about 2 months agoHugging Face Daily PapersMed-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
about 2 months agoHugging Face Daily PapersLearning a Continue-Thinking Token for Enhanced Test-Time Scaling
about 2 months agoHugging Face Daily PapersFine-Grained Perturbation Guidance via Attention Head Selection
about 2 months agoHugging Face Daily PapersAutoMind: Adaptive Knowledgeable Agent for Automated Data Science
about 2 months agoHugging Face Daily PapersChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
about 2 months agoHugging Face Daily PapersSWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
about 2 months agoHugging Face Daily PapersDomain2Vec: Vectorizing Datasets to Find the Optimal Data Mixture without Training
about 2 months agoHugging Face Daily PapersFedNano: Toward Lightweight Federated Tuning for Pretrained Multimodal Large Language Models
about 2 months agoHugging Face Daily PapersDecomposing MLP Activations into Interpretable Features via Semi-Nonnegative Matrix Factorization
about 2 months agoHugging Face Daily PapersNoLoCo: No-all-reduce Low Communication Training Method for Large Models