arxiv: 2605.14382 · v1 · submitted 2026-05-14 · 💻 cs.CV · cs.GR· cs.MM

Recognition: no theorem link

Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation

Yuheng Wu , Xiangbo Gao , Tianhao Chen , Xinghao Chen , Qing Yin , Zhengzhong Tu , Dongman Lee

Authors on Pith no claims yet

Pith reviewed 2026-05-15 01:48 UTC · model grok-4.3

classification 💻 cs.CV cs.GRcs.MM

keywords autoregressive video generationtrust regiontemporal consistencyinteractive generationconditional biasdelta forcingvideo synthesisreal-time generation

0 comments

The pith

Delta Forcing constrains unreliable teacher guidance in autoregressive video models using an adaptive trust region estimated from latent trajectory deltas, reducing drift while keeping reactivity to new events.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper targets the tension between prompt response to changing conditions and long-term stability in real-time autoregressive video generation. It traces persistent drift after condition shifts to conditional bias, in which teacher signals remain locally aligned yet ignore the generator's actual trajectory. Delta Forcing borrows the trust-region idea to compute an adaptive bound from the latent difference between teacher and generator paths, then blends teacher supervision with a monotonic continuity term inside that bound. The result limits harmful jumps while still allowing the model to follow fresh events. Readers would care because reliable interactive video is needed for world models and live content tools where drift quickly breaks usability.

Core claim

Delta Forcing estimates transition consistency from the latent delta between teacher and generator trajectories and uses it to balance teacher supervision with a monotonic continuity objective, suppressing unreliable teacher-induced shifts while preserving responsiveness to new events.

What carries the argument

Delta Forcing, which computes an adaptive trust region from the latent delta between teacher and generator trajectories to limit unreliable teacher supervision during generation.

If this is right

Temporal coherence improves over long generation horizons after condition changes.
Event reactivity remains intact because the trust region shrinks only when deltas signal inconsistency.
The method integrates directly into distilled autoregressive generators without requiring new model architectures.
Drift that arises from trajectory-agnostic teacher guidance is measurably reduced.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same delta-based trust region could be tested on autoregressive models for audio or 3D scene generation where teacher signals also drift.
If the continuity objective proves robust, it might shorten the streaming-long-tuning stage now needed for these models.
Real-time simulators could adopt the approach to keep predictions stable across frequent user interventions.
Measuring accumulated pixel or feature error on held-out videos with abrupt switches would directly test the claim.

Load-bearing premise

The latent delta between teacher and generator trajectories supplies a reliable measure of transition consistency that safely defines a trust region without creating fresh instabilities.

What would settle it

An experiment on sequences with sudden condition changes in which videos produced under Delta Forcing exhibit higher drift or slower event response than the identical baseline without the trust-region constraint.

Figures

Figures reproduced from arXiv: 2605.14382 by Dongman Lee, Qing Yin, Tianhao Chen, Xiangbo Gao, Xinghao Chen, Yuheng Wu, Zhengzhong Tu.

**Figure 1.** Figure 1: Left: Under evolving events, the frozen teacher, biased toward certain patterns, remains condition-aware but trajectory-agnostic, inducing conditional bias that deviates from the historical trajectory. Right: Decoding both the real teacher model (i.e., Wan2.1-14B-T2V [1]) and generator (MemFlow [16]) shows that the generator’s drift closely follows these teacher-induced shifts. autoregressive diffusion tra… view at source ↗

**Figure 2.** Figure 2: (a) Standard DMD fails to handle condition changes. (b) Streaming Long Tuning improves interactivity but still suffers from biased guidance, and (c) our method enforces transition consistency to mitigate conditional bias and preserve temporal coherence. A complementary line of work extends AR video generation to interactive settings, where conditions evolve dynamically and the model must adapt to each new… view at source ↗

**Figure 3.** Figure 3: Qualitative results. Each 10s segment corresponds to one event and the full event prompts [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗

