arxiv: 2605.10543 · v1 · submitted 2026-05-11 · 💻 cs.CV

Recognition: 2 theorem links

· Lean Theorem

TIE: Time Interval Encoding for Video Generation over Events

Zhilei Shu , Shangwen Zhu , Zihang Liang , Xiaofan Li , Qianyu Peng , Xinyu Cui , Bo Ye , Yiming Li

show 5 more authors

Fan Cheng Jian Zhao Yang Cao Zheng-Jun Zha Ruili Feng

Authors on Pith no claims yet

Pith reviewed 2026-05-12 04:22 UTC · model grok-4.3

classification 💻 cs.CV

keywords Time Interval EncodingVideo GenerationDiffusion TransformersPositional EncodingOverlapping EventsTemporal ControllabilityRotary Embeddings

0 comments

The pith

TIE encodes time as intervals rather than points inside diffusion transformers, allowing overlapping events to be represented natively in attention.

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

Video generators built on diffusion transformers encode time only at isolated points, so they cannot mathematically represent events that span durations or occur at the same time. The paper derives a generalization of rotary embeddings called Time Interval Encoding from two explicit principles: events must accumulate positional information across their entire length, and the representation must not reward longer intervals with greater weight. Under a uniform kernel these principles produce a closed-form sinc function that plugs directly into existing cross-attention layers. On the OmniEvents benchmark the change raises verified temporal constraint satisfaction from 77 percent to 96 percent and cuts boundary timing error by more than a factor of three while leaving image quality unchanged.

Core claim

Within RoPE-compatible bilinear attention, TIE is characterized by Temporal Integrability, which requires an event to aggregate positional evidence over its full duration, and Duration Invariance, which removes the trivial bias toward longer intervals. Under a uniform kernel this characterization yields an efficient closed-form sinc-based solution that preserves the standard attention interface and naturally attenuates boundary noise through interval integration.

What carries the argument

Time Interval Encoding (TIE), a plug-and-play generalization of rotary embeddings obtained from the pair of temporal integrability and duration invariance under a uniform kernel.

If this is right

Diffusion transformers can now accept prompts that describe concurrent or extended actions without architectural changes.
Temporal boundary error drops from 0.261 s to 0.073 s on the OmniEvents dataset.
Human-verified temporal constraint satisfaction rises from 77.34 % to 96.03 %.
Trajectory-level alignment metrics improve while the base model’s visual quality is retained.
The same attention interface remains unchanged, so TIE can be swapped in as a drop-in replacement.

Where Pith is reading between the lines

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

The same interval-first logic could be tested in audio or text generation models that must handle overlapping sound events or narrative timelines.
Robotics planners that output concurrent actions might benefit from replacing point-wise time encodings with TIE-style intervals.
An ablation that replaces the uniform kernel with a learned kernel would show whether the closed-form sinc solution is optimal or merely convenient.

Load-bearing premise

The uniform kernel together with the two stated principles is enough to produce a general, artifact-free interval encoding that works across diverse video domains without further tuning.

What would settle it

A controlled evaluation on a held-out set of videos containing many overlapping events in which TIE either fails to raise temporal constraint satisfaction above the point-encoding baseline or introduces measurable drops in visual fidelity.

Figures

Figures reproduced from arXiv: 2605.10543 by Bo Ye, Fan Cheng, Jian Zhao, Qianyu Peng, Ruili Feng, Shangwen Zhu, Xiaofan Li, Xinyu Cui, Yang Cao, Yiming Li, Zheng-Jun Zha, Zhilei Shu, Zihang Liang.

**Figure 1.** Figure 1: Generation results with TIE. By leveraging Time Interval Encoding (TIE), the model generates videos from structured event descriptions with explicit temporal boundaries. The examples demonstrate accurate event alignment under concurrent and overlapping event settings inaccessible to single-active-prompt baselines, including multi-entity dynamics and interleaved interactions. Abstract Director-style prompti… view at source ↗

**Figure 2.** Figure 2: Video examples: Best viewed with Acrobat Reader (Also works on Foxit PDF Reader / PDF-XChange Editor). Click the images to play the animation clips. interval-integrated form also acts as a temporal low-pass filter: boundary perturbations affect only the marginal portion of the event support, making RoTE naturally robust to noisy start and end times. To validate TIE in practice, we construct OmniEvents, a s… view at source ↗

