Research · 5 October 2026 Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Hugging Face
Research · 5 October 2026 How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows Hugging Face
Research · 5 October 2026 Coding Agents for Generalized Task and Motion Planning Problems Hugging Face
Research · 5 October 2026 AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation Hugging Face
Research · 5 October 2026 IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis Hugging Face
Research · 5 October 2026 Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes Hugging Face
Research · 5 October 2026 ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research Hugging Face
Research · 5 October 2026 Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation Hugging Face
Research · 5 October 2026 Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models Hugging Face
Research · 5 October 2026 Open-sourcing AstaBrief, the fast report-generation model in Asta Hugging Face
Research · 5 October 2026 Attempts to Keep Humans in the AI Loop May Actually Push Them Out IEEE Spectrum
Research · 5 October 2026 Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle Google Research
