- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This work presents Looping Visual Tokens (LVT), a recurrent mechanism for vision‑language models that iteratively updates native image tokens via a shared transformer block, without expanding token sequence length. Trained by aligning evolving visual states to perceptual targets derived from successive intermediate observations, LVT supports multi‑step spatial reasoning. Evaluated on visual spatial planning (VSP) and mental‑rotation tasks, ordered sequence supervision substantially improves generalization to longer transformations and larger unseen grids compared with answer‑only or final‑state supervision; LVT outperforms textual chain‑of‑thought on size extrapolation, where text suffers transcription failures. Diagnostic decoding and state interventions further distinguish perceptually recoverable visual content from the actual usage of recurrent states for downstream prediction.
Critical strengths
-
The method proposed in the paper doesn’t add extra latent tokens but directly reuses the model’s original image tokens; the backbone model is frozen, and only LoRA is fine-tuned. The recursive output calculation is directly connected to the existing pre-trained task readout head, so there’s no need to train a multi-modal model from scratch, making it easy to plug into existing VLMs.
-
The paper compares training with just the answer, the final state, ordered sequences, and shuffled supervision. Experiments show that supervising with ordered intermediate observations greatly boosts long-sequence and out-of-distribution generalization, performing significantly better than just using the final labels on longer paths and larger grid tasks.
-
The paper is written smoothly, and the main ideas are clear.
Critical weaknesses
-
During the reasoning phase, we need to run the shared Transformer blocks multiple times, and the more iterations there are, the higher the computation cost. Even though the number of tokens stays the same, the number of times the decoder layers are called increases linearly with each loop.
-
Most experiments in the paper use a preset number of loop iterations; although they tested convergence stopping, automatically deciding when to terminate the inner loop is still an unsolved problem.
-
Training requires a complete, aligned sequence of intermediate frame observations as teacher signals. In real-world scenarios, it's really hard to get this kind of precise step-by-step supervision, which limits practical application.
Questions for authors
This issue mainly affected my impression of this piece of work: While the paper includes internal ablations and one re‑implemented latent‑token baseline (Mirage), its external baseline suite remains incomplete. It misses key competitors including LoopViT, LVR, CoVT and Monet from latent visual reasoning literature. Critically, it lacks a compute‑matched baseline that simply increases static transformer depth at inference, making it hard to disentangle gains from iterative recurrent state updates versus extra test‑time compute. All main experiments rely solely on Qwen3‑VL‑4B‑Instruct without cross‑backbone validation. Besides, textual‑CoT baseline uses mismatched training sampling and output budget, introducing confounding variables for comparison.
7 comments
Response to Reviewer 3Nee (2/4)
Q1: Latent visual reasoning baselines
We ported LoopViT [1], LVR [2], CoVT [3], Monet [4] and Mirage [5] to our backbone, data, update budget and scorer, and evaluated them on VR-Bench [6] (trained on its official training split), VSP [7], mental rotation and MindCube [8], with three seeds each:
| Method | VR-Bench (official split) | VSP, closed loop | Rotation 150°+180° (sets 1 / 2) | MindCube |
|---|---|---|---|---|
| LVT | 40.8 (8 rounds) | 96.4 | 84.2 / 84.0 | 86.5 |
| Direct FT | 33.2 | 59.2 (57.9 trained on the question and image only) | 49.1 / 51.7 | 59.9 |
| LoopViT | 35.1 (6 iterations) | 55.3 | 92.6 / 93.5 | 63.4 |
| LVR | 30.3 | 56.0 | 52.9 / 54.8 | 63.7 |
| CoVT | 33.0 | 62.2 | 50.1 / 50.2 | 67.7 |
| Monet | 26.0 | 41.2 | 45.5 / 47.3 | 56.7 |
| Mirage | 32.6 | 55.9 | 59.1 / 60.3 | 59.3 |
LVT is above every port on VR-Bench, VSP and MindCube, and above four of the five on rotation. Per port:
- LoopViT iterates tied blocks 10–17 of the backbone's vision encoder. On VR-Bench (6 iterations, original image only, as in the original) it is 1.9 points above direct fine-tuning (35.1% vs. 33.2%) and 5.8 below LVT, both in every seed. On VSP it is level with direct fine-tuning (55.3% vs. 57.9%) and 41.1 points below LVT, and on MindCube it is 23.1 below LVT. On rotation it is above LVT (92.6% / 93.5% vs. 84.2% / 84.0%).
- LVR uses the input image as the latent target and, like the original, sees only the original image. It is below direct fine-tuning trained the same way on VR-Bench (30.3% vs. 33.2%) and level with it on the other three tasks (VSP 56.0% vs. 57.9%).
