- Rating
- 3(+1)
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces ReBind, a supervision framework for multi-reference video editing that combines explicit editing and preservation requirements with accurate source attribution. It addresses underspecified preservation constraints and incorrect assignments of entities or attributes to reference images. First, supervised fine-tuning trains ReBind-Instruct to generate structured instructions from source and edited video pairs together with reference images. A second stage applies GRPO, using content-level and relation-level rewards to improve semantic completeness and source consistency, with a length reward to limit verbosity. The resulting annotations train ReBind-Edit, an LTX-2.3-based editor that jointly conditions on the source video and multiple reference images. Benchmark comparisons and controlled ablations show that detailed instructions benefit editing and that corrupting reference assignments reduces editing quality even when descriptive content is largely preserved. On UniVBench and IntelligentVBench, ReBind-Edit achieves the best overall performance among the open-source methods evaluated.
Critical strengths
-
The paper addresses an important challenge in multi-reference video editing: accurately associating edited attributes with their corresponding visual references while preserving source-video content. The proposed ReBind supervision provides a clear and structured way to represent editing requirements, preservation constraints, and reference relationships.
-
ReBind-Edit achieves strong performance on IntelligentVBench and UniVBench, outperforming the compared open-source baselines. In particular, the controlled attribution-corruption experiment in Table 4 provides useful evidence that accurate reference assignments contribute to improved video editing performance.
Critical weaknesses
-
The overall training pipeline mainly follows the conventional SFT + GRPO paradigm. Although the proposed reference attribution supervision is task-specific, its methodological novelty beyond existing instruction tuning and reward optimization approaches is not sufficiently established. It is unclear why the proposed lengthy ReBind instructions are necessary compared with simpler explicit reference bindings or structured entity–attribute–source representations. Moreover, the Dual Checklist Reward is relatively straightforward, and the authors do not demonstrate why separate preservation and modification checklists are more effective than a single unified checklist.
-
Large multimodal models are extensively involved in data construction, reward computation, and evaluation. In particular, GPT-5.1 is used for both reward-related processing and final evaluation, potentially introducing evaluator-specific biases. The learned instructions may favor the detailed descriptions preferred by these models rather than those most effective for video editing. Independent evaluation would strengthen the conclusions.
-
ReBind-Instruct is evaluated using target videos, whereas the actual editing pipeline uses Qwen3-Omni to rewrite user instructions without access to target videos (Section 4.3). Although the complete editing pipeline is evaluated, the reported instruction quality scores do not directly establish the reliability of the deployment-time rewriter. A separate analysis is needed to determine whether rewriting introduces errors or alters the original editing intent.
-
Section 5.5.1 reports that a subset of reference assignments is corrupted but does not specify the proportion of affected samples or assignments, or how the subset is selected. Without these details, the 0.27-point performance decrease in Table 4 is difficult to interpret and the experiment is not fully reproducible.
Questions for authors
-
In Section 4.3 , has the Qwen3-Omni rewriter been evaluated separately without target videos? Please report any available checks on whether rewritten instructions alter the original editing intent or preservation requirements, and clarify their impact on the final outputs. This would help assess the inference-time step that the target-conditioned instruction evaluation in Appendix C.2 does not directly test.
-
For the attribution-corruption experiment in Section 5.5.1, what proportion of training samples and image-reference assignments were modified, and how was the affected subset selected? These details are needed to relate the 0.27-point drop in editing Overall to the annotation-error rate and to reproduce the controlled experiment.
-
Appendix B.1configures eight reference slots but uses only one to five reference images during training. Does the eight-slot configuration describe input capacity only, or are editing results with six to eight references available? Clarifying this distinction would establish the tested operating range without equating architectural capacity with demonstrated editing reliability.
6 comments
Rebuttal for Reviewer QhBm (2/3)
W2. Evaluator bias and independent evaluation
Thank you for raising this important concern! We address it through additional instruction evaluations with two alternative judges and independent assessments of downstream video editing performance.
