- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3(+1)
- Soundness
- 3(+1)
Read review
Paper summary
This work introduces the MEMFLOW framework, which alleviates the limitations of existing approaches that rely on predefined cache compression strategies. While various retrieval methods, such as those based on 3D spatial indexing, already exist. This specific approach dynamically retrieves the most relevant historical frames from a global memory bank to serve as context for generating the next video segment, guided by the segment's corresponding text prompt. Experiments demonstrate that this method effectively preserves context.
Critical strengths
- The two-stage memory selection process in this method is well-founded. NAM first determines the content to be retrieved based on the text, while SMA subsequently filters these memories according to the current generation state—leveraging semantic conditions and the visual generation state, respectively.
- The idea behind this paper is easy to understand, and the writing is clear.
Critical weaknesses
- There are directly verifiable numerical discrepancies between the main text and the appendices. The results for LongLive differ between Table 2 in the main text and Tables B/C in the appendix, whereas the results for MEMFLOW are consistent. The results for LongLive differ between Table 2 in the main text and Tables B/C in the appendix, whereas the results for MEMFLOW are consistent. In both Table 2 (main text) and Tables B/C (appendix), MEMFLOW achieves a Quality Score of 85.95 and a Semantic Score of 81.90. For LongLive, however, the values in Table 2 are 86.97 (Quality Score) and 76.47 (Semantic Score), while in Tables B/C (appendix), they are 83.96 (Quality Score) and 80.15 (Semantic Score). These discrepancies raise concerns regarding the reliability of the data presented in the paper.
- The baselines used for comparison in the experiments are outdated. The authors should include more recent baselines. Furthermore, the effectiveness of the model should be evaluated using architectures with a larger number of parameters. Many of the issues observed with the 1.4B-parameter model might not persist when scaled up to larger models.
- The paper introduces two changes. It modifies the model's underlying mechanism and, additionally, incorporates specific training datas, such as the reappearance of objects after they have vanished and the revisiting of previously encountered scenes. However, the paper does not evaluate the specific contribution of this training data. If LongLive were trained using the same MST prompt data, without the inclusion of NAM and SMA, what level of performance improvement would the model achieve?
Questions for authors
- Explain the inconsistencies in the numerical values that appear in the paper.
- Verify the effectiveness of the method on a larger model.
- Conduct additional MST ablation experiments.
4 comments
(2) Public single-prompt protocol. 60s generation on the first 128 MovieGen prompts with VBench-Long metrics, as used by recent long-video works (e.g., Self-Forcing++, Reward Forcing). All methods are evaluated by us under the same protocol:
Table b: Comparison of recent baselines for single-prompt 60s generation on MovieGen prompts
| Method | #Params | Quality Score ↑ | Aesth. Drift ↓ | Subject Consist. ↑ | Background Consist. ↑ | Motion Smooth. ↑ | Dynamic Degree ↑ | Aesthetic Quality ↑ | Imaging Quality ↑ | Overall Consist. ↑ |
|---|---|---|---|---|---|---|---|---|---|---|
| SkyReels-V2 | ||||||||||
| Self Forcing | ||||||||||
| FramePack | ||||||||||
| LongLive | ||||||||||
| Anchor Forcing | ||||||||||
| OmniMem | ||||||||||
| LongLive 2.0 | ||||||||||
| Helios (distilled) | ||||||||||
| MemFlow |
On this public single-prompt protocol, MemFlow achieves the best results on six of the nine metrics, including subject consistency, background consistency, and overall consistency. Even the larger LongLive 2.0 and Helios models do not obtain a higher quality score. These results show that MemFlow retains an advantage in general long-video quality over recent state-of-the-art methods, including those built on larger backbones.
In particular, MemFlow produces higher dynamics than LongLive (0.5755 vs. 0.4049), consistent with MST's exposure to multiple prompt switches during training. FramePack obtains higher motion smoothness than MemFlow. Its allocation of more context capacity to recent, more important frames may benefit motion smoothness. However, its generation speed is far below that of MemFlow (0.92 FPS vs. 18.7 FPS, as reported in Table 4 of the main paper).
R3-W2 (part 2) & Q2: Effectiveness on a larger model
We built a 5B version of MemFlow on LongLive 2.0, whose base model is Wan2.2-TI2V-5B. LongLive 2.0 uses a Frame Sink and a Shot Sink: the former is the same as in LongLive, and the latter keeps the KV cache of the first chunk of the clip generated under the current prompt, holds it throughout that clip, and replaces it with the first chunk of the next clip after a prompt switch. We replace the Shot Sink with Narrative Adaptive Memory (NAM) and Sparse Memory Activation (SMA) and fine-tune the LoRA with Memory-Forced Streaming Tuning (MST).
