每天自动聚合 AI 领域最新动态
This paper presents a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion framework for action and activity r...
Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes,...
Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they perturb inputs, meas...
Recent work in humanoid whole-body control has found success with a simple recipe: retarget human motion to robot kin...
We present a theoretical framework to explain the emergence of inductive reasoning abilities in Transformer language ...
Metacognition is a foundational component of intelligence critical to effective learning, problem solving, decision-m...
Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad ve...
Understanding how complex cognitive functions are organized within artificial systems is central to interpreting larg...
Personal AI assistants on mobile and wearable devices continuously perceive users' daily lives through visual and aud...
Large language models (LLMs) have achieved remarkable performance on high-school and olympiad-style mathematics, yet ...
Recent VLM and VLA systems have improved robotic perception and action prediction, yet long-horizon embodied agents s...
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, bu...