ReVEAL is a new framework for reasoning video object segmentation that decouples multi‑modal large language model (MLLM) reasoning from downstream segmentation. It introduces Visual Evidence Tokens (VETs) to link visual regions with target, background, or distractor roles, and uses a Dynamic Attention Layer Router to aggregate role‑specific grounding evidence. Trained on the ReVEAL‑47K dataset with a Contrastive Attention Grounding Loss, ReVEAL guides a frozen SAM2 model to predict target masks and achieves state‑of‑the‑art performance on five benchmarks without requiring costly cross‑model alignment.
arXiv:2601. 07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches.
VideoLVR introduces a method for multimodal large language models to maintain visual grounding during chain-of-thought reasoning by constructing latent visual evidence from local video regions at relevant moments. It uses a visual token prediction objective that unifies visual evidence reconstruction and text generation, allowing models to interleave text tokens with latent visual states. The approach is further extended with reinforcement learning, treating visual tokens as actions and optimizing policies with final-answer rewards, thereby improving video understanding without expanding the multimodal context.
The paper introduces the Very Big Video Reasoning (VBVR) Dataset, a large-scale collection of over one million video clips organized into 200 curated reasoning tasks. It also presents VBVR-Bench, a benchmark framework that uses rule-based, human-aligned scorers for reproducible evaluation of video reasoning models. The authors conduct a large-scale scaling study, noting early signs of emergent generalization to unseen reasoning tasks, and make all resources publicly available.
arXiv:2606. 00616v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos.
arXiv:2608. 16316v1 Announce Type: cross Abstract: Large Multimodal Models (LMMs) for video reasoning have long been hindered by the high computational cost of processing vast amounts of visual information.
arXiv:2608. 15869v1 Announce Type: cross Abstract: Multimodal large language models increasingly use visual chain-of-thought (Visual CoT) to reason about spatial, temporal, and embodied environments.
arXiv:2607. 11862v1 Announce Type: cross Abstract: Current Video Large Language Models (Video LLMs) excel in question answering (QA) but largely operate as black boxes, providing textual answers without verifiable visual grounding.
ReGuLaR introduces a relation‑grounded latent reasoning framework for large vision‑language models, explicitly anchoring latent states to key objects and their inter‑object relations. It employs a training‑time ReGFormer to focus reasoning on question‑relevant visual evidence, while inference proceeds without the ReGFormer. The authors also create the RGROUNDING‑351K dataset and demonstrate that ReGuLaR outperforms existing methods across diverse benchmarks, achieving state‑of‑the‑art results.
arXiv:2607. 08763v1 Announce Type: cross Abstract: Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences.
arXiv:2608.20814v1 Announce Type: new Abstract: Though Multimodal Large Language Models (MLLMs) have shown impressive potential in video understanding, long video understanding (LVU) remains challeng...
arXiv:2611.07408v1 Announce Type: cross Abstract: Panoptic Scene Graph generation (PSG) requires holistic yet fine-grained reasoning over complex relations among objects. However, current Multimodal...
The paper introduces LIRSeg, a method that replaces explicit Chain-of-Thought reasoning in multimodal large language models with a compact set of learnable latent tokens for reasoning segmentation. LIRSeg is trained in two stages—spatial alignment and GRPO—while employing extreme-advantage sampling, decoupled exploration-stability updates, and latent diversity amplification to enhance token informativeness. Experiments show that LIRSeg improves segmentation accuracy and reasoning efficiency, achieving significant gIoU gains over the VisionReasoner baseline and reducing reasoning tokens by about 16×.