The paper introduces Numerical Visual Chain-of-Thought (NV‑CoT), a framework that expands multimodal large language models (MLLMs) to reason over images using continuous numerical coordinates instead of discrete tokens or fixed patches. NV‑CoT allows MLLMs to generate bounding‑box coordinates directly as actions with minimal architectural changes, supporting both supervised fine‑tuning and reinforcement learning via a Gaussian or Laplace policy. Experiments on three benchmarks show that NV‑CoT improves localization precision, answer accuracy, and training convergence compared to 11 visual reasoning baselines.
arXiv:2608.22429v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) capable of thinking with images often rely on external tools for fine-grained perception. However, this relian...
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
arXiv:2608. 12220v1 Announce Type: cross Abstract: Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning.
Metric-Bench introduces a new benchmark for Vision‑Language Models (VLMs) that focuses on metric‑spatial reasoning in indoor scenes by using in‑image reference objects with known dimensions. The accompanying MetricReasoner fine‑tuning recipe employs structured prompts and numerical rewards to implicitly learn 2D‑to‑3D mapping without camera intrinsics. Experiments show that this approach improves spatial metric understanding by 43.1 % over existing models and boosts downstream embodied tasks, while also delivering gains on general VLM benchmarks.
Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures. Traditional methods typically encode input images into static feature representations and perform reasoning primarily within the linguistic domain, often overlooking the rich perceptual cues and explicit spatial geometry inherent in images.
arXiv:2606. 00616v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos.
The paper introduces PIVOT, a dual-level learning framework designed to improve visually-grounded multimodal reasoning in large vision-language models. PIVOT employs a self‑calibrated experience replay mechanism to selectively reuse valuable visual reasoning trajectories, and a vision‑guided advantage allocation scheme that assigns extra rewards to tokens with strong visual support. Experiments on multiple benchmarks show that PIVOT enhances the multimodal reasoning performance of these models.
arXiv:2608. 02833v1 Announce Type: cross Abstract: Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains.
Existing Vision-Language Models (VLMs) exhibits a critical bottleneck in robust spatial reasoning. Recent reinforcement learning (RL) methods aim to close this gap with verifiable outcomes, yet they suffer from poor credit assignment across intermediate reasoning steps.
arXiv:2606. 17539v1 Announce Type: cross Abstract: Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging.
arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.
arXiv:2508. 07683v2 Announce Type: replace-cross Abstract: Video Temporal Grounding (VTG) aims to localize specific video segments corresponding to natural language queries.