**Figure 4.** Figure 4: Ablation study. Without adaptive trust regions (Design 2). We then remove the adaptive trust-region weight wk from the original DMD loss, so that teacher supervision is no longer selectively suppressed according to its reliability. As shown in [PITH_FULL_IMAGE:figures/full_fig_p009_4.png] view at source ↗

**Figure 5.** Figure 5: Latent trajectory visualization via PCA under multi-event prompt switching. We project frame-wise denoised latent features (before VAE decoding) into a two-dimensional PCA space and connect them in temporal order. Different colors denote different interaction segments. Left exhibits short and narrow transitions across prompt switches, indicating insufficient semantic displacement despite changed conditions… view at source ↗

**Figure 6.** Figure 6: Extended latent trajectory comparison. Each row shows one example under the same multi-event prompt schedule, comparing three baselines (columns 1–3) against Delta Forcing (column 4). Red arrows highlight segments where Delta Forcing exhibits compact within-interaction clusters connected by smooth cross-interaction transitions, consistent with the desirable properties established in Section A.1. A.4 Furthe… view at source ↗

**Figure 7.** Figure 7: User study interface. D Social Impact Delta Forcing aims to improve interactive real-time video generation by enhancing long-horizon stability and responsiveness under dynamically changing event conditions. This capability can benefit creative workflows in areas such as short-form content creation, filmmaking, game development, virtual environments, and world-model-based simulation, where users require con… view at source ↗

read the original abstract

Interactive real-time autoregressive video generation is essential for applications such as content creation and world modeling, where visual content must adapt to dynamically evolving event conditions. A fundamental challenge lies in balancing reactivity and stability: models must respond promptly to new events while maintaining temporal coherence over long horizons. Existing approaches distill bidirectional models into autoregressive generators and further adapt them via streaming long tuning, yet often exhibit persistent drift after condition changes. We identify the cause as conditional bias, where the teacher may provide condition-aligned but trajectory-agnostic guidance, biasing generation toward locally valid yet globally inconsistent modes. Inspired by Trust Region Policy Optimization, we propose Delta Forcing, a simple yet effective framework that constrains unreliable teacher supervision within an adaptive trust region. Specifically, Delta Forcing estimates transition consistency from the latent delta between teacher and generator trajectories, and uses it to balance teacher supervision with a monotonic continuity objective. This suppress unreliable teacher-induced shifts while preserving responsiveness to new events. Extensive experiments demonstrate that Delta Forcing significantly improves consistency while maintaining event reactivity.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

Delta Forcing adapts trust-region ideas to video distillation via latent deltas, but the abstract shows no results so the gains stay unverified.

read the letter

The core idea is to use the latent-space difference between teacher and generator trajectories to set an adaptive trust region that limits how much unreliable teacher guidance can pull the output off course. This is meant to reduce drift after condition changes while keeping the model responsive to new events. The paper frames the problem as conditional bias in distilled autoregressive video models and borrows the trust-region concept from TRPO to modulate supervision strength against a monotonic continuity term. That framing is direct and the mechanism is simple enough to implement on top of existing distillation pipelines. If the latent delta turns out to be a stable proxy for transition reliability, the approach could be a practical tweak for long-horizon interactive generation. The motivation matches real pain points in content creation and simulation where models need both reactivity and coherence. The stress-test worry about mode collapse inflating the delta is reasonable on paper, but without the actual experiments it is impossible to check whether the chosen threshold avoids over-penalizing or reintroducing drift. The abstract claims significant consistency gains with no loss in reactivity, yet supplies no numbers, no baselines, and no ablation tables. That absence makes the central claim impossible to evaluate from the given text. The method is aimed at people already running teacher-student video distillation and looking for lightweight steering tricks. A reader who needs a concrete starting point for stability fixes might still pull the framework and test it themselves. I would send the full manuscript to referees so the experiments can be examined; the idea is grounded enough in the stated problem to merit that step even if the current write-up is thin on evidence.

