每天自动聚合 AI 领域最新动态
Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as polic...
How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during L...
Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals ...
We develop a framework for mechanism design with AI agents whose alignment (preferences) and capabilities (feasible a...
Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent...
Dynamic agent harnesses let language models change the software that shapes their own execution. This flexibility bri...
The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining...
Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code...
Traditional frameworks of political communication operate under linear, event-driven assumptions that treat voter per...
Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate synergy between ...
SAR-to-EO image translation aims to generate electro-optical (EO) imagery from synthetic aperture radar (SAR) observa...
Multimodal memory offers a scalable interface for long-video question answering, but existing methods often retrieve ...