PAPER·July 27, 2026Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture ProblemsHugging Face Papers
PAPER·July 27, 2026IDEAgent: Agentic Quality-Diversity Search for Research Idea GenerationHugging Face Papers
PAPER·July 27, 2026PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language ModelsHugging Face Papers
PAPER·July 27, 2026FilmBench: A Film-Grade Benchmark for Cinematic Video GenerationHugging Face Papers
PAPER·July 26, 2026VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token CompressionHugging Face Papers
PAPER·July 25, 2026Streaming Multi-Agent Autoregressive Diffusion Model with World State RegistersHugging Face Papers
PAPER·July 25, 2026Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task ConstructionHugging Face Papers
PAPER·July 25, 2026TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable ManipulationHugging Face Papers