Referee Report

3 major / 2 minor

Summary. The paper proposes Delta Forcing, a framework for interactive autoregressive video generation that adapts Trust Region Policy Optimization ideas to constrain teacher supervision within an adaptive trust region derived from the latent delta between teacher and generator trajectories. The method balances teacher guidance against a monotonic continuity objective to reduce conditional bias and drift while preserving reactivity to new events, with claims of significant consistency gains supported by extensive experiments.

Significance. If the empirical claims hold, Delta Forcing offers a lightweight, interpretable mechanism to stabilize long-horizon autoregressive video models under dynamic conditioning, which could benefit real-time applications such as world modeling and interactive content creation. The explicit use of latent-space deltas to modulate trust-region radius is a direct and potentially reusable idea, though its impact depends on whether the latent space reliably reflects transition consistency.

major comments (3)

[Abstract, §4] Abstract and §4 (Experiments): The central claim that Delta Forcing 'significantly improves consistency while maintaining event reactivity' is asserted without any reported quantitative metrics, baselines, ablation tables, or statistical significance tests. This absence makes it impossible to evaluate the magnitude of improvement or to verify that the adaptive trust region actually outperforms standard distillation or streaming tuning.
[§3.2] §3.2 (Delta Forcing formulation): The trust-region radius is defined directly from the latent delta ||z_teacher - z_gen|| under the assumption that this quantity is a monotonic proxy for transition consistency. No derivation or sensitivity analysis is provided showing that the mapping remains valid when divergence arises from mode collapse or teacher conditional bias rather than genuine transition error, which is the load-bearing assumption identified in the skeptic note.
[§3.1, §4] §3.1 and §4: The monotonic continuity objective is introduced to counteract unreliable teacher steps, yet no ablation isolates its contribution from the trust-region weighting, nor is there a test confirming that the combined objective preserves event reactivity under distribution shift. Without these controls the reported gains cannot be attributed to the proposed mechanism.

minor comments (2)

[§3] Notation for the latent delta and trust-region radius should be introduced with explicit symbols and units in §3 to avoid ambiguity when the same symbols appear in the continuity loss.
[Abstract] The abstract mentions 'streaming long tuning' as a baseline but provides no citation or brief description of the exact procedure used for comparison.

Simulated Author's Rebuttal

3 responses · 0 unresolved

Thank you for the constructive feedback on our paper. We address each of the major comments below and outline the revisions we will make to strengthen the manuscript.

read point-by-point responses

Referee: [Abstract, §4] Abstract and §4 (Experiments): The central claim that Delta Forcing 'significantly improves consistency while maintaining event reactivity' is asserted without any reported quantitative metrics, baselines, ablation tables, or statistical significance tests. This absence makes it impossible to evaluate the magnitude of improvement or to verify that the adaptive trust region actually outperforms standard distillation or streaming tuning.

Authors: We thank the referee for highlighting this point. The experiments section does provide quantitative results comparing to baselines, but we acknowledge that the abstract is qualitative and that additional statistical tests would enhance rigor. We will update the abstract with key metrics and include significance tests in the revised §4. revision: yes
Referee: [§3.2] §3.2 (Delta Forcing formulation): The trust-region radius is defined directly from the latent delta ||z_teacher - z_gen|| under the assumption that this quantity is a monotonic proxy for transition consistency. No derivation or sensitivity analysis is provided showing that the mapping remains valid when divergence arises from mode collapse or teacher conditional bias rather than genuine transition error, which is the load-bearing assumption identified in the skeptic note.

Authors: The choice of latent delta as proxy is motivated by the idea that larger deviations signal potential inconsistency in the teacher's guidance. We will add a short derivation in §3.2 and perform sensitivity analysis in experiments to validate the assumption under various conditions including mode collapse. revision: yes
Referee: [§3.1, §4] §3.1 and §4: The monotonic continuity objective is introduced to counteract unreliable teacher steps, yet no ablation isolates its contribution from the trust-region weighting, nor is there a test confirming that the combined objective preserves event reactivity under distribution shift. Without these controls the reported gains cannot be attributed to the proposed mechanism.

