每天自动聚合 AI 领域最新动态
World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A c...
Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural ...
Existing multi-agent benchmarks primarily test in competitive settings, short-horizon interactions under 20 steps, or...
Scaling language models to long contexts is limited by the quadratic cost of self-attention. Block sparse attention o...
Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over l...
Personalized large language models are often expected to follow explicit style instructions, yet we find that such in...
Adapting large language models to individual users remains challenging due to the tension between fine-grained person...
Jev is a fast, low-cost decision model that answers natural-language questions with choices, binary judgments, and sc...
Reference-based image quality assessment (IQA) metrics aim to reflect how humans perceive the perceptual distance bet...
Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend n...
Preparing high quality training data for foundation models requires scalable pipelines that transform heterogeneous d...
Streaming video understanding requires models to interpret evidence as it arrives, yet current evaluations often repo...