**Figure 3.** Figure 3: Comparison between normal RoPE (Point-wise) and [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗

**Figure 4.** Figure 4: Temporal alignment improvements of TIE. (a) Human-verified metrics show that RoTE consistently improves over finetuning across event occurrence, temporal error, ordering accuracy, overlap accuracy, and overall TCSR. Each bar shows the relative improvement over the finetuned baseline, while the in-bar label reports the raw score change from finetuning to TIE. (b) Trajectorylevel metrics further confirm the… view at source ↗

**Figure 5.** Figure 5: Text-to-video generation example. The Finetuned baseline misses some requested events (e.g., “the man puts his hand off”) and misaligns event onset (e.g., the train remains static in the frame instead of entering at 7.0s), whereas the TIE-enhanced variant responds at the correct time. Method Human Animal Object Retrieval Creative Easy Hard Average Base (10s) 27.6% 27.2% 20.3% 43.1% 13.9% 34.5% 5.9% 23.9% F… view at source ↗

**Figure 6.** Figure 6: Performance trends during training with and without [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗

**Figure 7.** Figure 7: Generation Results on Game Data: In each row we show the frames and their actions. To [PITH_FULL_IMAGE:figures/full_fig_p011_7.png] view at source ↗

**Figure 8.** Figure 8: Robustness to temporal annotation disturbance. (a) We perturb the start and end timestamps of each RoTE interval with Gaussian noise: [s, e] → [s + ϵs, e + ϵe], where ϵs, ϵe ∼ N (0, σ2 ). (b) RoTE remains robust as the disturbance strength increases: even under the largest disturbance, it still achieves better temporal alignment than finetuning with clean timestamps, while only moderately increasing FVD. I… view at source ↗

read the original abstract

Director-style prompting, robotic action prediction, and interactive video agents demand temporal grounding over concurrent events -- a regime in which 68% of general clips and over 99% of robotics/gameplay clips contain overlapping events, yet existing multi-event generators rest on a single-active-prompt assumption. However, modern video generators, such as Diffusion Transformers (DiT), represent time as discrete points through point-wise positional encodings. This formulation creates a fundamental dimension mismatch: temporally extended intervals and overlapping events are mathematically unrepresentable to the attention mechanism. In this paper, we propose Time Interval Encoding (TIE), a principled, plug-and-play interval-aware generalization of rotary embeddings that elevates time intervals to first-class primitives inside DiT cross-attention. Rather than introducing another heuristic interval embedding, we show that, within RoPE-compatible bilinear attention, TIE is characterized by two basic principles: Temporal Integrability, which requires an event to aggregate positional evidence over its full duration, and Duration Invariance, which removes the trivial bias toward longer intervals. Under a uniform kernel, this characterization yields an efficient closed-form sinc-based solution that preserves the standard attention interface and naturally attenuates boundary noise through interval integration. Empirically, TIE preserves the visual quality of the base DiT model while substantially improving temporal controllability. In our experiments on the OmniEvents dataset, it improves human-verified Temporal Constraint Satisfaction Rate from 77.34% to 96.03% and reduces temporal boundary error from 0.261s to 0.073s, while also improving trajectory-level temporal alignment metrics. The code and dataset are available at https://github.com/MatrixTeam-AI/TIE.

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

TIE derives a sinc-based interval encoding from two principles that improves temporal control in DiT video models.

read the letter

The one thing to know is that TIE provides a way to encode time intervals directly in diffusion transformer attention for video generation, derived from basic principles instead of heuristics. They start with Temporal Integrability, meaning the encoding must integrate over the full duration of an event, and Duration Invariance to strip out length bias. Choosing a uniform kernel then gives a closed-form sinc function that slots into the standard RoPE-compatible attention without changing the interface. This addresses the issue of overlapping events, which the abstract notes are in most clips. Their tests on OmniEvents show the temporal constraint satisfaction rate rising from 77.34% to 96.03% and boundary error falling from 0.261s to 0.073s, with visual quality held steady. The public code and dataset are a plus for anyone wanting to reproduce or extend it. One area that needs more attention is the kernel selection. The paper presents the uniform kernel as leading naturally to the sinc solution, but offers little argument for why it is optimal or free of artifacts in varied settings like different frame rates or complex motions. All quantitative results come from a single dataset, which leaves the generalization question open even if the idea is sound on paper. This work targets researchers and engineers building video models for applications like action prediction or interactive agents where timing matters. Anyone dealing with multi-event scenarios in generative video will see immediate value in trying the encoding. The approach shows honest engagement with the limitations of point-wise time encodings and delivers measurable improvements, so it merits a full referee review to examine the math and any additional experiments. I recommend putting it through peer review.