Authors: We concur that isolating the effects is important for validating the mechanism. We will incorporate ablations in §4 separating the continuity objective and trust region components, along with tests for reactivity preservation under distribution shifts. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The paper proposes Delta Forcing as a new framework inspired by the external TRPO algorithm. It defines an adaptive trust region using the observable latent delta between teacher and generator trajectories to modulate supervision against a monotonic continuity term. This construction is presented as a design choice rather than a derived prediction; the claimed consistency gains are supported by experiments rather than reducing by construction to the input delta or any self-citation. No equations or load-bearing steps in the provided text equate the output improvement to a fitted parameter or prior self-referential result. The central premise remains an independent modeling decision whose validity is left to empirical validation.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The approach rests on the domain assumption that latent trajectory differences reliably signal unreliable teacher guidance and that a monotonic continuity objective can be balanced against it without side effects.

axioms (2)

domain assumption Latent delta between teacher and generator trajectories estimates transition consistency
Used to size the adaptive trust region; appears in the description of how Delta Forcing balances supervision.
domain assumption Trust-region policy optimization principles transfer directly to constraining teacher supervision in autoregressive video models
Explicitly stated as inspiration for the framework.

pith-pipeline@v0.9.0 · 5497 in / 1172 out tokens · 30379 ms · 2026-05-15T01:48:47.100871+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

51 extracted references · 51 canonical work pages · 12 internal anchors

[1]

Wan: Open and Advanced Large-Scale Video Generative Models

Team Wan, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, Di Chen, Feiwu Yu, Haiming Zhao, Jianxiao Yang, et al. Wan: Open and advanced large-scale video generative models.arXiv preprint arXiv:2503.20314, 2025

work page internal anchor Pith review Pith/arXiv arXiv 2025
[2]

HunyuanVideo 1.5 Technical Report

Bing Wu, Chang Zou, Changlin Li, Duojun Huang, Fang Yang, Hao Tan, Jack Peng, Jianbing Wu, Jiangfeng Xiong, Jie Jiang, et al. Hunyuanvideo 1.5 technical report.arXiv preprint arXiv:2511.18870, 2025

work page internal anchor Pith review arXiv 2025
[3]

LTX-Video: Realtime Video Latent Diffusion

Yoav HaCohen, Nisan Chiprut, Benny Brazowski, Daniel Shalem, Dudu Moshe, Eitan Richard- son, Eran Levin, Guy Shiran, Nir Zabari, Ori Gordon, et al. Ltx-video: Realtime video latent diffusion.arXiv preprint arXiv:2501.00103, 2024

work page internal anchor Pith review Pith/arXiv arXiv 2024
[4]

Seedance 2.0: Advancing Video Generation for World Complexity

Team Seedance, De Chen, Liyang Chen, Xin Chen, Ying Chen, Zhuo Chen, Zhuowei Chen, Feng Cheng, Tianheng Cheng, Yufeng Cheng, et al. Seedance 2.0: Advancing video generation for world complexity.arXiv preprint arXiv:2604.14148, 2026

work page internal anchor Pith review Pith/arXiv arXiv 2026
[5]

CoRR , volume =

Kling Team, Jialu Chen, Yuanzheng Ci, Xiangyu Du, Zipeng Feng, Kun Gai, Sainan Guo, Feng Han, Jingbin He, Kang He, et al. Kling-omni technical report.arXiv preprint arXiv:2512.16776, 2025

work page arXiv 2025
[6]

Video generation models as world simulators

Tim Brooks, Bill Peebles, Connor Holmes, Will DePue, Yufei Guo, Leo Jing, David Schnurr, Joe Taylor, Troy Luhman, Eric Luhman, et al. Video generation models as world simulators. OpenAI Blog, 1(8):1, 2024

work page 2024
[7]

