arXiv:2609.38140v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes tokens independently within a homogeneous expert pool and re…
Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes tokens independently within a homogeneous expert pool and regularizes expert usage toward uniformity, making i…
arXiv:2609.38978v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have become a dominant architecture for video generation, but their efficiency is limited by the quadratic complexity of full attention. Sparse attention reduces this cost by retrieving important blocks…
arXiv:2609.39096v1 Announce Type: new Abstract: Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows with the generated history. Existing compression strategies discard history using fixed windows or select tokens through lo…
arXiv cs.CV
TIER_1English(EN)·Ping Liu, Chi Zhang·
arXiv:2609.36832v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can generate realistic depictions of actions such as kicking, stabbing, and shooting, raising safety concerns that motivate targeted concept erasure. Although concept erasure has been extensively…
arXiv:2609.38114v1 Announce Type: new Abstract: Autoregressive video diffusion enables interactive streaming generation, but suffers from error accumulation over long rollouts. Self-rollout training reduces exposure bias, yet finite rollouts leave long-range drift unresolved. We …