We re-evaluate all models in Table 3 using Claude-Opus-5.5 and Gemini-4.0 Argon. The results are reported below:
| Model | GPT-5.1 (original) | Claude-Opus-5.5 | Gemini-4.0 Argon | ||||||
|---|---|---|---|---|---|---|---|---|---|
| IQ ↑ | RA ↑ | Overall ↑ | IQ ↑ | RA ↑ | Overall ↑ | IQ ↑ | RA ↑ | Overall ↑ | |
| Closed-Source Models | |||||||||
| Gemini-2.5-Pro | 46.37 | 63.85 | 55.11 | 55.04 | 60.73 | 57.89 | 55.70 | 38.82 | 47.26 |
| Gemini-3.1-Pro | 59.24 | 52.90 | 56.07 | 64.95 | 49.84 | 57.39 | 68.50 | 32.11 | 50.30 |
| Open-Source Models | |||||||||
| Qwen2.5-Omni-3B | 10.10 | 21.86 | 15.98 | 19.24 | 15.13 | 17.19 | 19.09 | 5.59 | 12.34 |
| Qwen2.5-Omni-7B | 14.32 | 35.37 | 24.84 | 19.37 | 32.43 | 25.90 | 19.85 | 11.53 | 15.69 |
| Qwen3-Omni-Captioner | 22.01 | 39.47 | 30.74 | 40.96 | 36.84 | 38.90 | 43.27 | 17.05 | 30.16 |
| Qwen3-Omni-Instruct | 31.82 | 49.59 | 40.70 | 43.34 | 50.09 | 46.71 | 43.44 | 27.30 | 35.37 |
| Gemma4-31B-it | 49.49 | 36.71 | 43.10 | 56.24 | 31.25 | 43.75 | 58.31 | 17.02 | 37.66 |
| ReBind-Instruct (Ours) | 61.68 | 59.60 | 60.64 | 67.95 | 52.71 | 60.33 | 70.42 | 32.58 | 51.50 |
ReBind-Instruct achieves the highest IQ and Overall among all evaluated models under both alternative judges, and ranks first among open-source models on all three metrics. Its Overall score exceeds its Qwen3-Omni-Instruct base by 13.62 points under Claude and 16.13 points under Gemini. These results provide support across judges for the instruction-level improvements, reducing the concern that the reported gains depend specifically on GPT-5.1.
Our evidence also includes independent evaluations of the edited videos themselves. On the single-reference IntelligentVBench benchmark, editing performance is evaluated using Gemini-2.5-Pro, where ReBind-Edit achieves the highest average score among all evaluated methods (Table 2). Separately, our human study on multi-reference editing asks participants to rank anonymized outputs based on instruction following, source-video preservation, reference-image preservation, and visual quality. ReBind-Edit receives the highest preference scores across all four criteria (Figure 4). These assessments directly evaluate editing outcomes and provide complementary evidence beyond instruction quality assessed by automated judges.
We will include these additional results and clarify the evaluation models and protocols in the revised manuscript.
Rebuttal for Reviewer QhBm (3/3)
W3 & Q1. Reliability and impact of automatic instruction rewriting
Thank you for this valuable comment! We agree that the target-conditioned instruction evaluation in Table 3 does not directly establish the reliability of deployment-time rewriting. Automatic rewriting can introduce inaccuracies or deviations from the original editing intent, potentially affecting downstream editing performance. We therefore compared downstream editing performance using instructions generated by Qwen3-Omni-30B-A3B-Instruct and Claude-Opus-5.5, together with Claude instructions reviewed and corrected by human annotators.
Both automatic rewriters used only the original user instruction, source video, and reference images, without access to target videos. We evaluated all three instruction sources on the same 100 UniVBench MRVE cases, keeping the ReBind-Edit checkpoint, generation settings, and per-case random seeds fixed. All generated videos were evaluated against the original user instructions and benchmark visual inputs, rather than the rewritten instructions.
| Instruction source | Sub. ↑ | Back. ↑ | Action ↑ | Cam. ↑ | Color ↑ | Light. ↑ | Style ↑ | Rel.Pos. ↑ | Overall ↑ |
|---|---|---|---|---|---|---|---|---|---|
| Qwen3-Omni-30B-A3B-Instruct | 6.20 | 7.41 | 7.12 | 8.21 | 7.39 | 7.85 | 6.54 | 7.70 | 7.30 |
| Claude-Opus-5.5 | 6.24 | 7.34 | 7.54 | 8.38 | 7.12 | 7.74 | 6.45 | 7.70 | 7.31 |
| Human-corrected instructions | 6.33 | 7.67 | 7.43 | 8.61 | 7.37 | 7.79 | 6.68 | 7.94 | 7.48 |
Qwen3-Omni achieves an Overall score of 7.30, closely matching Claude-Opus-5.5 at 7.31 and falling 0.18 points below the human-corrected reference. These results show that the default rewriter maintains downstream editing performance close to the human-corrected condition on the evaluated cases, while manual correction provides further improvement.
We retain Qwen3-Omni as the default open-source rewriter to facilitate community use without requiring a proprietary rewriting API. We will include these results and the experimental details in the revised manuscript and investigate further improvements to deployment-time instruction rewriting.
