TECH·4 days agoA $500 RL fine-tune of a 9B open model beat frontier models on catalog review | Hacker NewsHacker News
PAPER·June 3, 2026AFUN: Towards an Affordance Foundation Model for Functionality UnderstandingHugging Face Papers
PAPER·June 2, 2026On the Scaling of PEFT: Towards Million Personal Models of Trillion ParametersHugging Face Papers
PAPER·June 2, 2026Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language ModelsarXiv
PAPER·May 28, 2026PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity PerspectiveHugging Face Papers
PAPER·May 26, 2026ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM InferencearXiv
PAPER·May 21, 2026Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the RoadHugging Face Papers
