- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper propose V2T, a 2-stage method to improve visual reasoning. First, it trains a teacher LVLM on filtered interleaved data. Second, it distills a student that reasons only in text. The student is trained with ground-truth text cross-entropy plus a KL loss to the teacher's logits When a reasoning image is a crop of the original, the teacher's attention is also distilled. An optional GRPO stage adds an attention-IoU grounding reward. Experiments reports clear gain of V2T over teacher and other baselines.
Critical strengths
- A simple, practical idea: Distilling visual evidence into text is a clean approach to retain useful multimodal information while reducing inference cost. The attention distillation idea is simple yet shown effective in experiments.
- Clear experiment design and gains: Gains are observed in comparison with multiple representative visual reasoning baselines. The training and inference cost reported is substantially lower than other methods.
Critical weaknesses
- Fair and complete baselines:
The authors compare against latent reasoning and text-only CoT methods on the Zebra-CoT held-out test set, but the paper does not describe how these baselines were trained. Given most results are lower than the Qwen2.5-VL base model, I suspect the compared methods were not trained on the Zebra-CoT data. A comparison under the same training data budget would make the results considerably more convincing. In addition, the paper would benefit from two simple baselines trained on the same data: (1) SFT on answers only, without reasoning traces, and (2) SFT on text-only CoT, both on same training set. These would help show that the gains come from the proposed method rather than from the additional training data.
In addition, some reported baseline results appear to differ from those in the original papers (e.g., MONET reports 83.25 on V* and LVR reports 81.7 on V*). If this is due to differences in model versions or evaluation settings, it would be helpful for the authors to clarify this in the paper. Addressing these points would strengthen the consistency of the results in Table 2 and the overall empirical claims.
- Unfaithful cot of student and generalization ability:
In the demo presented (fig.7,8), the student still outputs text chain of thought without the actual image. While I understand this is inherited from teacher, but the pattern suggest the student model may overfit to answer distribution and lose generalization. It would be helpful if the authors could discuss this behavior and evaluate the student on additional datasets, including out-of-distribution datasets for the same task, to better assess its generalization ability.
Questions for authors
See weakness above.
I have one additional, more minor question. The proposed method relies heavily on attention distillation, which can only operate over the original input image. Visual reasoning problems of this kind, which mainly require grounding in and operating on the input image, are now largely addressed by tool-calling approaches. It is unclear whether the method can generalize to settings where the visual evidence comes from outside the original image, for example generating new image as evidence. I would argue these are the settings where this kind of visual reasoning matters most. Could the authors comment on how the method might extend to such problems and thoughts on visual reasoning pattern?
4 comments
-
W2: Unfaithful CoT of student and generalization ability.
Thank you for raising this. We read the concern as two questions: whether the inherited phrasing indicates the student absorbed surface form rather than capability, and whether it generalizes.
On the phrasing: it is inherited vocabulary, not an empty template. No image is generated, but the operation of the phrasing names — concentrating on a sub-region before reporting what is there — is what the student does. Attention IoU rises from 0.191 for the base model to 0.269 for V2T (Table 5), so the regions the trace refers to are the regions the student attends to, and in Figs. 7 and 8 it resolves cases the teacher gets wrong. Inheriting a format while exceeding the teacher’s accuracy is not the signature of imitation.
On generalization: this is already tested. V2T is trained on Zebra-CoT and evaluated on HR-Bench 4K/8K, V*Bench, BLINK, and POPE, none of which share Zebra-CoT’s distribution or task format, and it improves over the base model on every one (Table 2). A model overfit to the teacher’s answer distribution would not transfer across four unrelated benchmarks.
We additionally test whether the framework itself transfers beyond visual reasoning. This is a separate training run rather than the same checkpoint: we apply V2T to ViRC and evaluate on mathematical reasoning benchmarks (Table 3 in the revision).