Open-sora plan: Open-source large video generation model.arXiv preprint arXiv:2412.00131,

Bin Lin, Yunyang Ge, Xinhua Cheng, Zongjian Li, Bin Zhu, Shaodong Wang, Xianyi He, Yang Ye, Shenghai Yuan, Liuhan Chen, et al. Open-sora plan: Open-source large video generation model.arXiv preprint arXiv:2412.00131, 2024

work page arXiv 2024
[8]

Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models.arXiv preprint arXiv:2405.04233, 2024

Fan Bao, Chendong Xiang, Gang Yue, Guande He, Hongzhou Zhu, Kaiwen Zheng, Min Zhao, Shilong Liu, Yaole Wang, and Jun Zhu. Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models.arXiv preprint arXiv:2405.04233, 2024

work page arXiv 2024
[9]

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion, December 2024

Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, and Vincent Sitzmann. Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion, December 2024

work page 2024
[10]

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion, November 2025

Xun Huang, Zhengqi Li, Guande He, Mingyuan Zhou, and Eli Shechtman. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion, November 2025

work page 2025
[11]

Freeman, Fredo Durand, Eli Shechtman, and Xun Huang

Tianwei Yin, Qiang Zhang, Richard Zhang, William T. Freeman, Fredo Durand, Eli Shechtman, and Xun Huang. From Slow Bidirectional to Fast Autoregressive Video Diffusion Models, September 2025

work page 2025
[12]

Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation, February 2026

Hongzhou Zhu, Min Zhao, Guande He, Hang Su, Chongxuan Li, and Jun Zhu. Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation, February 2026. 10

work page 2026
[13]

Freeman, and Taesung Park

Tianwei Yin, Michaël Gharbi, Richard Zhang, Eli Shechtman, Fredo Durand, William T. Freeman, and Taesung Park. One-step Diffusion with Distribution Matching Distillation, October 2024

work page 2024
[14]

Improved distribution matching distillation for fast image synthesis

Tianwei Yin, Michaël Gharbi, Taesung Park, Richard Zhang, Eli Shechtman, Fredo Durand, and William T Freeman. Improved distribution matching distillation for fast image synthesis. Advances in neural information processing systems, 37:47455–47487, 2024

work page 2024
[15]

LongLive: Real-time Interactive Long Video Generation, October 2025

Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, Song Han, and Yukang Chen. LongLive: Real-time Interactive Long Video Generation, October 2025

work page 2025
[16]

MemFlow: Flowing adaptive memory for consistent and efficient long video narratives, December 2025

Sihui Ji, Xi Chen, Shuai Yang, Xin Tao, Pengfei Wan, and Hengshuang Zhao. MemFlow: Flowing adaptive memory for consistent and efficient long video narratives, December 2025

work page 2025
[17]

arXiv preprint arXiv:2510.02283 (2025)

Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, and Cho-Jui Hsieh. Self-forcing++: Towards minute-scale high-quality video generation.arXiv preprint arXiv:2510.02283, 2025

work page arXiv 2025
[18]

Trust region policy optimization

John Schulman, Sergey Levine, Pieter Abbeel, Michael Jordan, and Philipp Moritz. Trust region policy optimization. InInternational conference on machine learning, pages 1889–1897. PMLR, 2015

work page 2015
[19]

Live: Long-horizon interactive video world modeling.arXiv preprint arXiv:2602.03747, 2026

Junchao Huang, Ziyang Ye, Xinting Hu, Tianyu He, Guiyu Zhang, Shaoshuai Shi, Jiang Bian, and Li Jiang. Live: Long-horizon interactive video world modeling.arXiv preprint arXiv:2602.03747, 2026

work page arXiv 2026
[20]

arXiv preprint arXiv:2602.06028 (2026)

Shuo Chen, Cong Wei, Sun Sun, Ping Nie, Kai Zhou, Ge Zhang, Ming-Hsuan Yang, and Wenhu Chen. Context forcing: Consistent autoregressive video generation with long context.arXiv preprint arXiv:2602.06028, 2026

work page arXiv 2026
[21]

