- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3(+1)
- Soundness
- 2
Read review
Paper summary
This paper proposes Adaptive Visual-Textual Reasoning (AVTR), which uses generative supervision to learn question-conditioned continuous visual states and adaptively selects among direct answering, visual imagination, textual reasoning, and their composition. Training comprises visual replay, question-conditioned visual reflection, imagination-guided supervised finetuning, and outcome-guided routing optimization. The visual generator is used only during training; inference directly uses the continuous visual states without generating pixels.
Experiments cover 16 benchmarks spanning image understanding, spatial reasoning, video understanding, and temporal grounding, with evaluations on both 9B and 2B backbones. The paper reports a 4.5-point improvement in average score and approximately 33% lower inference latency relative to the backbone’s textual-reasoning mode.
Critical strengths
1. The method is well motivated and supported by comparisons within the same model. AVTR uses generative supervision to learn question-conditioned visual states while avoiding image-generation overhead at inference. Table 4 compares reasoning routes using the same checkpoint, showing complementary strengths of visual and textual reasoning and that no fixed route is consistently optimal across tasks. This provides direct empirical support for adaptive selection of reasoning modalities.
2. The evaluation is broad and includes informative ablations. Results across diverse image and video tasks, two model scales, and ablations of training stages and reasoning routes collectively support the framework’s effectiveness. Beyond aggregate improvements, the paper examines which tasks benefit from each reasoning modality. These findings support the method’s practical value and are an important basis for my positive recommendation.
Critical weaknesses
1. The contribution of generative supervision is not fully isolated. Table 5 includes pure-SFT and feature-alignment controls, but it is unclear whether these variants use the same relevant training data, Stage-3 optimization, and inference routes as full AVTR. If these conditions differ, the performance gaps may reflect differences in supervision, training, and routing. The results therefore support the complete framework, while the specific advantage of generative supervision over alternative objectives requires a clearer explanation.
2. The efficiency measurement protocol needs further clarification. Figure 5 reports an appealing improvement in both performance and latency, but the hardware, batch size, timing boundaries, and averaging procedure are not sufficiently specified. Appendix B also introduces a fallback to non-thinking predictions when generation reaches the length limit, without clarifying whether the preceding reasoning and additional fallback computation are included in latency. Since efficiency is a central contribution, these details are important for interpreting the conditions under which the reported 33% latency reduction holds.
Questions for authors
1. Contribution of generative supervision: Do the pure-SFT, feature-aligned, and full AVTR settings in Table 5 use the same training data, Stage-3 optimization, and inference routes? If not, please identify the main differences. If results controlling for these factors already exist, please provide them or indicate their location in the paper. Otherwise, please explain the limitations of the current comparison in separating the contribution of generative supervision from other training factors; retraining models is not requested.
2. Efficiency measurements: Please specify the hardware, batch size, timing boundaries, and averaging procedure for the AVTR and backbone textual-reasoning results in Figure 5, and clarify whether both were measured under the same conditions. When the fallback described in Appendix B is triggered, does the reported latency include both the preceding reasoning and the additional fallback computation? Please provide fallback frequencies if they are already recorded; otherwise, clarification of the accounting procedure and its limitations is sufficient, without new evaluations.
3 comments
Apology and Correction of the Review
Thank you for pointing this out. You are correct—the review was intended for another submission. I sincerely apologize for the confusion and the rebuttal time this has cost you. I have corrected the review and rating, with clarification requests focused on existing experimental details and no new experiments requested.
Response to Reviewer zPgD
Thank you for timely updating your review and for your positive assessment of our work. We appreciate your constructive feedback and address the two concerns below.
W1 / Q1. Contribution of generative supervision
We would like to clarify that the Pure SFT and Feature Alignment variants are compared against our model before Stage-3 RL instead of the final AVTR with adaptive routing. This reference corresponds to the "AVTR w/o adaptive RL (S3)" row in the lower half of Table 5. We report the results side by side here for clarity.
| Method | V* | HR-4K | HR-8K | BLINK | ERQA | MMSI | VSI | RWQA | MVBench | Video-MME | LVB |
|---|---|---|---|---|---|---|---|---|---|---|---|
| No visual supervision | 86.9 | 82.3 | 80.6 | 72.1 | 47.7 | 37.5 | 65.3 | 75.0 | 69.5 | 72.1 | 68.7 |
| Feature supervision | 87.4 | 82.3 | 79.1 | 72.5 | 48.0 | 37.2 | 65.1 | 75.6 | 69.8 | 72.9 | 69.4 |
| Generative supervision | 88.4 | 86.7 | 83.8 | 75.9 | 50.7 | 38.4 | 67.9 | 76.3 | 71.5 | 74.4 | 69.4 |
Training data and supervision. All three variants use the same answer-SFT dataset, with the following differences:
- Pure SFT uses no visual targets, as it does not involve visual supervision.
- Feature alignment uses the same question-conditioned visual targets as generative supervision and follows the same Stage-1 and Stage-2 training, replacing the generative objective with feature-space cosine alignment.
- Generative supervision uses the same visual targets and Stage-1/2 training, with an aligned generator providing visual supervision. Stage-0 is a necessary VLM–generator alignment stage for our generative supervision, during which the VLM remains frozen and its reasoning ability is untouched.
Evaluation protocol. All three variants are evaluated before Stage-3 RL, without adaptive routing. Pure SFT directly generates short answers, while feature alignment and generative supervision use a forced Visual route followed by short-answer generation. Therefore, this comparison isolates the effects of different supervision methods without involving Stage-3 optimization or adaptive routing.
Thank you for raising this concern. We will clarify these training and evaluation details in the revision.
W2 / Q2. Efficiency measurement protocol
Thank you for pointing this out. We clarify the efficiency measurement protocol below and will add these details to Appendix B.
Hardware and batching. All methods are evaluated under the same settings, using NVIDIA H100 80GB GPUs, one vLLM engine per GPU, greedy decoding, 8192 new generation token limit, and same visual input budgets. We use continuous batching with up to 32 concurrent sequences per engine and data parallelism across GPUs.
Timing and averaging. The measurement includes multimodal input processing, vision encoding, prefill, decoding, and routing decisions. We calculate the average per-query time cost.
Length limit and fallback. When a thinking trace reaches the 8192 token limit, generation is truncated before producing a final answer. To avoid penalizing accuracy solely due to truncation, we use the corresponding short-answer prediction for reliable evaluation. In these cases, the reported latency includes the full reasoning generation but excludes the additional cost of the short-answer replacement. On average, 7.2% of Qwen3.5 thinking traces and 5.4% of AVTR thinking traces reach this limit.
Review Appears to Refer to a Different Submission
Thank you for your review. However, the comments above appear to refer to a different paper and do not match the content or method of our submission. Could you please update the review with comments specific to our paper and revise the score accordingly? We would be happy to respond to any concerns about our work once the correct comments are provided.