- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes AmendAR, a method for correcting previously generated chunks in autoregressive video diffusion while preserving the KV cache. It appends compact revision tokens that guide subsequent generation and uses a backward decoder to refine earlier chunks with later information. Training uses enhanced versions of the model’s own generated videos as supervision. The paper provides theoretical analyses of cache invariance and information benefits, and experiments on three video backbones demonstrate improved event and temporal consistency with moderate inference overhead.
Critical strengths
The method addresses the difficulty of correcting committed video chunks without invalidating the KV cache. Compact revision tokens and a backward decoder allow later information to refine earlier outputs while preserving cached states, providing a meaningful extension to autoregressive video generation.
Critical weaknesses
The streaming benefit is limited by the backward decoder’s dependence on future chunks. The reported preview latency measures the uncorrected first chunk, whereas its final corrected version requires the complete sequence. This dependence conflicts with the streaming nature of autoregressive video generation, where chunks should be finalized and displayed incrementally without waiting for the entire video.
Questions for authors
1.Since the final corrected version of an early chunk depends on the complete sequence, how should AmendAR be used in live streaming, where previously displayed frames cannot be revised? Please clarify the intended playback protocol and report the quality and latency of corrected outputs under a fixed lookahead budget. 2. How does AmendAR compare with applying VEnhancer directly to the same generated drafts, in terms of both quality and total inference latency? This comparison would help establish the practical advantage of learning compact revisions over using the enhancement teacher as a post-processing method.
3 comments
(2/2) VEnhancer applied directly to the drafts: quality and latency
(2/2)
VEnhancer as a post-processor on native drafts
Applied directly at test time, VEnhancer reaches quality close to AmendAR's but costs far more time, needs the complete clip, and cannot inform later chunks. This was the right comparison to ask for. Table 14 (App. G.2) now reports it with the target-building settings (noise augmentation 200, 15 steps, CFG 7.5) at batch size one on the backbone's GPUs, on Wan and Hunyuan (on MAGI, generation alone already takes about 950 s per video):
| System | VP-2 | Story | Final latency (s) |
|---|---|---|---|
| Wan: native | 25.5 | 24.9 | 11.63 |
| Wan: native + VEnhancer | 32.4 | 31.6 | 175.05 |
| Wan: AmendAR | 33.2 | 33.0 | 14.06 |
| Hunyuan: native + VEnhancer | 23.2 | 24.2 | 112.41 |
| Hunyuan: AmendAR | 24.6 | 25.8 | 62.20 |
Native + VEnhancer stays within 1.6 points of AmendAR. It adds 59.6-163.4 s per video, so the total is 1.8-12.5 times AmendAR's final latency; the factor is largest on Wan, where generation itself is fastest. We read this as close on quality and clearly different in cost and usability.
What learning compact revisions buys over the teacher
- Time. On Wan, 14.06 s instead of 175.05 s per video, with the first chunk shown after 1.37 s (preview) or 4.39 s (committed, ).
- Streaming. Post-processing needs the finished clip; AmendAR's correction runs inside the stream with a short lookahead (part 1/2).
- Later chunks follow the correction. Revisions sit in the cache, so the generator conditions on them. Blocking that access lowers the raw drafts by 1.9-2.6 points on every backbone and benchmark (Table 4). A post-processor cannot have this effect.
We do not claim that AmendAR beats the teacher at equal information. On AmendAR's own drafts the teacher is still the stronger corrector (Table 5), and the Limitations paragraph says so. We also added the learned, compact alternative that Reviewer 8DRV proposed: a text-conditioned refiner trained on enhanced versions of a time-matched video-only model's drafts. On Wan, AmendAR stays 1.1-1.3 points above it on both automatic completion benchmarks (Table 15).
Changes in the paper. Sec. 5.2 ("Teacher post-processing and bidirectional generators"), Table 14 and App. G.2, and the Limitations paragraph.
Thank you again for two questions that sharpened what the paper claims. If the streaming protocol and the teacher comparison resolve your concerns, we would be grateful if you would consider revisiting your score; we are happy to clarify anything further.
A major advantage of autoregressive over bidirectional video generation is the ability to display chunks as soon as they are generated. However, AmendAR’s additional gains require waiting for future chunks. At , it does not outperform the time-matched video-only baseline on Wan, while even more than doubles the first-chunk latency. Therefore, my concern remains unresolved, and I will maintain my original score.
(1/2) Live streaming: committed playback with a fixed lookahead
(1/2)
Thank you for the review, and for putting your finger on the exact gap in our streaming story. You are right that the submission timed an uncorrected first chunk and scored a fully corrected video, and never measured what a viewer gets when a chunk, once shown, can no longer change. We now measure exactly that.
How AmendAR should be used in live streaming
For live playback, AmendAR displays each chunk once and never replaces it; we call this committed playback with lookahead L. Chunk i is shown when chunk min(i+L,N) and its revision exist, rendered by the backward scan of that prefix. No retraining is needed, because the decoder is already trained on every prefix length (Eq. 4), and the cache is untouched. L=0 corrects each chunk with its own revision only; L=N−1 is the offline final render. The second mode, a revisable preview, is for settings where swapping a shown chunk is acceptable (an editor or a review tool). Sec. 4.2 now defines both.
Quality and latency under a fixed lookahead (Table 13, App. G.1; the scored video concatenates exactly the committed chunks a viewer saw; TC-Bench is shown where the readout was already scored)
Three things follow, and they hold on MAGI and Hunyuan as well:
On our A100s no backbone generates faster than real time, so the lookahead shows up as a start-up delay: on Wan, the first committed chunk appears after 4.39 s with L=2, against 1.32 s for the native preview. On hardware fast enough for real-time generation, the same lookahead is simply a playback buffer of L chunks.
Changes in the paper. Sec. 4.2 (two ways to use the stream), Sec. 5.2 ("Committed playback needs a short lookahead"), Table 13 with all three backbones, and the Limitations paragraph, which now states that live playback needs a short lookahead.
In short: the final render does depend on the whole record, as you say, and for streaming that never replaces a frame we now recommend L=2, which keeps most of the gain at a small, measured delay.