Referee Report

3 major / 2 minor

Summary. The paper proposes Time Interval Encoding (TIE), a plug-and-play generalization of rotary embeddings (RoPE) for Diffusion Transformers (DiT) in video generation. It characterizes TIE via two principles—Temporal Integrability (aggregating positional evidence over an event's full duration) and Duration Invariance (removing bias toward longer intervals)—and derives a closed-form sinc-based encoding under a uniform kernel that integrates into standard bilinear attention while attenuating boundary noise. On the OmniEvents dataset, TIE raises human-verified Temporal Constraint Satisfaction Rate from 77.34% to 96.03%, reduces boundary error from 0.261s to 0.073s, and improves trajectory alignment metrics while preserving base-model visual quality; code and data are released.

Significance. If the central characterization holds, TIE supplies a principled, parameter-free interval primitive for attention-based video models, directly addressing the point-wise time representation mismatch that prevents native handling of overlapping events (common in 68%+ of clips). The open release of code and the OmniEvents dataset is a clear strength for reproducibility. The approach could meaningfully advance controllable generation for robotics, gameplay, and director-style prompting.

major comments (3)

[§3] §3 (Method): The manuscript states that the two principles plus a uniform kernel yield the closed-form sinc TIE, but provides no comparative derivation or argument showing why the uniform kernel is the minimal or unique choice that satisfies Temporal Integrability and Duration Invariance without introducing domain-specific artifacts; alternatives (e.g., Gaussian or triangular kernels) are not examined.
[§4] §4 (Experiments): All quantitative results and human evaluations are confined to the OmniEvents dataset; no cross-dataset tests, ablations on varying event densities, motion complexity, or frame rates are reported, leaving the claim of general, artifact-free generalization unsupported.
[§3.3] §3.3 / Eq. (7)–(9): The claim that interval integration “naturally attenuates boundary noise” is asserted from the sinc form, yet no separate quantitative boundary-noise metric, ablation, or visualization isolates this effect from the overall TCS-rate and boundary-error gains.

minor comments (2)

[Figures 3–4] Figure 3 and 4 captions should explicitly state the number of samples and the exact human-evaluation protocol (e.g., number of raters, inter-rater agreement) rather than referring only to “visual quality.”
[Eq. (10)] Notation: the transition from the continuous integral form to the discrete sinc implementation in Eq. (10) would benefit from an explicit discretization step or reference to the sampling rate used.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the thoughtful and constructive review. We address each major comment point-by-point below with clarifications and commitments to revisions that strengthen the manuscript without misrepresenting the current results.

read point-by-point responses

Referee: [§3] §3 (Method): The manuscript states that the two principles plus a uniform kernel yield the closed-form sinc TIE, but provides no comparative derivation or argument showing why the uniform kernel is the minimal or unique choice that satisfies Temporal Integrability and Duration Invariance without introducing domain-specific artifacts; alternatives (e.g., Gaussian or triangular kernels) are not examined.

Authors: The uniform kernel is the minimal choice that yields a parameter-free closed-form solution under the two principles: its constant weight allows direct integration over the interval to produce the sinc function while exactly satisfying Duration Invariance (normalization removes length bias) and Temporal Integrability (full-duration aggregation). Other kernels (Gaussian, triangular) would either require additional hyperparameters or lose the closed-form property, introducing artifacts or breaking RoPE compatibility. We will revise §3 to include an explicit derivation subsection showing this minimality and briefly contrast the uniform case with alternatives, noting that empirical comparison of kernels is reserved for future work given the computational cost of retraining DiT variants. revision: partial
Referee: [§4] §4 (Experiments): All quantitative results and human evaluations are confined to the OmniEvents dataset; no cross-dataset tests, ablations on varying event densities, motion complexity, or frame rates are reported, leaving the claim of general, artifact-free generalization unsupported.