Table c: Cross-backbone validation for 60s multi-prompt generation.
| Model | Base model | #Params | Memory | Quality Score ↑ | Aesth. Drift ↓ | Subj. Consist. CLIP ↑ | Subj. Consist. DINO ↑ | Scene Consist. CLIP ↑ | Scene Consist. DINO ↑ | Prompt Align. ↑ | Transition Align. ↑ |
|---|---|---|---|---|---|---|---|---|---|---|---|
| LongLive | Wan2.1-T2V | Frame Sink | |||||||||
| MemFlow | Wan2.1-T2V | Frame Sink + NAM + SMA | |||||||||
| LongLive 2.0 | Wan2.2-TI2V | Frame Sink + Shot Sink | |||||||||
| LongLive 2.0 + our memory | Wan2.2-TI2V | Frame Sink + NAM + SMA |
On this backbone, our design brings the same pattern of gains in subject consistency and transition alignment as on the 1.3B LongLive, which verifies the effectiveness of our method on a larger model. Overall, seven of the eight metrics improve on the 5B backbone. The gains in subject consistency and transition alignment are smaller than at 1.3B, because LongLive 2.0 has been trained on large-scale long, multi-shot data and is a much stronger base model. Our memory design supplies more relevant context needed when earlier content returns, and MST teaches the model to use it and follow more complex narrative changes.
In addition, in the 60s multi-prompt comparison above, the larger baselines (LongLive 2.0 at 5B and Helios at 14B) remain clearly below the 1.3B MemFlow in scene consistency, and Helios also in subject consistency. Scaling up the model alone does not resolve long-range consistency under prompt switches, so the issue is not specific to small models.
R3-W3 & Q3: Ablation on MST
Thank you for the suggestion. To evaluate the specific contribution of the training data, we ran exactly this experiment: LongLive trained with the same MST prompts and schedule, without NAM and SMA.
Table d: MST ablation for 60s multi-prompt generation.
| Method | Memory | Training Paradigm | Quality Score ↑ | Aesth. Drift ↓ | Subj. Consist. CLIP ↑ | Subj. Consist. DINO ↑ | Scene Consist. CLIP ↑ | Scene Consist. DINO ↑ | Prompt Align. ↑ | Transition Align. ↑ |
|---|---|---|---|---|---|---|---|---|---|---|
| LongLive | Frame Sink | w/o MST | ||||||||
| LongLive + MST (new) | Frame Sink | MST | ||||||||
| MemFlow w/o MST | Frame Sink + NAM + SMA | w/o MST | ||||||||
| MemFlow | Frame Sink + NAM + SMA | MST |
(1) MST training alone improves LongLive, mainly in transition alignment: the model learns to follow more complex narrative changes, such as subject removal and re-introduction. It also improves scene consistency and subject consistency to some extent. Its scene consistency is close to MemFlow, but its subject consistency remains far below MemFlow, showing that MST training alone cannot make up for the absence of the memory design in preserving subject identity. (2) LongLive + MST still remains well below MemFlow in subject consistency, because a first-chunk sink cannot store subjects that are introduced later; the cue needed at re-appearance is not in the context, and simply training cannot recover it. (3) Our model with the memory design but without MST (third row) shows a deterioration across all visual and semantic consistency metrics compared with full MemFlow. MST further improves fine-grained subject identity (DINO), scene consistency, and transition alignment on top of the gains already provided by the memory design, while subject consistency under CLIP remains nearly unchanged. These results suggest that MST helps the model make fuller use of the retrieved memory and manage complex content transitions. The training paradigm and the memory mechanism are complementary, and the full model performs best among these variants.
R3-W1 & Q1: Numerical discrepancies
Thank you for checking the numbers carefully. The discrepancy comes from two different sources for the LongLive numbers and does not affect our conclusion. The LongLive row in Table 2 reports the numbers published in the LongLive paper, whereas the per-dimension LongLive results in Tables B/C come from our own evaluation of the released checkpoint. MemFlow is evaluated by us in both places, which is why its numbers match. The same holds for the 30s setting (Table 4 versus Tables B/C). We could not exactly match the published LongLive numbers with the released checkpoint. The gap may come from evaluation details that are not fully specified, such as the prompt rewriting applied to the prompts before generation and random seeds, and GPU hardware differences. Under either set of LongLive numbers, MemFlow consistently achieves a higher total score at both 5s and 30s, so this discrepancy does not change our conclusion about the advantage of our method. In the revision, we will add a clarification in the appendix stating that the LongLive results in Tables 2 and 4 are taken from the LongLive paper, whereas those in Tables B/C come from our own evaluation of the released checkpoint.
R3-W2 (part 1): More recent baselines
We added recent methods under two protocols.
(1) Our multi-prompt 60s.Four recent methods that support streaming long video generation with prompt switching, evaluated on our 60s multi-prompt test set:Table a: Comparison of recent baselines for 60s multi-prompt generation
MemFlow achieves the best quality score, the lowest aesthetic drift and the best prompt alignment, and clearly leads the four recent methods in scene consistency under both features as well as in subject consistency under DINO. LongLive 2.0, built on a 5B backbone, obtains higher subject consistency under CLIP and the highest transition alignment. This is expected: before its final Distribution Matching Distillation (DMD), LongLive 2.0 is trained on large-scale long, multi-shot video data, which improves cross-shot consistency, whereas MemFlow is only fine-tuned at the DMD stage on a multi-switch prompt set and builds on a smaller base model. Helios, despite its 14B backbone and competitive quality score, shows the weakest subject consistency, suggesting that model capacity alone does not preserve identities across prompt switches. Thus MemFlow remains competitive against more recent baselines: it is the best or second best on seven of the eight metrics with a 1.3B model.