每天自动聚合 AI 领域最新动态
Spatial return models take the interaction matrix as given and leave feedback uninterpreted. We construct a bandwidth...
Portfolio risk assessment ordinarily relies on reliable estimates of cross-asset return covariances, which are diffic...
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of...
Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring res...
Agent performance depends jointly on the model parameters and the executable harness code that manages context and co...
A language model's prediction of its next token develops across layers, and lens methods track this process by decodi...
Conversational Recommender Systems (CRS) typically require domain-specific dialogue data, which is costly, scarce, an...
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to fi...
Polymeric materials are central to modern technologies, with applications ranging from energy to health and transport...
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model ...
Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve throu...
Large language models now answer medical questions with expert-level performance. However, the context these systems ...