Authors: OmniEvents was constructed precisely to isolate the multi-event temporal constraint problem that standard datasets do not emphasize. Because TIE is a plug-and-play replacement for positional encodings inside existing DiT attention, the architecture-level generalization argument holds, yet we agree broader empirical support is desirable. In the revision we will add qualitative results and limited quantitative checks on at least one additional public video dataset (e.g., a subset of WebVid or a robotics clip collection) together with an ablation on event density, to better substantiate the generalization claim. revision: yes
Referee: [§3.3] §3.3 / Eq. (7)–(9): The claim that interval integration “naturally attenuates boundary noise” is asserted from the sinc form, yet no separate quantitative boundary-noise metric, ablation, or visualization isolates this effect from the overall TCS-rate and boundary-error gains.

Authors: The reported boundary-error reduction (0.261 s → 0.073 s) and TCS improvement already reflect the net effect of interval integration. The sinc kernel’s low-pass character theoretically suppresses high-frequency boundary discontinuities; we will strengthen the presentation by adding a dedicated figure in §3.3 that visualizes per-boundary attention weights and error histograms with/without TIE, thereby isolating the attenuation mechanism from the aggregate metrics. revision: yes

Circularity Check

0 steps flagged

No circularity: derivation proceeds from stated principles plus kernel choice to closed-form solution without reduction to inputs.

full rationale

The paper states two principles (Temporal Integrability and Duration Invariance) that characterize TIE inside RoPE-compatible bilinear attention, then shows that a uniform kernel yields a closed-form sinc solution. This is a forward derivation from assumptions to result rather than any self-definition, fitted parameter renamed as prediction, or load-bearing self-citation. No equations or text in the abstract or described chain exhibit the specific reduction required to flag circularity. The uniform kernel is an explicit modeling choice whose consequences are derived, not smuggled in via prior self-work.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on two domain assumptions that define what a valid interval encoding must satisfy, plus the choice of a uniform kernel to obtain a closed-form solution. No free parameters or new physical entities are introduced.

axioms (2)

domain assumption Temporal Integrability: an event must aggregate positional evidence over its full duration
One of the two basic principles used to characterize TIE inside RoPE-compatible bilinear attention.
domain assumption Duration Invariance: the encoding must remove trivial bias toward longer intervals
Second principle required to avoid length-dependent artifacts in the interval representation.

pith-pipeline@v0.9.0 · 5644 in / 1337 out tokens · 44892 ms · 2026-05-12T04:22:06.763369+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

Under a uniform kernel, this characterization yields an efficient closed-form sinc-based solution... Ai,c,r = sinc(θir) [cos(θic) −sin(θic); sin(θic) cos(θic)]
IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

Temporal Integrability... Duration Invariance... TIE(k, I) = 1/C(μ_I) E_τ∼μ_I [RoPE(k, τ)]

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

48 extracted references · 48 canonical work pages · 2 internal anchors

[1]

Cosmos world foundation model platform for Physical AI, 2025

NVIDIA: Niket Agarwal, Arslan Ali, Maciej Bala, Yogesh Balaji, Erik Barker, Tiffany Cai, Prithvijit Chattopadhyay, Yongxin Chen, Yin Cui, Yifan Ding, Daniel Dworakowski, Jiaojiao Fan, Michele Fenzi, Francesco Ferroni, Sanja Fidler, Dieter Fox, Songwei Ge, Yunhao Ge, Jinwei Gu, Siddharth Gururani, Ethan He, Jiahui Huang, Jacob Huffman, Pooya Jannaty, 12 Ji...

work page 2025
[2]

Align your latents: high-resolution video synthesis with latent diffusion models

Andreas Blattmann, Robin Rombach, Huan Ling, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, and Karsten Kreis. Align your latents: high-resolution video synthesis with latent diffusion models. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

work page 2023
[3]

Jake Bruce, Michael D. Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, Yusuf Aytar, Sarah Maria Elis- abeth Bechtle, Feryal Behbahani, Stephanie C. Y . Chan, Nicolas Heess, Lucy Gonzalez, Simon Osindero, Sherjil Ozair, Scott Reed, Jingwei Zhang, Konrad Zolna, Jeff Clune, N...

work page 2024
[4]

StoryBench: A Multifaceted Benchmark for Continuous Story Visualization

Emanuele Bugliarello, Hernan Moraldo, Ruben Villegas, Mohammad Babaeizadeh, Mohammad Taghi Saffar, Han Zhang, Dumitru Erhan, Vittorio Ferrari, Pieter-Jan Kindermans, and Paul V oigtlaender. StoryBench: A Multifaceted Benchmark for Continuous Story Visualization. In Advances in Neural Information Processing Systems, 2023

work page 2023
[5]