- CoVT in the table is our surrogate, which uses targets from the frames and the backbone's own visual features, with linear heads, and inserts its 16 latent tokens before every answer. It is above direct fine-tuning on MindCube and level with it on VSP, rotation and VR-Bench (33.0% vs. 33.2%). We also ran the original expert-backed version (frozen SAM, Depth-Anything-V2 and DINOv2 targets, its four-stage curriculum, latent tokens emitted by the model): it is below the surrogate on VR-Bench, VSP and MindCube (26.0%, 51.0% and 53.8%), in every seed on VR-Bench and VSP, and on rotation it is 24.6 / 23.0 points below LVT (59.6% / 61.0%).
- Monet is trained with its auxiliary images, as in the original. It is below direct fine-tuning on VR-Bench and VSP and level with it on MindCube and at unseen rotation angles.
- Mirage first aligns four latent positions with the features of a helper image, each item's final frame, under a down-weighted answer loss, and then trains on the answer alone. On VR-Bench it is level with direct fine-tuning (32.6% vs. 33.2%) and 8.3 points below LVT in every seed. On VSP it is level with direct fine-tuning trained the same way (55.9% vs. 57.9%) and 40.6 below LVT. At unseen rotation angles it reaches 59.1% / 60.3%, 25.1 / 23.7 points below LVT. On MindCube it is level with direct fine-tuning (59.3% vs. 59.9%) and 27.2 points below LVT.
Training FLOPs per update relative to direct fine-tuning, frozen targets counted once per example (inference FLOPs per call in parentheses), and latent positions:
| Method | Latent positions (train / test) | VR-Bench | VSP | Rotation | MindCube |
|---|---|---|---|---|---|
| LVT | none; 8 / 20 / angle/30° / 4 rounds over the image tokens | 2.0× (1.65×) | 1.5× (2.9×) | 1.3× (1.2×) | 1.7× (1.25×) |
| LoopViT | none; iterated layers (6 iterations on VR-Bench) | 1.2× (1.2×) | 1.2× (1.7×) | 1.2× (1.2×) | 1.5× (1.3×) |
| LVR | 100–369 / 16 | 1.4× (1.04×) | 1.4× (1.04×) | 1.4× (1.06×) | 1.3× (1.01×) |
| CoVT | 16 / 16 | 1.1× (1.04×) | 1.1× (1.04×) | 1.1× (1.06×) | 1.1× (1.01×) |
| Monet | 8 / 8 | 2.4× (1.02×) | 1.9× (1.02×) | 1.8× (1.03×) | 1.7× (1.01×) |
| Mirage | 4 / 4 | 1.03× (1.01×) | 1.03× (1.01×) | 1.05× (1.02×) | 1.02× (1.00×) |
We have included these results in Section 4.2 and Appendices H, I and U of the revision.
[1] W.-J. Shu, X. Qiu, R.-J. Zhu, et al. LoopViT: Scaling Visual ARC with Looped Transformers. arXiv:2602.02156, 2026.
[2] B. Li, X. Sun, J. Liu, et al. Latent Visual Reasoning. ICLR 2026.
[3] Y. Qin, B. Wei, J. Ge, et al. Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens. ECCV 2026.
[4] Q. Wang, Y. Shi, Y. Wang, et al. Monet: Reasoning in Latent Visual Space Beyond Image and Language. CVPR 2026.
[5] Z. Yang, X. Yu, D. Chen, et al. Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens. CVPR 2026.
[6] C. Yang, H. Wan, Y. Peng, et al. Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks. arXiv:2511.15065, 2025.
[7] Q. Wu, H. Zhao, M. Saxon, et al. VSP: Assessing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for VLMs. arXiv:2407.01863, 2024.
[8] Q. Wang, B. Yin, P. Zhang, et al. MindCube: Spatial Mental Modeling from Limited Views. arXiv:2506.21458, 2025.
