activity
20242026
collaborators

63 papers

cs.CV2026

SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing

Xuanyi Zhou, Qiuyang Mang, Shuo Yang +7

Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sparse attention reduces this cost…

cs.CV2026

Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility

Yiheng Li, Feng Liang, Dan Kondratyuk +3

The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via li…

cs.CL2026

Residual Context Diffusion Language Models

Yuezhou Hu, Harman Singh, Monishwaran Maheswaran +10

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive language models because they can decode multiple tokens in parallel. Howeve…

cs.LG2026

SEED: Targeted Data Selection by Weighted Independent Set

Yuan Zhang, Lifeng Guo, Junwen Pan +5

Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this proble…

cs.LG2026

Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling

Coleman Hooper, Minwoo Kang, Suhong Moon +7

There is a growing demand for agentic AI technologies for a range of downstream applications like customer service and personal assistants. For applications where the agent needs t…

cs.LG2026

Learning, Fast and Slow: Towards LLMs That Adapt Continually

Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal +6

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific informat…