每天自动聚合 AI 领域最新动态
We introduce HyperBrowseComp, a multilingual and multimodal browsing benchmark comprising 423 manually authored and h...
Existing Simulink benchmarks mainly evaluate whether generated models compile, execute, or resemble a reference model...
World simulation is inherently multisensory, demanding synchronized visual and acoustic dynamics in real time. Yet pr...
We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometr...
Masked diffusion language models (dLMs) offer a promising parallel alternative to autoregressive models for complex r...
Typed decision models answer schema-constrained questions about a text in one forward pass and return probabilities m...
World action models integrate future visual dynamics with robot action prediction, but their scalability remains limi...
As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challe...
Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulat...
Video generation models (VGMs) offer strong spatiotemporal priors for embodied observation--action modeling. However,...
Chain-of-thought (CoT) reasoning allows humans to inspect how large language models reach their answers, and oversee ...
Existing online video segmentation methods struggle to track objects in long, complex videos with long-term occlusion...