Response to Reviewer 3Nee (3/4)
Q2: Compute-matched baseline
Looping the direct fine-tuned checkpoint itself at test time, without training the loop, gives LVT's inference compute and does not help: it collapses on VSP and VR-Bench and changes nothing on MindCube and rotation (Q2 continued). We therefore also trained a compute-matched baseline: an answer-only loop that runs the same shared block for the same number of rounds with exactly LVT's parameters, so it adds the same depth at inference (the four shared layers per round) and has the same test-time compute, and is trained on the same data for the same number of updates, only without frames: no frame loss and, on VSP, no starts from intermediate frames (LVT without these starts still reaches 94.1%; three seeds). It separates the effect of the extra rounds from that of supervising the recurrent states with frames. On VR-Bench it runs without write-back, as LVT does there, and like every VR-Bench model here it sees only the question and the original image as input, never an intermediate frame:
| Task | LVT | Answer-only loop |
|---|---|---|
| VSP [1], closed loop, 20 rounds | 96.4 | 66.1 |
| MindCube [2], 4 rounds | 86.5 | 77.2 |
| Mental rotation, 150°+180°, fresh set 1 | 84.2 | 81.5 |
| VR-Bench [3], official split only, 8 rounds | 40.8 | 39.4 |
| VR-Bench, official + generated training levels, 8 rounds | 57.1 | 56.0 |
LVT is above this answer-only loop on all four tasks: by 30.3 points on VSP, 9.3 on MindCube and 2.7 on rotation (84.2% vs. 81.5%), and on VR-Bench in every seed, by 1.4 points on the official split (40.8% vs. 39.4%, p = 0.009), 1.1 with generated levels (57.1% vs. 56.0%) and 6.1 on the 258 official test mazes whose layouts do not occur in training (51.2% vs. 45.1%, with generated levels). We have included these results in Section 4.2 and Appendices J and U of the revision.
[1] Q. Wu, H. Zhao, M. Saxon, et al. VSP: Assessing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for VLMs. arXiv:2407.01863, 2024.
[2] Q. Wang, B. Yin, P. Zhang, et al. MindCube: Spatial Mental Modeling from Limited Views. arXiv:2506.21458, 2025.
[3] C. Yang, H. Wan, Y. Peng, et al. Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks. arXiv:2511.15065, 2025.
Response to Reviewer 3Nee (1/4)
Thank you for your careful and constructive review. We appreciate your recognition that LVT reuses the model's original image tokens and plugs into existing VLMs, and that ordered intermediate supervision improves long-sequence and out-of-distribution generalization. We respond to the three weaknesses first and then to your questions, starting with the baseline suite, which you noted mainly affected your impression (Q1).
W1: Inference cost of recurrence
Measured per test item, LVT takes as long as direct fine-tuning on VR-Bench (1.17 vs. 1.18 s) and 2–24% longer on VSP, rotation and MindCube. We now report FLOPs and measured latency for every task. Relative to direct fine-tuning, on one RTX 5090:
Training FLOPs include the frozen teacher, counted once per training example because its targets are fixed. The number of rounds can also be reduced: on VSP, propagating two rings per round halves the rounds and still reaches 85.3%, against 59.2% for direct fine-tuning (Appendices M and U).
W2: Automatic stopping
LVT does not need to decide when to stop: it runs a fixed number of rounds, and the rounds after the last frame are trained to keep the final frame, so extra rounds leave the state unchanged and the budget only needs to be large enough. This needs no stop label and no extra head, and it already runs on three tasks: every VSP call runs 20 rounds, trained with 0–4 such holding rounds, every VR-Bench item runs 8 rounds and every MindCube question 4, and all their gains are obtained with this fixed budget. On rotation, the one task whose main result sets the rounds from the angle stated in the question, both a learned stop (a halting head on the mean probe-image state) and a fixed 7-round budget with padding stay above direct fine-tuning at the unseen 150° and 180° (60.0% and 57.4%, 61.0% with write-back, vs. 49.1%, first fresh set), and the angle-derived rounds give 84.2% (Sections 3.3 and 4.1, Appendix P).
W3: Availability of frame supervision
LVT needs frames only during training; at test time it sees the same input as direct fine-tuning. The frames can also come from data that already exists: on VR-Bench they are rendered once offline, and on MindCube they are built from the real views supplied with each question plus a drawn top-down map. Frames can also be sampled from video. On MindCube, we generated a short clip between pairs of real views of each training scene with a video model conditioned on the real first and last frames (Wan 3.0 [4]), and supervised the rounds with frames sampled from these clips (8,225 of 10,000 training questions). This variant reaches 79.7% on the official test, against 59.9% for direct fine-tuning and 77.2% for the answer-only loop, and is above both in every seed. The clips are generated rather than recorded, but they show that frames sampled from video can supervise LVT, suggesting that recorded videos could also serve as a source of frames.
[1] C. Yang, H. Wan, Y. Peng, et al. Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks. arXiv:2511.15065, 2025.
[2] Q. Wu, H. Zhao, M. Saxon, et al. VSP: Assessing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for VLMs. arXiv:2407.01863, 2024.
[3] Q. Wang, B. Yin, P. Zhang, et al. MindCube: Spatial Mental Modeling from Limited Views. arXiv:2506.21458, 2025.
[4] Team Wan, A. Wang, B. Ai, et al. Wan: Open and Advanced Large-Scale Video Generative Models. arXiv:2503.20314, 2025.