每天自动聚合 AI 领域最新动态
A central bottleneck in multi-hop Question Answering (QA) is that the granularity at which a question is expressed of...
While unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model, fun...
Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled ro...
Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends...
AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but eviden...
We present H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world m...
Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environ...
Robotic manipulation faces a fundamental scaling challenge: robust generalization demands broad physical experience, ...
We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Dr...
Multimodal GUI agents have emerged as a promising paradigm for digital task automation, yet transitioning from benchm...
This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirement...
Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at f...