Found 2,475 document(s)
Page 101 of 165
-
Open access biomedical research article published in J Am Heart Assoc....
-
Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while miss the implicit user intent (e.g., "where ...
-
Knowledge distillation can transfer large multimodal models to compact models for autonomous driving, but uniform token-level matching can dilute planning-relevant semantics and amplify teacher errors. We propose RSKD, a...
-
Open access biomedical research article published in Global Spine J....
-
AI agents must decide when another search is worth its cost. Answer-success probabilities capture question difficulty, while this decision requires estimating the additional benefit of search. We introduce SearchHorizonB...
-
Vision--language--action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. However, it remains unclear how to design VLA models, their inference so...
-
Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent learning for rapid reuse. This limitation is...
-
Skills provide LLM agents with reusable procedural knowledge, making appropriate skill selection essential for reliable agent behavior. As skill libraries expand, distinguishing semantically similar candidates becomes in...
-
This paper presents Memory- and Communication-Aware Framework for Long-Context LLM Inference (MCF) that optimizes long-context inference through communication-aware and stage-adaptive KV-cache layout transitions. At the ...
-
In high-stakes domains such as finance, critical information evolves through multi-party interaction. Recovering these changes and their sources is fundamental to reliable speech understanding. Existing speech benchmarks...
-
Coding agents resend a growing context on every model call, and context policies are usually judged by the prompt tokens they save. Executed work also depends on call count and prefix reuse: a caching runtime prefills on...
-
We propose a lending protocol with far fewer risks than existing pool-based lending protocols (e.g., Aave, Compound). In our protocol, lenders and borrowers embody the spirit of decentralization by making competing inter...
-
Quick Response (QR) code deblurring must ultimately recover the encoded payload, yet how accurately the underlying camera motion must be estimated remains an open question. To address this question, we formulate motion-b...
-
User memory helps personalized systems build on their understanding of users over time. In e-commerce, users convey their preferences and needs through both explicit language and implicit interactions with products. We s...
-
Cities must coordinate domains like infrastructure, mobility, environmental management, emergency response, and public services as conditions evolve. An urban Spatio-Temporal Intelligence (STI) system helps the city moni...