PAPER·June 2, 2026EVA01: Unified Native 3D Understanding and Generation via Mixture-of-TransformersHugging Face Papers
PAPER·June 2, 2026A Matter of TASTE: Improving Coverage and Difficulty of Agent BenchmarksHugging Face Papers
PAPER·June 2, 2026LongLive-RAG: A General Retrieval-Augmented Framework for Long Video GenerationHugging Face Papers
PAPER·June 2, 2026MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment SimulationHugging Face Papers
PAPER·June 2, 2026OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web AgentsHugging Face Papers
PAPER·June 2, 20263DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via CodeHugging Face Papers
PAPER·June 2, 2026StressDream: Steering Video World Models for Robust Policy Evaluation and ImprovementHugging Face Papers
PAPER·June 2, 2026When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing TradeoffsHugging Face Papers
