每天自动聚合 AI 领域最新动态
Speculative Decoding (SD) accelerates large language model inference by allowing a lightweight draft model to propose...
The deep learning revolution, kicked off by AlexNet, taught us that end-to-end training beats decomposing a problem i...
Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perce...
Forward latent world models predict how actions change a scene, but recover actions for a desired change only through...
Transformers propagate information across depth through a single additive residual stream: every sublayer reads only ...
On-device speech emotion recognition (SER) is critical for real-time applications, yet large self-supervised models t...
We present ShadowDancer, a novel approach to any-action, frame-level control of interactive video world models. The o...
Deep Research agents extend LLM-based assistants into long-horizon workflows involving planning, retrieval, evidence ...
In our prior work, Pedestrian Archetypes, we defined pedestrian archetypes as collections of behaviors that uniquely ...
Deployed LLM agents increasingly keep their long-term memory as a filesystem: a directory tree of markdown files that...
Multimodal large language models increasingly use sketches, annotations, tools, and intermediate images during reason...
Memory is central to long-horizon LLM agents, yet existing memory systems primarily preserve interaction content rath...