PAPER·2 days agoRSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-ImprovementarXiv
PAPER·2 days agoThe Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic DistillationHugging Face Papers
PAPER·6 days agoFilling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMsarXiv
PAPER·June 2, 2026Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?Hugging Face Papers
PAPER·June 2, 2026From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM CompressionarXiv
TECH·June 1, 2026NVIDIA unveils “Cosmos 3,” a world model for physical AI, in three versions including one for edge useImpress Watch
PAPER·June 1, 2026SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and DialogueHugging Face Papers
TECH·May 30, 2026Making AI chatbots helpful weakens their ability to simulate human behavior, large-scale study findsTHE DECODER
PAPER·May 29, 2026Geometry Matters: 3D Foundation Priors for Learning Semantic CorrespondenceHugging Face Papers
PAPER·May 29, 2026RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable DomainsHugging Face Papers
PAPER·May 29, 2026LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-TrainingHugging Face Papers