Model Post Training Recipe Post Training GPU hours MathVista Geometry MathVista Algebraic MathVista Math Word MathVista Geometry Problem LogicVista Avg. Qwen2.5-VL-7B base - - 70.3 69.4 74.2 70.2 43.6 65.5 Text-only SFT SFT 40 74.9 74.0 73.7 76.0 43.2 68.4 Interleaved SFT SFT 50 73.6 73.7 71.0 75.0 46.3 67.9 V2T SFT 50 74.1 75.1 72.0 76.4 49.0 69.3 V2T + GRPO SFT + RL 130 78.7 77.2 83.9 81.2 46.1 73.4 Vision-R1-7B SFT + RL 3392 76.2 74.7 76.3 78.4 45.4 70.2 VL-Rethinker-7B RL 128 76.2 74.4 80.6 78.4 45.9 71.1 VLAA-Thinker-7B RL 167 68.2 67.6 83.9 68.8 46.3 67.0 MONET-7B SFT + RL 330 58.2 58.7 77.4 57.2 39.6 58.2 LVR-7B SFT 160 66.5 64.1 75.3 67.8 35.3 61.8 In this setting V2T is trained on ViRC [1]; V2T + GRPO is initialized from that checkpoint and trained further with GRPO on ViRL [2]. These test whether the V2T framework transfers to another domain, and are not evaluations of the Zebra-CoT checkpoint used in the main experiments.
The framework transfers. Among SFT-only models, V2T improves over the base model (65.5 → 69.3) and over Text-Only SFT trained on the same data (68.4 → 69.3), with its clearest gain on LogicVista (49.0, the highest of any model listed). Vision-R1 and VL-Rethinker both use RL, so the matched comparison for them is V2T + GRPO, which reaches 73.4 against their 70.2 and 71.1 — at 130 GPU-hours against Vision-R1’s 3,392. These baselines are likewise trained on mathematical reasoning data. Neither MathVista nor LogicVista appears in ViRC or ViRL training, so these are out-of-distribution evaluations within the mathematics setting.
[1] Wang et al., ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking, CVPR 2026, arXiv:2512.14654.
[2] Wang et al., From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning, 2025, arXiv:2511.23031.
-
Q1: Generalizing beyond the original input image.
Thank you for raising this. We would first clarify that V2T neither relies primarily on attention distillation nor is limited to reasoning images that are crops of the input. Nearly 30% of our filtered Zebra-CoT set consists of newly constructed visual states — generated molecular structures in Chemistry (12.5%) and future board positions in Chess (15.9%, Table 9). These cannot be mapped back to the input, and their reasoning signal transfers through logit distillation alone.
Attention distillation is optional, applied only where a spatial mapping exists. Logit distillation alone raises the average from 58.9 to 61.5; attention alone reaches 59.4; together 62.8 (full ablation in our response to Reviewer 3VAQ’s W2). The teacher’s reasoning behavior is the primary signal. For settings involving newly constructed evidence, V2T simply omits the attention term — no change to the framework. Logit distillation is agnostic to how the reasoning image was produced, so the binding constraint on extending to such settings is the availability of interleaved training trajectories, not the method.
On tool-calling: we would push back on the premise that it largely solves this class of problem. The tool-based baselines are the direct evidence — Thyme and DeepEyes reach 58.0 and 59.1 against V2T’s 62.8 on the broader suite, at 45× inference cost, and BAGEL-Zebra-7B, which generates new images via a diffusion head rather than cropping, reaches 57.8 at 30×. Fig. 2 suggests why: each visual state inserted into the reasoning interferes with the text that follows, and the cost compounds as states accumulate, so producing more visual evidence at inference does not straightforwardly help.
V2T can build on these methods rather than compete with them. Tool-generated images are intermediate visual states of exactly the kind V2T distills, so a teacher trained on tool-call trajectories would let a student inherit the reasoning those tools enable without invoking them at inference. The Visual Search portion of Zebra-CoT is already this case, since its reasoning images are crops of the input — the same artifacts a cropping tool produces.
