人工智能
83 篇 · 资讯流From Pixel to Poses: Object-centric Tool Manipulation Learning from Human Demonstrations
Scaling up robotic manipulation is primarily bottlenecked by the scarcity of real-world robot data. While recent approac
原文 ↗Jailbreaks for Black-Box Uncertainty Quantification in Large Reasoning Models
While Large Reasoning Models (LRMs) excel at complex reasoning, alignment through reinforcement learning often induces s
原文 ↗TempoKV: Timely Staging of LLM KV Caches for Memory-Semantic Flash
Reusable prefix key-value (KV) caches can outgrow GPU memory in large language model (LLM) serving. A memory-semantic fl
原文 ↗JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments
In complex embodied visual reasoning scenarios, an agent often has only a limited field of view, and the evidence needed
原文 ↗WeaveData: A Multimodal Data Analysis System with Self-Critiquing and Self-Evolving LLM Plans
Multimodal data analysis, which answers questions over relational tables, text, and images, has attracted growing attent
原文 ↗Dynamic Flow, Static Graph: KV Cache Reuse for Efficient LLM Serving on Mobile NPUs
On-device large language model (LLM) serving is a cornerstone of local-first personal intelligence, offering users data
原文 ↗Nereus: Adaptive Parallelism for LLM Post-Training
Reinforcement learning (RL) post-training for large language models (LLMs) coordinates multiple models across generation
原文 ↗DataMagic: Authoring Data Videos through Declarative Multi-Agent Orchestration
Data videos communicate data insights through dynamic charts, voice narration, and synchronized animations, and have bec
原文 ↗Robust Hierarchical Structures for Agentic Document Analysis
Large Language Models (LLMs) enable us to better understand text documents, including PDFs and Word documents. However,
原文 ↗GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI
Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity incre
原文 ↗