W4 & Q2. Reference attribution corruption protocol
Thank you for requesting this clarification. We identified eligible multi-reference training samples containing correct image-reference assignments with incompatible alternative references in the same sample. We randomly selected eligible samples accounting for 30.0% of the training set.
Within each selected sample, we redirected each verified correct image-reference assignment with an incompatible alternative to one such alternative from the same sample, choosing randomly when multiple alternatives were available. The descriptive text, instruction format, and all other assignments, including <Video_1> references, remained unchanged. In total, 38.0% of image-reference assignments across the full training set were modified.
Both settings used the same visual training data, editor architecture, and hyperparameters. Under this corruption setting, Editing Overall decreased by 0.27 points, with declines across all eight editing dimensions while IQ remained nearly unchanged. We will add these statistics and the corruption procedure to Section 5.5.1.
Q3. Eight-slot input capacity and evaluated reference range
Thank you for asking us to clarify this distinction! The eight-slot configuration was preset during implementation to provide additional input capacity. After data construction and filtering, our training samples contained one to five reference images, while the original eight-slot configuration was retained. As described in Appendix B.1, unused slots are masked during attention.
Our reported evaluations cover one to five reference images; the benchmarks do not include cases with six to eight references. The model can process up to eight reference images without structural modification. In a small number of manual tests, we observed satisfactory editing results in some eight-reference cases. However, these successes have not yet translated into consistently reliable performance across cases.
We will clarify the distinction between input capacity, training coverage, and the evaluated reference range in Appendix B.1 and Section 5. Extending training coverage and improving robustness with six to eight references remain future work.
Rebuttal for Reviewer QhBm (1/3)
We sincerely thank you for your constructive review, especially for your positive comments on our motivation, method design, and quantitative results. We address your concerns point by point below.
W1. Contribution, instruction supervision, and checklist design
Thank you for these constructive comments!
1. Source attribution supervision and targeted optimization
ReBind contributes a supervision formulation and targeted optimization for multi-reference video editing, with SFT and GRPO serving as the optimization tools. The formulation jointly specifies editing requirements, preservation constraints, and the visual sources of entities and attributes. ReBind-Instruct learns to produce these annotations through complementary objectives for content quality and reference consistency.
Our key insight is that descriptive completeness and source-attribution correctness are distinct requirements for effective editor supervision. Table 4 provides controlled evidence for this distinction: corrupting selected image-reference assignments while preserving descriptive text, instruction format, visual training data, and editor training settings leaves IQ largely unchanged, but reduces Editing Overall by 0.27 points, with declines across all eight dimensions. Thus, detailed descriptions remain insufficient when their source assignments are incorrect.
Table 5 further supports optimizing attribution separately from descriptive quality: adding the relation reward improves RA, even though IQ decreases relative to the setting using the content reward alone. Together, these findings support explicit source attribution and its targeted optimization as complementary to descriptive enrichment, which constitutes the methodological focus of ReBind.
2. Instruction quality, attribution accuracy, and downstream editing
We evaluate instructions along two dimensions: Instruction Quality (IQ) measures semantic completeness and correctness, while Reference Accuracy (RA) measures source-attribution accuracy.
To examine the value of detailed descriptions beyond explicit reference bindings, we compare full ReBind instructions with compact versions derived from the same annotations. The compact instructions retain the original reference assignments and edit/preserve targets while removing detailed appearance descriptions. Both settings use the same visual training data, editor architecture, and training configuration, with 50K examples and 5K training steps.
The two variants achieve similar RA scores, while full ReBind instructions achieve substantially higher IQ. Full instructions improve Editing Overall by 0.12 points, with gains across all eight editing dimensions, particularly Subject, Color, and Style. These results support retaining detailed descriptions alongside explicit source bindings to improve fine-grained editing performance. We will include this additional comparison and its construction details in Section 5.5.1.
3. Purpose of the dual checklist design
The dual checklist design makes both preservation and modification requirements explicit in the content reward. Correctly describing the requested changes is insufficient if the instruction omits source content that should remain unchanged.
As described in Section 4.2.2 and illustrated in Figure 3, these requirements can concern different attributes of the same entity: its identity and clothing may change, while its motion and interactions should be preserved. We therefore derive keypoints for both aspects from the ground-truth instruction and jointly evaluate the generated instruction for missing, incorrect, and hallucinated content. This allows the reward to penalize omitted preservation requirements even when the requested modifications are accurately described.
Here, “dual” refers to the two complementary categories used to construct the supervision, rather than two independent evaluations. A unified checklist retaining the same requirements and scoring rules can implement the same design. We will clarify this distinction and the joint evaluation procedure in the revised manuscript.