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 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

work page 2025
[6]

arXiv preprint arXiv:2305.13840 (2023)

Weifeng Chen, Jie Wu, Pan Xie, Hefeng Wu, Jiashi Li, Xin Xia, Xuefeng Xiao, and Liang Lin. Control-A-Video: controllable text-to-video generation with diffusion models.arXiv preprint arXiv:2305.13840, 2023

work page arXiv 2023
[7]

AgiBot world colosseum

AgiBot World Colosseum contributors. AgiBot world colosseum. https://github.com/ OpenDriveLab/AgiBot-World, 2024

work page 2024
[8]

Tenenbaum, Dale Schuurmans, and Pieter Abbeel

Yilun Du, Sherry Yang, Bo Dai, Hanjun Dai, Ofir Nachum, Joshua B. Tenenbaum, Dale Schuurmans, and Pieter Abbeel. Learning universal policies via text-guided video generation. InAdvances in Neural Information Processing Systems, 2023

work page 2023
[9]

AnimateDiff: animate your personalized text-to-image diffu- sion models without specific tuning

Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. AnimateDiff: animate your personalized text-to-image diffu- sion models without specific tuning. InInternational Conference on Learning Representations, 2024

work page 2024
[10]

VideoScore: building automatic metrics to simulate fine-grained human feedback for video generation

Xuan He, Dongfu Jiang, Ge Zhang, Max Ku, Achint Soni, Sherman Siu, Haonan Chen, Abhranil Chandra, Ziyan Jiang, Aaran Arulraj, Kai Wang, Quy Duc Do, Yuansheng Ni, Bohan Lyu, Yaswanth Narsupalli, Rongqi Fan, Zhiheng Lyu, Yuchen Lin, and Wenhu Chen. VideoScore: building automatic metrics to simulate fine-grained human feedback for video generation. In Procee...

work page 2024
[11]

GANs trained by a two time-scale update rule converge to a local Nash equilibrium

Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, Günter Klambauer, and Sepp Hochreiter. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. InAdvances in Neural Information Processing Systems, 2017

work page 2017
[12]

GAIA-1: A Generative World Model for Autonomous Driving

Anthony Hu, Lloyd Russell, Hudson Yeo, Zak Murez, George Fedoseev, Alex Kendall, Jamie Shotton, and Gianluca Corrado. GAIA-1: a generative world model for autonomous driving. arXiv preprint arXiv:2309.17080, 2023. 13

work page internal anchor Pith review arXiv 2023
[13]

EnerVerse: envisioning embodied future space for robotics manipulation

Siyuan Huang, Liliang Chen, Pengfei Zhou, Shengcong Chen, Zhengkai Jiang, Yue Hu, Yue Liao, Peng Gao, Hongsheng Li, Maoqing Yao, et al. EnerVerse: envisioning embodied future space for robotics manipulation. InAdvances in Neural Information Processing Systems, 2025

work page 2025
[14]

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
[15]

V ACE: all-in- one video creation and editing

Zeyinzi Jiang, Zhen Han, Chaojie Mao, Jingfeng Zhang, Yulin Pan, and Yu Liu. V ACE: all-in- one video creation and editing. InProceedings of the IEEE/CVF International Conference on Computer Vision, 2025

work page 2025
[16]

Kingma and Jimmy Ba

Diederik P. Kingma and Jimmy Ba. Adam: a method for stochastic optimization. InInternational Conference on Learning Representations, 2015

work page 2015
[17]

MultiSports: a multi-person video dataset of spatio-temporally localized sports actions

Yixuan Li, Lei Chen, Runyu He, Zhenzhi Wang, Gangshan Wu, and Limin Wang. MultiSports: a multi-person video dataset of spatio-temporally localized sports actions. InProceedings of the IEEE/CVF International Conference on Computer Vision, 2021

work page 2021
[18]

VideoDirectorGPT: consistent multi- scene video generation via LLM-guided planning

Han Lin, Abhay Zala, Jaemin Cho, and Mohit Bansal. VideoDirectorGPT: consistent multi- scene video generation via LLM-guided planning. InProceedings of the First Conference on Language Modeling, 2024

work page 2024
[19]

Decoupled weight decay regularization

Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization. InInternational Conference on Learning Representations, 2019

work page 2019
[20]

