Research
New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.
Current coding agents fail to handle complex, interdependent specifications like interface compatibility and error handling in long-horizon software development.
Existing evaluations lack human-grounded, fine-grained diagnostics for proactive agent decisions, timing, and intervention quality.
VLA models struggle to incorporate physical dynamics into action generation without high-latency video world model inference.
World models must follow successive commands while preserving history and action consequences, which current methods do not handle well.
Existing unified diffusion models lack effective transfer of visual understanding and generation abilities across paradigms.
Named by an AI from these papers' abstracts.
No papers match these filters. Try another field or a longer range.