Surgical WAM: A World-Action Model for Data-Efficient Surgical Robot Learning
Learning reliable surgical manipulation policies is bottlenecked by the scarcity of action-labeled demonstrations: te...
每天自动聚合 AI 领域最新动态
Learning reliable surgical manipulation policies is bottlenecked by the scarcity of action-labeled demonstrations: te...
Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoi...
Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mo...
Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging pers...
Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualizatio...
Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often boun...
Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the ...
Omni-modal dialogue models can understand multimodal inputs and synthesize spoken replies, yet their responses remain...
Jigsaw puzzle solving requires jointly reasoning about visual content and geometric constraints, yet existing benchma...
The rapid advancement of artificial intelligence (AI) has significantly accelerated research in time-series analysis,...
Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of...
After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can b...