每天自动聚合 AI 领域最新动态
In LLM-agent opinion simulations, each agent reports the probability that a claim is true after seeing its own previo...
Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existin...
Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but its cost ...
While multimodal contrastive models like CLIP and CLAP successfully learn shared representations, their embeddings ty...
Large Language Models (LLMs) are increasingly used to optimize code for performance. This practice often assumes that...
Statement autoformalization translates mathematics from natural language into a proof assistant such as Lean 4, and m...
Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by t...
Large language model (LLM) platforms introducing advertising must decide how much capability ad revenue should fund a...
Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that...
Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperatio...
Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under dive...
Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language...