Rolling forcing: Autoregressive long video diffusion in real time, September 2025

Kunhao Liu, Wenbo Hu, Jiale Xu, Ying Shan, and Shijian Lu. Rolling forcing: Autoregressive long video diffusion in real time, September 2025

work page 2025
[22]

Reward Forc- ing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation, December 2025

Yunhong Lu, Yanhong Zeng, Haobo Li, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Jiapeng Zhu, Hengyuan Cao, Zhipeng Zhang, Xing Zhu, Yujun Shen, and Min Zhang. Reward Forc- ing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation, December 2025

work page 2025
[23]

Anchor forcing: Anchor memory and tri-region rope for interactive streaming video diffusion.arXiv preprint arXiv:2603.13405, 2026

Yang Yang, Tianyi Zhang, Wei Huang, Jinwei Chen, Boxi Wu, Xiaofei He, Deng Cai, Bo Li, and Peng-Tao Jiang. Anchor forcing: Anchor memory and tri-region rope for interactive streaming video diffusion.arXiv preprint arXiv:2603.13405, 2026

work page arXiv 2026
[24]

Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis

Jintao Chen, Chengyu Bai, Xinda Xue, Mu Xu, et al. Grounded forcing: Bridging time- independent semantics and proximal dynamics in autoregressive video synthesis.arXiv preprint arXiv:2604.06939, 2026

work page internal anchor Pith review Pith/arXiv arXiv 2026
[25]

Streaming autoregressive video generation via diagonal distillation, 2026

Jinxiu Liu, Xuanming Liu, Kangfu Mei, Yandong Wen, Ming-HsuanYang, and Weiyang Liu. Streaming autoregressive video generation via diagonal distillation, 2026

work page 2026
[26]

Hiar: Efficient au- toregressive long video generation via hierarchical denoising.arXiv preprint arXiv:2603.08703, 2026

Kai Zou, Dian Zheng, Hongbo Liu, Tiankai Hang, Bin Liu, and Nenghai Yu. Hiar: Efficient au- toregressive long video generation via hierarchical denoising.arXiv preprint arXiv:2603.08703, 2026

work page arXiv 2026
[27]

SkyReels-V2: Infinite-length Film Generative Model

Guibin Chen, Dixuan Lin, Jiangping Yang, Chunze Lin, Junchen Zhu, Mingyuan Fan, Hao Zhang, Sheng Chen, Zheng Chen, Chengcheng Ma, et al. Skyreels-v2: infinite-length film generative model (2025).URL https://arxiv. org/abs/2504.13074

work page internal anchor Pith review Pith/arXiv arXiv 2025
[28]

MAGI-1: Autoregressive Video Generation at Scale

Hansi Teng, Hongyu Jia, Lei Sun, Lingzhi Li, Maolin Li, Mingqiu Tang, Shuai Han, Tianning Zhang, WQ Zhang, Weifeng Luo, et al. Magi-1: Autoregressive video generation at scale.arXiv preprint arXiv:2505.13211, 2025

work page internal anchor Pith review Pith/arXiv arXiv 2025
[29]

Shotstream: Streaming multi-shot video generation for interactive storytelling.arXiv preprint arXiv:2603.25746,

Yawen Luo, Xiaoyu Shi, Junhao Zhuang, Yutian Chen, Quande Liu, Xintao Wang, Pengfei Wan, and Tianfan Xue. Shotstream: Streaming multi-shot video generation for interactive storytelling. arXiv preprint arXiv:2603.25746, 2026. 11

work page arXiv 2026
[30]

Echoshot: Multi-shot portrait video generation

Jiahao Wang, Hualian Sheng, Sijia Cai, Weizhan Zhang, Caixia Yan, Yachuang Feng, Bing Deng, and Jieping Ye. Echoshot: Multi-shot portrait video generation. InThe Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025

work page 2025
[31]