On visual reasoning patterns more broadly: the fact that distillation works at all suggests much of what a reasoning image contributes is recoverable in text, with the image serving during training to fix which properties matter rather than supplying something text cannot carry. The open question, in our view, is when carrying a visual state beats describing it. Existing methods assume the answer is nearly always; our results suggest otherwise.
Dear Reviewer,
Thank you again for your feedback. We address your concerns about baseline fairness and generalization by running the baselines you suggested, reporting the student’s performance on out-of-distribution visual tasks, and testing V2T separately in mathematics.
Please let us know if any questions remain before the discussion deadline. If our response addresses your concerns, we would appreciate it if you would reconsider your score.
Best regards,
The Authors
We thank the reviewer for their valuable feedback, recognizing V2T as a simple and practical approach, the effectiveness of attention distillation, and the clear experimental design showing gains over representative visual reasoning baselines at substantially lower training and inference cost.
W1: Fair and complete baselines.
The reviewer is correct that LVR and MONET are not trained on Zebra-CoT; we evaluate their publicly released checkpoints. These methods are defined by their training pipelines as much as their architectures — MONET trains on 125K interleaved samples plus RL, LVR on 438K Visual-CoT samples — so retraining either on our 23K set would produce a data-starved variant rather than a methodologically equivalent comparison. The released checkpoints represent each method as its authors intended, trained on substantially more data than V2T. This follows standard practice in this area: LVR compares against PixelReasoner and Vision-R1, and MONET against DeepEyes and LVR, in each case without retraining on matched data. Bagel-Zebra is the informative case, since it is trained on Zebra-CoT with 182K samples, roughly 8× ours, and reaches 57.8 against V2T’s 62.8.
Table: Training budgets for all compared methods. SFT and RL columns give the number of training samples; — indicates the method does not include that stage. V2T trains on the least data and compute of any method compared; even with GRPO it uses fewer GPU-hours than every baseline.
That these checkpoints fall below Qwen2.5-VL-7B on the Zebra-CoT held-out set reflects the training-data mismatch the reviewer identifies together with the protocol differences discussed below, not a failure to reproduce them.
Controlled baselines on matched data. We report both baselines the reviewer suggests — Answer-Only SFT, trained on final answers alone, and Text-Only SFT, trained on textual CoT without intermediate images or distillation — from the same base model on the same Zebra-CoT set.
Reasoning traces matter in-domain: answer-only supervision loses 8.3 points to text-only CoT on the held-out set, though out of domain the two are indistinguishable (58.5 vs. 58.9) and both sit near the base model. V2T exceeds both on both evaluations — by 18.8 and 10.5 points on the held-out set, and 4.3 and 3.9 on the broader suite — so the gains come from the distillation signal rather than from exposure to the training set.
The exception is RPM, where answer-only supervision scores highest (85.4). RPM patterns are recoverable by direct visual pattern matching, so answer-only training can exploit this shortcut rather than reasoning through the transformation.
On differing baseline numbers. Reported scores for the same model vary across papers because protocols differ. On V*Bench, MONET reports 83.25 for MONET and LVR reports 81.7 for LVR, while Qwen2.5-VL-7B is reported at 78.5 by LVR, 76.4 by MONET, and 75.9 by us. LVR uses exact matching; MONET uses exact matching primarily, invoking DeepSeek-V3.1 or Gemini-2.5-Pro only when ambiguous. These diverge in both directions — exact matching rejects semantically correct answers that differ in formatting, common for long chains of thought, and accepts superficial string matches regardless of whether the reasoning supports them. Published numbers from different papers are therefore not directly comparable.
What matters for our claims is internal consistency. Every model in Tables 1, 2, and 4 is evaluated with the same framework, the same Qwen3-235B-A22B-Instruct-2507-FP8 judge, and the same settings, under a shared 32,768-token budget chosen to accommodate longer tool-calling contexts. For the latent-reasoning baselines we use MONET’s released vLLM implementation, adapted for LVR, with both set to 10 latent steps per MONET’s public implementation. Appendix D verifies judge stability: GPT-4o and our judge agree within 0.5 points across HR-Bench 4K/8K and V*Bench.