- Rating
- 4
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper proposes Decoupled Latent Visual Reasoning (DLVR) for multimodal table reasoning. DLVR organizes latent computation into progressive row, column, and subtable stages, while separating structural and content representations within each stage. The model is trained using a two-stage framework consisting of decoupled latent supervised fine-tuning followed by Latent Intervention GRPO with a Latent Contribution Reward. The authors also construct TableLVR-41K to provide stage-specific supervision. Experiments across seven benchmarks and two LVLM backbones show improvements over direct answering, explicit reasoning methods, and generic latent visual reasoning baselines, together with substantially reduced inference time and generation length.
Critical strengths
-
DLVR provides an effective and computationally efficient alternative to explicit multimodal reasoning. Across two LVLM backbones, the method achieves strong performance on a broad set of table reasoning benchmarks while requiring substantially fewer generated tokens and lower inference time than textual CoT and explicit image-based reasoning methods. This combination of reasoning performance and inference efficiency makes the approach particularly relevant for practical deployment.
-
The methodological design is well aligned with the structural characteristics of table reasoning. Rather than directly applying generic latent visual reasoning or GRPO, the paper introduces row, column, and subtable latent stages, structure-content decoupling, stage-specific latent supervision, and an intervention-based reward that encourages the generated latent states to contribute to answer prediction. The matched baselines and component ablations provide empirical support for these table-specific design choices.
Critical weaknesses
None
Questions for authors
-
Why is fusion reconstruction performed only on the average-pooled stage representation, rather than preserving a finer-grained correspondence across the latent states? Would token-level or position-wise reconstruction provide additional supervision for the relational structure encoded within each stage?
-
Could the authors clarify how is implemented for the visual and content targets in Eq. (3)? In particular, how is correspondence established between the resulting visual states and content states before computing ?
3 comments
Thanks for the detailed clarifications. My questions have been adequately addressed, and I will maintain my positive rating.
Response to Reviewer NjyK
Thank you for your kind follow-up and for confirming that your questions have been adequately addressed. We sincerely appreciate your continued positive assessment of our work.
We are particularly grateful for your recognition of the following aspects:
- Reasoning effectiveness and inference efficiency: DLVR achieves strong performance across diverse table reasoning benchmarks while substantially reducing generated tokens and inference time compared with explicit reasoning methods.
- Table-specific methodological design: Our row, column, and subtable latent stages, structure-content decoupling, stage-specific supervision, and intervention-based reward are tailored to the structural characteristics of table reasoning, with matched baselines and ablations supporting their effectiveness.
We are especially encouraged by your recognition of the practical efficiency and methodological contributions of DLVR, which are central motivations of this work.
Thank you again for your thoughtful feedback, constructive suggestions, and support.
Response to Reviewer NjyK
Thank you for reviewing our paper and for the insightful comments. Our point-to-point responses to your comments are given below. We have clarified the implementation of PoolK and the index-based correspondence between visual and content targets in Section 3.2.2. We have also added a position-wise reconstruction comparison to the ablation studies in Section 5 and Appendix C. All revisions to the manuscript are highlighted in blue for ease of reference. We hope these revisions address your questions, and we welcome any further suggestions.
R1: We thank the reviewer for this question. We use average-pooled fusion reconstruction to recover stage-level visual evidence while allowing complementary information to be distributed across latent states. This design has three motivations:
(1) Reduced reliance on strict positional correspondence. Visual and content targets are pooled independently, and matching indices do not necessarily correspond to the same cells or visual regions. Stage-level reconstruction reduces reliance on this approximate correspondence rather than imposing an additional position-wise matching constraint.
(2) Flexible information allocation across latent states. The K latent states represent sequential computation rather than K predefined visual regions. Average-pooled reconstruction allows these states to collectively represent the evidence within each stage, without requiring every fused state to reproduce a prescribed visual target.
(3) Complementarity with content supervision. The content loss already provides position-wise supervision for content states. The fusion loss instead constrains the combined structural and content representation at the stage level, complementing content alignment without imposing the same granularity on both objectives.
Empirical comparison. To further investigate this design choice, we conduct an additional experiment replacing average-pooled fusion reconstruction with position-wise reconstruction, while keeping other settings unchanged. As shown in Table 1, average-pooled reconstruction achieves a higher average score, with particularly notable improvements on InfoTabs and PubHealthTab. These results suggest that imposing position-wise reconstruction does not necessarily provide more effective supervision, supporting our choice of stage-level reconstruction to preserve flexibility in latent information allocation.
Table 1: Comparison of average-pooled and position-wise fusion reconstruction.
Thank you for pointing out this ambiguity. We implement PoolK using one-dimensional adaptive average pooling along the token dimension (i.e.,
torch.nn.functional.adaptive_avg_pool1d), producing K representations from each input sequence. For visual targets, we preserve the visual encoder’s output token order. For content targets, we remove padding and preserve the token order of the serialized cell content. The two sequences are pooled independently.The correspondence is therefore index-based rather than an explicit semantic alignment between cells and visual patches. Specifically, we compute $ S_{m,k} = V_{m,k}-P (T_{m,k} ) $ for $ k=1,...,K $, where the learnable projection P maps content representations into the visual feature space but does not explicitly establish token-level alignment. Accordingly, Sm serves as an approximate structural proxy during teacher forcing, rather than a guaranteed content-free structural representation.
Action taken: We have clarified the implementation of PoolK and the index-based correspondence between visual and content targets in Section 3.2.2, and added the position-wise fusion reconstruction comparison and an analysis of the flexibility provided by average-pooled reconstruction in Section 5 and Appendix C (Tables 2 and 9).