Moviebench: A hierarchical movie level dataset for long video generation

Xiaoxue Wu, Bingjie Gao, Yu Qiao, Yaohui Wang, and Xinyuan Chen. Cinetrans: Learning to generate videos with cinematic transitions via masked diffusion models.arXiv preprint arXiv:2508.11484, 2025

work page arXiv 2025
[32]

Maskˆ 2dit: Dual mask-based diffusion transformer for multi-scene long video generation

Tianhao Qi, Jianlong Yuan, Wanquan Feng, Shancheng Fang, Jiawei Liu, SiYu Zhou, Qian He, Hongtao Xie, and Yongdong Zhang. Maskˆ 2dit: Dual mask-based diffusion transformer for multi-scene long video generation. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 18837–18846, 2025

work page 2025
[33]

Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation

Gordon Chen, Ziqi Huang, and Ziwei Liu. Prompt relay: Inference-time temporal control for multi-event video generation.arXiv preprint arXiv:2604.10030, 2026

work page internal anchor Pith review Pith/arXiv arXiv 2026
[34]

Mind the time: Temporally-controlled multi-event video generation

Ziyi Wu, Aliaksandr Siarohin, Willi Menapace, Ivan Skorokhodov, Yuwei Fang, Varnith Chordia, Igor Gilitschenski, and Sergey Tulyakov. Mind the time: Temporally-controlled multi-event video generation. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 23989–24000, 2025

work page 2025
[35]

Alchemint: Fine-grained temporal control for multi-reference consistent video generation.arXiv preprint arXiv:2512.10943, 2025

Sharath Girish, Viacheslav Ivanov, Tsai-Shien Chen, Hao Chen, Aliaksandr Siarohin, and Sergey Tulyakov. Alchemint: Fine-grained temporal control for multi-reference consistent video generation.arXiv preprint arXiv:2512.10943, 2025

work page arXiv 2025
[36]

Switchcraft: Training-free multi-event video generation with attention controls.arXiv preprint arXiv:2602.23956, 2026

Qianxun Xu, Chenxi Song, Yujun Cai, and Chi Zhang. Switchcraft: Training-free multi-event video generation with attention controls.arXiv preprint arXiv:2602.23956, 2026

work page arXiv 2026
[37]

Mevg: Multi-event video generation with text-to-video models

Gyeongrok Oh, Jaehwan Jeong, Sieun Kim, Wonmin Byeon, Jinkyu Kim, Sungwoong Kim, and Sangpil Kim. Mevg: Multi-event video generation with text-to-video models. InEuropean Conference on computer vision, pages 401–418. Springer, 2024

work page 2024
[38]

TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation

Hongyu Zhang, Yufan Deng, Zilin Pan, Peng-Tao Jiang, Bo Li, Qibin Hou, Zhiyang Dou, Zhen Dong, and Daquan Zhou. Ts-attn: Temporal-wise separable attention for multi-event video generation.arXiv preprint arXiv:2604.19473, 2026

work page internal anchor Pith review Pith/arXiv arXiv 2026
[39]

Ditctrl: Exploring attention control in multi-modal diffusion trans- former for tuning-free multi-prompt longer video generation

Minghong Cai, Xiaodong Cun, Xiaoyu Li, Wenze Liu, Zhaoyang Zhang, Yong Zhang, Ying Shan, and Xiangyu Yue. Ditctrl: Exploring attention control in multi-modal diffusion trans- former for tuning-free multi-prompt longer video generation. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 7763–7772, 2025

work page 2025
[40]

DINOv2: Learning Robust Visual Features without Supervision

Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy V o, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, et al. Dinov2: Learning robust visual features without supervision.arXiv preprint arXiv:2304.07193, 2023

work page internal anchor Pith review Pith/arXiv arXiv 2023
[41]

Oriane Siméoni, Huy V . V o, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julie...

work page 2025
[42]

