about 2 months agoHugging Face Daily PapersSRLAgent: Enhancing Self-Regulated Learning Skills through Gamification and LLM Assistance
about 2 months agoHugging Face Daily PapersKvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy
about 2 months agoHugging Face Daily PapersUniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting
about 2 months agoHugging Face Daily PapersVerIF: Verification Engineering for Reinforcement Learning in Instruction Following
about 2 months agoAI News CN (Telegram) - English TranslationSam Altman believes that the AI industry will develop "new insights" next year.
about 2 months agoHugging Face Daily PapersSAFE: Multitask Failure Detection for Vision-Language-Action Models
2 months agoHugging Face Daily PapersEmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection
2 months agoHugging Face Daily PapersVision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
2 months agoAI News CN (Telegram) - English Translation🤖AI Field Dynamics: Tencent Music acquires Himalaya, and ByteDance releases Doubao Large Model 1.6