Diffusion Transformers (DiTs) deliver high-fidelity image and video generation, but inference requires many sequential model evaluations. Two acceleration strategies are increasingly important: model compression makes each evaluation cheaper, while adaptive inference avoids selected teacher computation through reuse, f...
Shuai-Qi Cheng, Jia-Hao Zhang, Bo-Yuan Gu et al.· 0 citations
Long-running agents retain KV caches across turns and sessions for hours or days. Compressing these persistent caches requires reducing storage while controlling reconstruction error. We present AlignPred, a codec that combines local alignment with predictive coding under a configurable KV reconstruction-error budget....
Xu Yang, Jia-Peng Zhang, Zhi-Wei Zuo et al.· 1 citation
TRACE is proposed, a score-level evidence verification operator for PRVR that achieves the best SumR on all three benchmarks and improves the DreamPRVR backbone by 1.2, 1.1, and 1.5 points, respectively.
Shuai-Qi Cheng, Si-Yu You, Yan-Bin Wu et al.· 0 citations
Self-Indexing Attention is proposed, a training-free framework built on a shared transform-domain sign-magnitude representation that provides a reusable token-level index for grouped prefill selection and decode retrieval, while the same representation remains compatible with external KV-cache compression without separ...
Xu Yang, Jia-Peng Zhang, Yu-Xi Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.