SkillCycle: Co-Evolving Agent Policies and Skill Banks
Research
Research News
New papers, breakthroughs and academic AI research
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
Research
PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong Priors
Research
VIS-Ground: Video Interactive Storytelling with Contextual Grounding
Research
The Confidence Game: Strategic Miscalibration in Human-AI Delegation
Research
How Private is Private? A Comparative Study for Face De-Identification
Research
Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation
Research
The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning
Research
Self-Consuming Generative Models with Co-Evolving Human Preferences
Research
BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation
Research
Controllable Crowd Generation through World-Model Planning
Research
GRC-Net: Global Representation Consistency Network for Unsupervised Multimodal Anomaly Detection
Research