PAPER·June 2, 2026LongAttnComp: Cross-Family Context Compression for Long-Context ReasoningHugging Face Papers
PAPER·June 2, 2026VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time OptimizationHugging Face Papers
PAPER·June 2, 2026Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?Hugging Face Papers
PAPER·June 2, 2026K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean ContextsHugging Face Papers
PAPER·June 2, 2026On the Scaling of PEFT: Towards Million Personal Models of Trillion ParametersHugging Face Papers
PAPER·June 2, 2026RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA ModelsHugging Face Papers
PAPER·June 2, 2026HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White PapersHugging Face Papers
PAPER·June 2, 2026Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference OptimizationHugging Face Papers
PAPER·June 2, 2026Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM AgentsHugging Face Papers
PAPER·June 2, 2026One-Forcing: Towards Stable One-Step Autoregressive Video GenerationHugging Face Papers