VBench: Comprehensive benchmark suite for video generative models

Ziqi Huang, Yinan He, Jiashuo Yu, Fan Zhang, Chenyang Si, Yuming Jiang, Yuanhan Zhang, Tianxing Wu, Qingyang Jin, Nattapol Chanpaisit, Yaohui Wang, Xinyuan Chen, Limin Wang, Dahua Lin, Yu Qiao, and Ziwei Liu. VBench: Comprehensive benchmark suite for video generative models. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

work page 2024
[43]

VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

Dian Zheng, Ziqi Huang, Hongbo Liu, Kai Zou, Yinan He, Fan Zhang, Yuanhan Zhang, Jingwen He, Wei-Shi Zheng, Yu Qiao, and Ziwei Liu. VBench-2.0: Advancing video generation benchmark suite for intrinsic faithfulness.arXiv preprint arXiv:2503.21755, 2025. 12

work page internal anchor Pith review Pith/arXiv arXiv 2025
[44]

VBench++: Comprehensive and versatile benchmark suite for video generative models.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

Ziqi Huang, Fan Zhang, Xiaojie Xu, Yinan He, Jiashuo Yu, Ziyue Dong, Qianli Ma, Nattapol Chanpaisit, Chenyang Si, Yuming Jiang, Yaohui Wang, Xinyuan Chen, Ying-Cong Chen, Limin Wang, Dahua Lin, Yu Qiao, and Ziwei Liu. VBench++: Comprehensive and versatile benchmark suite for video generative models.IEEE Transactions on Pattern Analysis and Machine Intelli...

work page 2025
[45]

Long-clip: Unlocking the long-text capability of clip.arXiv preprint arXiv:2403.15378, 2024

Beichen Zhang, Pan Zhang, Xiaoyi Dong, Yuhang Zang, and Jiaqi Wang. Long-clip: Unlocking the long-text capability of clip.arXiv preprint arXiv:2403.15378, 2024

work page arXiv 2024
[46]

Improving Video Generation with Human Feedback

Jie Liu, Gongye Liu, Jiajun Liang, Ziyang Yuan, Xiaokun Liu, Mingwu Zheng, Xiele Wu, Qiulin Wang, Menghan Xia, Xintao Wang, et al. Improving video generation with human feedback.arXiv preprint arXiv:2501.13918, 2025

work page internal anchor Pith review Pith/arXiv arXiv 2025
[47]

Learning transferable visual models from natural language supervision

Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. Learning transferable visual models from natural language supervision. InInternational conference on machine learning, pages 8748–8763. PmLR, 2021

work page 2021
[48]

Distribution matching distillation meets reinforcement learning.arXiv preprint arXiv:2511.13649, 2025

Dengyang Jiang, Dongyang Liu, Zanyi Wang, Qilong Wu, Liuzhuozheng Li, Hengzhuang Li, Xin Jin, David Liu, Changsheng Lu, Zhen Li, et al. Distribution matching distillation meets reinforcement learning.arXiv preprint arXiv:2511.13649, 2025

work page arXiv 2025
[49]

Optimizing few-step generation with adaptive matching distillation.arXiv preprint arXiv:2602.07345, 2026

Lichen Bai, Zikai Zhou, Shitong Shao, Wenliang Zhong, Shuo Yang, Shuo Chen, Bojun Chen, and Zeke Xie. Optimizing few-step generation with adaptive matching distillation.arXiv preprint arXiv:2602.07345, 2026

work page arXiv 2026
[50]

Visualizing data using t-sne.Journal of Machine Learning Research, 9(86):2579–2605, 2008

Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-sne.Journal of Machine Learning Research, 9(86):2579–2605, 2008

work page 2008
[51]

McInnes, J

L. McInnes, J. Healy, and J. Melville. UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.ArXiv e-prints, February 2018. 13 A Motivation Study via Latent Trajectory Visualization To supplement our motivation analysis, we provide a latent-space diagnostic that reveals how existing interactive streaming video generation methods beha...

work page 2018