VDT: general-purpose video diffusion transformers via mask modeling

Haoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo, Zhiwu Lu, Ping Luo, and Mingyu Ding. VDT: general-purpose video diffusion transformers via mask modeling. InInternational Conference on Learning Representations, 2024

work page 2024
[21]

Latte: latent diffusion transformer for video generation.Transactions on Machine Learning Research, 2025

Xin Ma, Yaohui Wang, Xinyuan Chen, Gengyun Jia, Ziwei Liu, Yuan-Fang Li, Cunjian Chen, and Yu Qiao. Latte: latent diffusion transformer for video generation.Transactions on Machine Learning Research, 2025

work page 2025
[22]

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. Springer, 2024

work page 2024
[23]

Scalable diffusion models with transformers

William Peebles and Saining Xie. Scalable diffusion models with transformers. InProceedings of the IEEE/CVF International Conference on Computer Vision, 2023

work page 2023
[24]

FreeNoise: tuning-free longer video diffusion via noise rescheduling

Haonan Qiu, Menghan Xia, Yong Zhang, Yingqing He, Xintao Wang, Ying Shan, and Ziwei Liu. FreeNoise: tuning-free longer video diffusion via noise rescheduling. InInternational Conference on Learning Representations, 2024

work page 2024
[25]

Qwen3 technical report, 2025

Qwen Team. Qwen3 technical report, 2025

work page 2025
[26]

Dynamic programming algorithm optimization for spoken word recognition.IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978

Hiroaki Sakoe and Seibi Chiba. Dynamic programming algorithm optimization for spoken word recognition.IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978

work page 1978
[27]

Make-A-Video: text-to-video generation without text-video data

Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, and Yaniv Taigman. Make-A-Video: text-to-video generation without text-video data. InInternational Conference on Learning Representations, 2023

work page 2023
[28]

Roformer: Enhanced transformer with rotary position embedding.Neurocom- puting, 2024

Jianlin Su et al. Roformer: Enhanced transformer with rotary position embedding.Neurocom- puting, 2024

work page 2024
[29]

Towards accurate generative models of video: a new metric and challenges

Thomas Unterthiner, Sjoerd van Steenkiste, Karol Kurach, Raphaël Marinier, Marcin Michalski, and Sylvain Gelly. Towards accurate generative models of video: a new metric and challenges. ArXiv, 2018. 14

work page 2018
[30]

Diffusion models are real-time game engines

Dani Valevski, Yaniv Leviathan, Moab Arar, and Shlomi Fruchter. Diffusion models are real-time game engines. InInternational Conference on Learning Representations, 2025

work page 2025
[31]

Phenaki: variable length video generation from open-domain textual descriptions

Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans, Hernan Moraldo, Han Zhang, Mohammad Taghi Saffar, Santiago Castro, Julius Kunze, and Dumitru Erhan. Phenaki: variable length video generation from open-domain textual descriptions. InInternational Conference on Learning Representations, 2023

work page 2023
[32]

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, Jianyuan Zeng, Jiayu Wang, Jingfeng Zhang, Jingren Zhou, Jinkai Wang, Jixuan Chen, Kai Zhu, Kang Zhao, Keyu Yan, Lianghua Huang, Mengyang Feng, Ningyi Zhang, Pandeng Li, Pingyu Wu, Ruihang Chu, Ruili Feng, Shiwei Zhang, Siyang Sun, Tao Fang, T...

work page internal anchor Pith review Pith/arXiv arXiv 2025
[33]

Gen- L-Video: multi-text to long video generation via temporal co-denoising.arXiv preprint arXiv:2305.18264, 2023

Fu-Yun Wang, Wenshuo Chen, Guanglu Song, Han-Jia Ye, Yu Liu, and Hongsheng Li. Gen- L-Video: multi-text to long video generation via temporal co-denoising.arXiv preprint arXiv:2305.18264, 2023

work page arXiv 2023
[34]

VideoComposer: compositional video synthesis with motion controllability

Xiang Wang, Hangjie Yuan, Shiwei Zhang, Dayou Chen, Jiuniu Wang, Yingya Zhang, Yujun Shen, Deli Zhao, and Jingren Zhou. VideoComposer: compositional video synthesis with motion controllability. InAdvances in Neural Information Processing Systems, 2023

work page 2023
[35]

Is your world simulator a good story presenter? a consecutive events-based benchmark for future long video generation,

