AI Agent Papers2026
Evaluates whether agents can search, browse, and combine evidence across the live Web to produce unique factual answers. Its 200 tasks expose persistent weaknesses in long-horizon search and tool coordination.
Jointly selects timesteps, network blocks, and channels from a frozen diffusion model under a channel budget for downstream discriminative tasks. It improves compact features across segmentation, classification, and semantic correspondence.
Improves length generalization in looped language models by aligning each iteration with a specific intermediate state and anchoring recurrent-state scale. On swap-S₅, a model trained on up to 32 moves reaches 95.5% accuracy at 512 moves.
AI Agent Papers2026
Coordinates parallel subagents to tackle long-horizon tasks, then checks progress and evidence to revise its approach. It also supports exploratory science with inspectable research artifacts.
AI Video Papers2026
Songlin Yang, Zhe Wang +9MMLab@HKUST, The Hong Kong University of Science and Technology, Tencent Video +1
Trains video diffusion models to use multimodal language-model representations for generating video from sparse inputs and controlling factors such as characters, scenes, actions, and camera movement.