3 months agoHugging Face Daily PapersNot All Correct Answers Are Equal: Why Your Distillation Source Matters
3 months agoHugging Face Daily PapersRAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
3 months agoHugging Face Daily PapersVisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
3 months agoAI News CN (Telegram) - English Translation🎬Actor union sues Epic Games for using AI Darth Vader voice in "Fortnite"
3 months agoHugging Face Daily PapersMUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language
3 months agoHugging Face Daily PapersTowards Embodied Cognition in Robots via Spatially Grounded Synthetic Worlds
3 months agoHugging Face Daily PapersVid2World: Crafting Video Diffusion Models to Interactive World Models
3 months agoHugging Face Daily PapersTowards eliciting latent knowledge from LLMs with mechanistic interpretability
3 months agoAI News CN (Telegram) - English Translation🖼 Manus open registration is met with a cold response, and there is no expected time for the Chinese version to be launched.
3 months agoHugging Face Daily PapersScaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
3 months agoHugging Face Daily PapersBreaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?
3 months agoAI News CN (Telegram) - English TranslationGoogle I/O 2025 is about to open. Theme speech video entrance