New methods enhance long video generation quality and consistency

COVERAGE [9]

1. arXiv cs.AI TIER_1 · Bo Ye, Xinyu Cui, Jian Zhao, Tong Wei, Min-Ling Zhang · 2026-05-22 04:00

   DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation

   arXiv:2605.21028v1 Announce Type: cross Abstract: Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed alloca…

2. arXiv cs.AI TIER_1 · Min-Ling Zhang · 2026-05-20 11:01

   DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation

   Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps early frames cached even when the curre…

3. Hugging Face Daily Papers TIER_1 · 2026-05-19 01:28

   PhyWorld: Physics-Faithful World Model for Video Generation

   World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse and realistic visual futures. However, …

4. arXiv cs.CV TIER_1 · Sheng Li, Yang Sui, Junhao Ran, Bo Yuan, Yue Dai, Xulong Tang · 2026-05-22 04:00

   Temporal Aware Pruning for Efficient Diffusion-based Video Generation

   arXiv:2605.17837v2 Announce Type: replace Abstract: Video diffusion models have recently enabled high-quality video generation with ViT-based architectures, but remain computationally intensive because generation requires attention computation over long spatiotemporal sequences. …

5. arXiv cs.CV TIER_1 · Hongzhou Zhu, Min Zhao, Guande He, Hang Su, Chongxuan Li, Jun Zhu · 2026-05-22 04:00

   Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation

   arXiv:2602.02214v3 Announce Type: replace Abstract: To achieve real-time interactive video generation, current methods distill pretrained bidirectional video diffusion models into few-step autoregressive (AR) models, facing an architectural gap when full attention is replaced by …

6. arXiv cs.CV TIER_1 · Linfeng Zhang · 2026-05-20 11:24

   Dynamic Video Generation: Shaping Video Generation Across Time and Space

   Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive resolution sampling has emerged as a promising ac…

7. arXiv cs.CV TIER_1 · Jong Chul Ye · 2026-05-20 08:55

   FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching

   Extending the generation horizon of video diffusion models to long sequences remains a long-standing and important challenge. Existing training-free approaches fall into two categories: extensions of bidirectional models, which are tightly coupled to specific architectures and su…

8. arXiv cs.CV TIER_1 · K. Huang · 2026-05-18 11:28

   Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos

   Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce longer videos. Frame-level autoregressive frameworks, e.g., FIFO-diffusion, offer the advantage of generating infinitely long videos…

9. arXiv cs.CV TIER_1 · Chuanguang Yang · 2026-05-15 14:33

   Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation

   Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them difficult to handle interactive scenarios…