- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies the problem of visual grounding. To this end, the authors propose to incorporate the localization into the thinking / reasoning process to help a better and more precise visual grounding. The authors identify Reasoning-to-Coordinate Collapse as an essential gap between semantic reasoning and coordinate formation, and this is the motivation for their method. The authors develop E2RPO (edge-evidence attribution) to jointly optimize spatial updates and action-relevant visual attribution. The authors report results on several benchmarks, including RefCOCO, segmentation, RealVLG for robotic manipulation, etc. The results on RefCOCO show their improvement over Qwen2.5-VL-7B and Qwen3-VL-8B.
Critical strengths
-
Visual grounding is an important task to study. As an essential capability of VLMs, the visual grounding capability can have lots of downstream applications such as robotics, autonomous driving and tool-based visual reasoning.
-
Results on different domains. In addition to the conventional RefCOCO benchmarks, the authors have also shown the results of their method on other different domains, including driving and robotics, which is good to reveal the potential applications and impacts of the research.
Critical weaknesses
-
Motivation of incorporating localization into the reasoning process is not very clear to me. While in driving scenarios such as Figure 15, I think it is important to incorporate localization into the reasoning process, I am not sure whether it is very effective in RefCOCO scenarios such as in Figure 4. In that example, the query is "the bus that is almost out of view", and the initial grounding bounding box incorrectly locates another bus; this is due to the incorrectness in understanding which target object the query actually refers to. If the model can understand the reference correctly, for example, it should be the bus on the left of the image instead, then it can definitely do the visual grounding quite correctly. Using the current paradigm as in Figure 4 can make the eventual prediction correct, but the process may not be the most efficient, as it involves getting the incorrect prediction first, delete it, and then add another prediction box.
-
Efficiency results. The important applications of visual grounding models is in the robotics and autonomous driving scenarios. In these scenarios, being real-time is very important. Therefore, it would be better if the authors can also show the efficiency results of their method, to make sure that the visual grounding algorithm they developed is efficient for real-time deployment on embodied systems.
Questions for authors
-
As mentioned in Weakness 1, would the proposed method / thinking trace actually be the most efficient way to fix those incorrect visual grounding samples?
-
What is the efficiency of the proposed method compared with Qwen3 / Qwen2.5 models?
2 comments
Response to Reviewer 6FFu (2/2)
W2 / Q2. Inference Efficiency
As suggested, we evaluate inference efficiency on RefCOCOg using Hugging Face Transformers with BF16 precision and FlashAttention-2 on NVIDIA A800 80GB GPUs, with a per-GPU batch size of 4 and a maximum generation length of 1,024 tokens. Under these settings, we report the average number of visual encodings and inference latency per sample for the original Qwen backbones, iterative baselines, and ThinkAxis.
| Method | Avg. Visual Encodings ↓ | Avg. Latency (s) ↓ |
|---|---|---|
| Qwen2.5-VL-7B | 1.0 | 1.90 |
| Qwen3-VL-8B | 1.0 | 2.47 |
| IVT | 3.2 | 8.90 |
| Multi-turn | 2.4 | 6.07 |
| ThinkAxis-7B (Ours) | 1.0 | 3.28 |
| ThinkAxis-8B (Ours) | 1.0 | 3.92 |
Compared with the original Qwen2.5-VL-7B and Qwen3-VL-8B backbones, ThinkAxis incurs additional inference latency (1.90s → 3.28s and 2.47s → 3.92s, respectively) due to explicit localization reasoning, while achieving substantial gains in localization precision, including an avg. +6.5 point improvement in [email protected] over Qwen2.5-VL-7B. We have included the inference-efficiency comparison in Sec. 4.3 (Table 8) of the revised manuscript.
Importantly, ThinkAxis avoids repeated visual encoding across localization steps. Compared with the evaluated IVT-style and multi-turn baselines, ThinkAxis-7B reduces inference latency by 63.1% and 46.0%, respectively, while achieving higher localization accuracy. Furthermore, revised Appendix Table 13 (original Table 11) reports only 2.2 average localization steps, compared with 3.4 for raw offsets and 4.2 for absolute-coordinate regeneration, demonstrating the efficiency of structured grounding actions.
Regarding practical applications, current VLMs still face challenges in meeting the real-time requirements of autonomous driving and robotics. We see greater near-term potential in high-precision offline data annotation for both domains, particularly in complex driving scenes with densely distributed objects and robotic manipulation scenarios requiring precise object boundaries, where direct coordinate prediction remains challenging.
Summary. Our additional analyses clarify that ThinkAxis does not require an incorrect initial prediction or a fixed correction process, but adaptively determines when and how localization should be refined. The efficiency experiments quantify its computational overhead over the original Qwen backbones while demonstrating the benefits of avoiding repeated visual encoding compared with multi-turn approaches. Together with the driving experiments, these results further support the practical value of ThinkAxis for high-precision offline annotation.
Response to Reviewer 6FFu (1/2)
Thank you for your constructive comments. We have thoughtfully addressed all of your suggestions and concerns in our revised manuscript.
We clarify that ThinkAxis does not require an incorrect initial prediction followed by correction. Figure 4 is intended to illustrate the range of executable grounding actions, rather than a mandatory error-then-correction process. Instead, ThinkAxis adaptively determines whether and how to refine the current localization. As shown in the table below, 94.1% of predictions with an initial IoU ≥ 0.95 terminate directly without additional corrections, while more challenging cases receive progressively more refinement steps.
Additional visualizations further illustrate this adaptive behavior. Figure 8 of the revised manuscript shows precise boundary refinement after correct target identification (IoU: 0.646 → 0.992), while Fig. 12 demonstrates semantic reassessment and target replacement (IoU: 0.039 → 0.987). Table 7 further shows that correction magnitudes decrease from 11.44% to 1.54% as localization accuracy improves, consistent with progressively finer adjustments. We have added the adaptive stopping analysis and precise localization example to Sec. 4.3 (Table 9 and Fig. 8) of the revised manuscript.
Regarding effectiveness on RefCOCO, the advantage of ThinkAxis is particularly evident in more precise boundary localization. Conventional evaluations primarily focus on [email protected], which does not fully capture the precision of predicted bounding boxes. ThinkAxis achieves an average +6.5 point improvement in [email protected] (Table 1), demonstrating the value of explicit localization reasoning for precise coordinate formation beyond coarse target identification.