Yiping Wang, Xuehai He, Kuan Wang, Luyao Ma, Jianwei Yang, Shuohang Wang, Si- mon Shaolei Du, and Yelong Shen. Is your world simulator a good story presenter? a consecutive events-based benchmark for future long video generation.arXiv preprint arXiv:2412.16211, 2024

work page arXiv 2024
[36]

Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, F. Xia, Quoc Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems, 2022

work page 2022
[37]

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 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

work page 2025
[38]

Dreamfactory: Pioneering multi-scene long video generation with a multi-agent framework.arXiv preprint arXiv:2408.11788,

Zhifei Xie, Daniel Tang, Dingwei Tan, Jacques Klein, Tegawend F Bissyand, and Saad Ezzini. DreamFactory: pioneering multi-scene long video generation with a multi-agent framework. arXiv preprint arXiv:2408.11788, 2024

work page arXiv 2024
[39]

Learning interactive real-world simulators

Sherry Yang, Yilun Du, Seyed Kamyar Seyed Ghasemipour, Jonathan Tompson, Leslie Pack Kaelbling, Dale Schuurmans, and Pieter Abbeel. Learning interactive real-world simulators. In International Conference on Learning Representations, 2024

work page 2024
[40]

Direct-a-Video: customized video generation with user-directed camera movement and object motion

Shiyuan Yang, Liang Hou, Haibin Huang, Chongyang Ma, Pengfei Wan, Di Zhang, Xiaodong Chen, and Jing Liao. Direct-a-Video: customized video generation with user-directed camera movement and object motion. InACM SIGGRAPH 2024 Conference Papers, 2024

work page 2024
[41]

LongLive: real-time interactive long video generation

Shuai Yang, Wei Huang, Ruihang Chu, Yicheng Xiao, Yuyang Zhao, Xianbang Wang, Muyang Li, Enze Xie, Yingcong Chen, Yao Lu, et al. LongLive: real-time interactive long video generation. InInternational Conference on Learning Representations, 2026

work page 2026
[42]

CogVideoX: text-to-video diffusion models with an expert transformer

Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Yuxuan Zhang, Weihan Wang, Yean Cheng, Bin Xu, Xiaotao Gu, Yuxiao Dong, and Jie Tang. CogVideoX: text-to-video diffusion models with an expert transformer. InInternational Conference on Learning Representations, 2025. 15

work page 2025
[43]

NUW A-XL: diffusion over diffusion for eXtremely long video generation

Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, Jianlong Fu, Ming Gong, Lijuan Wang, Zicheng Liu, Houqiang Li, and Nan Duan. NUW A-XL: diffusion over diffusion for eXtremely long video generation. InProceedings of the 61st Annual Meeting of the Association for Computational...

work page 2023
[44]

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. InInternational Conference on Learning Representations, 2026

work page 2026
[45]

Videogen-of-thought: Step-by-step generating multi-shot video with minimal manual intervention.arXiv preprint arXiv:2412.02259, 2024

Mingzhe Zheng, Yongqi Xu, Haojian Huang, Xuran Ma, Yexin Liu, Wenjie Shu, Yatian Pang, Feilong Tang, Qifeng Chen, Harry Yang, et al. VideoGen-of-Thought: step-by-step generating multi-shot video with minimal manual intervention.arXiv preprint arXiv:2412.02259, 2024

work page arXiv 2024
[46]

Pexels-400k: a large-scale dataset for video and image generation

Zhou Zhi-Min. Pexels-400k: a large-scale dataset for video and image generation. https: //huggingface.co/datasets/jovianzm/Pexels-400k, 2023

work page 2023
[47]

Robo- Dreamer: learning compositional world models for robot imagination

Siyuan Zhou, Yilun Du, Jiaben Chen, Yandong Li, Dit-Yan Yeung, and Chuang Gan. Robo- Dreamer: learning compositional world models for robot imagination. InProceedings of the International Conference on Machine Learning, 2024

work page 2024
[48]

bi,j->bij

Fangqi Zhu, Hongtao Wu, Song Guo, Yuxiao Liu, Chilam Cheang, and Tao Kong. IRASim: a fine-grained world model for robot manipulation. InProceedings of the IEEE/CVF International Conference on Computer Vision, 2025. A Details and Proofs for TIE A.1 Proofs for Section 3 This subsection provides the full formalization and proofs for the principle-based chara...

work page arXiv 2025