机器学习
47 篇 · 资讯流BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models
For efficient deployment of large language models (LLMs), methods of ultra-low-bit backbones reduce weight storage, memo
原文 ↗Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration
Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols
原文 ↗ForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic Worlds
Animals build cognitive maps of vast environments, use them to perform map-based navigation, and might even be reusing t
原文 ↗ATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference
Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed sampling b
原文 ↗Unifying Embodied Foundation Models via a Model-to-Policy Formulation
Vision-language-action (VLA) models and world-action models (WAMs) have emerged as promising approaches to robot learnin
原文 ↗Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods a
原文 ↗Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion
Recent advances in robot learning have driven rapid progress in humanoid control, enabling increasingly agile behaviors
原文 ↗UniW(A)M: A Unified Mixture-of-Experts Framework for World and World-Action Models
World models (WMs) and world-action models (WAMs) focus on future world prediction and executable action generation, res
原文 ↗RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions
Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientif
原文 ↗RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation
Pre-trained robot policies, such as Vision-Language-Action (VLA) models, provide a strong foundation for generalist robo
原文 ↗