每天自动聚合 AI 领域最新动态
Language models hold latent quantities in a form they can report on, and more of a quantity is present in that form w...
Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as th...
We present AnyTalk, a novel method for generating 3D speech animations for arbitrary characters without requiring any...
In collection operations, accumulating payload progressively slows the vehicle, imposing a cumulative penalty on rout...
Boundary representation (B-Rep) generation is a fundamental task in computer-aided design, yet the direct synthesis o...
As AI datacenters retire functional GPUs, vast quantities of still capable accelerators enter secondary markets. This...
Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training languag...
Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strate...
Learning to generate or reconstruct explorable worlds requires video paired with more than RGB: camera motion, scene ...
Despite recent advances in unified multimodal models for multi-reference image generation, existing benchmarks remain...
Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended...
AI has long assisted scientific research, but the rapid advance of LLMs and agentic scaffolds is reshaping the landsc...