Pith. sign in

REVIEW 12 cited by

One-Minute Video Generation with Test-Time Training

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.05298 v1 pith:OIRTPRZK submitted 2025-04-07 cs.CV

classification cs.CV
keywords videoslayersone-minutecomplexgeneratestoriesbecauseexpressive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Transformers today still struggle to generate one-minute videos because self-attention layers are inefficient for long context. Alternatives such as Mamba layers struggle with complex multi-scene stories because their hidden states are less expressive. We experiment with Test-Time Training (TTT) layers, whose hidden states themselves can be neural networks, therefore more expressive. Adding TTT layers into a pre-trained Transformer enables it to generate one-minute videos from text storyboards. For proof of concept, we curate a dataset based on Tom and Jerry cartoons. Compared to baselines such as Mamba~2, Gated DeltaNet, and sliding-window attention layers, TTT layers generate much more coherent videos that tell complex stories, leading by 34 Elo points in a human evaluation of 100 videos per method. Although promising, results still contain artifacts, likely due to the limited capability of the pre-trained 5B model. The efficiency of our implementation can also be improved. We have only experimented with one-minute videos due to resource constraints, but the approach can be extended to longer videos and more complex stories. Sample videos, code and annotations are available at: https://test-time-training.github.io/video-dit

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Forget, Anticipate and Adapt: Test Time Training for Long Videos

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    FFN performs TTT on multi-hour videos by restricting updates to three frames and using a surprise metric for adaptive window sizing, plus a new EpicTours dataset.

  2. Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning

    cs.LG 2025-07 conditional novelty 6.0 of 10

    Selecting the most confident 32-token prefix and completing only it gives better accuracy per compute than majority voting on five math reasoning datasets, using only the model's own confidence as a selector.

  3. LoViC: Efficient Long Video Generation with Context Compression

    cs.CV 2025-07 conditional novelty 6.0 of 10

    LoViC uses FlexFormer, a single-query-token Q-Former with interpolated rotary positional encoding, to compress long video-text context for efficient long-video generation.

  4. Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Hunyuan-GameCraft generates long, action-controlled game videos from a single image by unifying keyboard/mouse inputs into a continuous camera space and conditioning on mixed historical context.

  5. VeriThinker: Learning to Verify Makes Reasoning Model Efficient

    cs.LG 2025-05 conditional novelty 6.0 of 10

    VeriThinker shows that fine-tuning a reasoning model only on a solution-verification task reduces chain-of-thought length on MATH500 and AIME by 20-45% while preserving or slightly improving accuracy.

  6. Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging

    cs.LG 2025-05 conditional novelty 6.0 of 10

    TTMM pre-trains many local LoRA experts on data clusters and merges the most relevant few at test time, approximating test-time training with a 100x speedup and near-TTT perplexity.

  7. ENA: Efficient N-dimensional Attention

    cs.LG 2025-08 conditional novelty 5.0 of 10

    ENA combines linear recurrence with hardware-friendly sliding tile attention to model images and videos efficiently, claiming Transformer-level accuracy at roughly 70% attention sparsity.

  8. From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    An explainable model using BLEURT, CometKiwi, pause features, and Chinese phraseological diversity predicts human-rated quality dimensions in English-Chinese consecutive interpreting, with SHAP identifying the stronge...

  9. Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning

    cs.CL 2025-06 conditional novelty 5.0 of 10

    ADAPT, a diversity-aware prefix fine-tuning method, improves best-of-N sampling efficiency for a 1.5B reasoning model, reaching 80% accuracy at N=32 versus N=256 for the baseline.

  10. ATLAS: Learning to Optimally Memorize the Context at Test Time

    cs.CL 2025-05 conditional novelty 5.0 of 10

    A new recurrent memory module (Atlas) that optimizes its memory over a window of past tokens and uses Muon-style second-order updates, reporting gains over Transformers and existing linear RNNs on long-context tasks.

  11. REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing

    cs.CV 2025-05 conditional novelty 5.0 of 10

    REGen generates documentary teasers by fine-tuning an LLM to write a script with <QUOTE> markers, then a trained retriever fills each marker with the most relevant clip from the source video.

  12. Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A hierarchical direct preference optimization with four alignment levels plus automated data selection improves physical plausibility of text-to-video models.

Pith tools