mlsanityData to 7 Oct 2026

Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought

arXiv 2505.23766 ↗First posted 29 May 2025cs.CVcited by 26

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

Recent advances in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks, yet they often struggle with vision-centric scenarios where precise visual focus is needed for accurate reasoning. In this paper, we introduce Argus to address these limitations with a new visual attention grounding mechanism. Our approach employs object-centric grounding as visual chain-of-thought signals, enabling more effective goal-conditioned visual attention during multimodal reasoning tasks. Evaluations on diverse benchmarks demonstrate that Argus excels in both multimodal reasoning tasks and referring object grounding tasks. Extensive analysis further validates various design choices of Argus, and reveals the effectiveness of explicit language-guided visual region-of-interest engagement in MLLMs, highlighting the importance of advancing multimodal intelligence from a visual-centric perspective. Project page: https://yunzeman.github.io/argus/

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 36 of its 115 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

36 of 115 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Improve Vision Language Model Chain-of-thought Reasoning21 Oct
  2. 2024Visual-O1: Understanding Ambiguous Instructions via Multi-modal Multi-turn Chain-of-thoughts Reasoning4 Oct
  3. 2023Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings3 May
  4. 2023Chain of Thought Prompt Tuning in Vision Language Models16 Apr
  5. 2023Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models8 Mar
  6. 2023Multimodal Chain-of-Thought Reasoning in Language Models2 Feb

Other references · 30

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2023Segment Anythingcited by 8,158
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  6. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  7. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  8. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  9. 2017Decoupled Weight Decay Regularizationcited by 1,722
  10. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  11. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,033
  12. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
18 more
  1. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 891
  2. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  3. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  4. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  5. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  6. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  7. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  8. 2023Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuningcited by 439
  9. 2024Mini-Gemini: Mining the Potential of Multi-modality Vision Language Modelscited by 361
  10. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 283
  11. 2023LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understandingcited by 272
  12. 2024MM1: Methods, Analysis & Insights from Multimodal LLM Pre-trainingcited by 230
  13. 2023G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Modelcited by 208
  14. 2023LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agentscited by 188
  15. 2023To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuningcited by 143
  16. 2024Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detectioncited by 122
  17. 2024VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Modelscited by 42
  18. 2024Contrastive Localized Language-Image Pre-Trainingcited by 33

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 18.

26 papers.

Sort:

By area:

  1. 2025Latent Visual Reasoningcited by 99
  2. 2025Explain Before You Answer: A Survey on Compositional Visual Reasoningcited by 26
  3. 2026Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planningcited by 20
  4. 2025Thinking in 360deg: Humanoid Visual Search in the Wildcited by 14
  5. 2025PhysToolBench: Benchmarking Physical Tool Understanding for MLLMscited by 9
  6. 2025LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sightcited by 8
  7. 2025See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Togglescited by 4
  8. 2026Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoningcited by 3
  9. 2026Planning with the Viewscited by 2
  10. 2025Draft and Refine with Visual Expertscited by 1
  11. 20254D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillationcited by 1
  12. 2026Vision Harnessing Agent for Open Ad-hoc Segmentationcited by 1
14 more
  1. 2026Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual Evidencecited by 1
  2. 2026Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinkingcited by 0
  3. 2026Getting to the Point: Pointing Improves LVLMs at Countingcited by 0
  4. 2026PortraitCraft: A Benchmark for Portrait Composition Understanding and Generationcited by 0
  5. 2026Real-Time Visual Attribution Streaming in Thinking Modelcited by 0
  6. 2026When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Modelscited by 0
  7. 2026GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoningcited by 0
  8. 2026Learning to See What You Need: Gaze Attention for Multimodal Large Language Modelscited by 0
  9. 2026Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoningcited by 0
  10. 2026From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Modelscited by 0
  11. 2026Learning to Zoom Efficiently with a Contrastive Curriculumcited by 0
  12. 2026Region-Level Policy Optimization for Fine-grained MLLM Perceptioncited by 0
  13. 2026MinCU: A Fine-Grained Benchmark for Grounded Minimal-Change Understanding in Image Pairscited by 0
  14. 2026Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidencecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
  2. 2025Argus Inspection: Do Multimodal Large Language Models Possess the Eye of Panoptes?
  3. 2025VGR: Visual Grounded Reasoning
  4. 2025Diagnosing Visual Reasoning: Challenges, Insights, and a Path Forward
  5. 2026Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration
  6. 2026Do MLLMs Really See It: Reinforcing Visual Attention in Multimodal LLMs
  7. 2025Mind with Eyes: from Language Reasoning to Multimodal Reasoning
  8. 2024Plug-and-Play Grounding of Reasoning in Multimodal Large Language Models