{"total":53,"rows":[{"id":"2505.14362","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","created":"2025-05-20","cited_by_count":410,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2412.18547","title":"Token-Budget-Aware LLM Reasoning","created":"2024-12-24","cited_by_count":247,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2505.20272","title":"Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning","created":"2025-05-26","cited_by_count":49,"area":"lr"},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"area":null},{"id":"2411.13504","title":"Disentangling Memory and Reasoning Ability in Large Language Models","created":"2024-11-20","cited_by_count":44,"area":"lr"},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2505.18962","title":"System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts","created":"2025-05-25","cited_by_count":27,"area":"lr"},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26,"area":"mllm"},{"id":"2507.15028","title":"Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding","created":"2025-07-20","cited_by_count":24,"area":"lr"},{"id":"2501.00192","title":"MLLM-as-a-Judge for Image Safety without Human Labeling","created":"2024-12-31","cited_by_count":23,"area":null},{"id":"2503.18071","title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","created":"2025-03-23","cited_by_count":22,"area":"lr"},{"id":"2505.16315","title":"Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning","created":"2025-05-22","cited_by_count":21,"area":"lr"},{"id":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19,"area":"lr"},{"id":"2409.15657","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","created":"2024-09-24","cited_by_count":16,"area":"mllm"},{"id":"2503.18135","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","created":"2025-03-23","cited_by_count":16,"area":"lr"},{"id":"2507.05920","title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","created":"2025-07-08","cited_by_count":14,"area":"lr"},{"id":"2507.22050","title":"DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router","created":"2025-07-29","cited_by_count":13,"area":"lr"},{"id":"2505.14009","title":"Activation-Guided Consensus Merging for Large Language Models","created":"2025-05-20","cited_by_count":12,"area":"lr"},{"id":"2409.14083","title":"SURf: Teaching Large Vision-Language Models to Selectively Utilize Retrieved Information","created":"2024-09-21","cited_by_count":11,"area":"mllm"},{"id":"2505.15249","title":"Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation","created":"2025-05-21","cited_by_count":10,"area":"mllm"},{"id":"2507.03704","title":"Controlling Thinking Speed in Reasoning Models","created":"2025-07-04","cited_by_count":10,"area":"lr"},{"id":"2509.20912","title":"DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning","created":"2025-09-25","cited_by_count":10,"area":"lr"},{"id":"2512.14044","title":"OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving","created":"2025-12-16","cited_by_count":9,"area":"lr"},{"id":"2602.11499","title":"What if Agents Could Imagine? Reinforcing Open-Vocabulary HOI Comprehension through Generation","created":"2026-02-12","cited_by_count":8,"area":"lr"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2602.08346","title":"What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning","created":"2026-02-09","cited_by_count":7,"area":"lr"},{"id":"2603.01083","title":"Can Vision Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective","created":"2026-03-01","cited_by_count":6,"area":"mllm"},{"id":"2509.11796","title":"FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning","created":"2025-09-15","cited_by_count":5,"area":"lr"},{"id":"2605.15542","title":"DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding","created":"2026-05-15","cited_by_count":5,"area":"mllm"},{"id":"2512.02715","title":"GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding","created":"2025-12-02","cited_by_count":4,"area":"mllm"},{"id":"2603.29602","title":"IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2509.17743","title":"VideoPro: Adaptive Program Reasoning for Long Video Understanding","created":"2025-09-22","cited_by_count":3,"area":"lr"},{"id":"2602.23615","title":"HART: High-Resolution Annotation-Free Reasoning Technique through a Closed-loop Framework","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2508.00429","title":"Node-as-Agent: Graph Agentic Network","created":"2025-08-01","cited_by_count":2,"area":"rag"},{"id":"2509.04687","title":"Guideline-Consistent Segmentation via Multi-Agent Refinement","created":"2025-09-04","cited_by_count":2,"area":"agents"},{"id":"2512.22009","title":"iSHIFT: Lightweight Slow-Fast GUI Agent with Adaptive Perception","created":"2025-12-26","cited_by_count":2,"area":"mllm"},{"id":"2602.21497","title":"See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"},{"id":"2603.27494","title":"Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs","created":"2026-03-29","cited_by_count":1,"area":"lr"},{"id":"2610.09683","title":"System Switch: When Should a Fast Decision Model Stop and Think?","created":"2026-10-07","cited_by_count":1,"area":"lr"},{"id":"2503.14948","title":"ChatStitch: Visualizing Through Structures via Surround-View Unsupervised Deep Image Stitching with Collaborative LLM-Agents","created":"2025-03-19","cited_by_count":0,"area":"agents"},{"id":"2507.07685","title":"Rationale-Enhanced Decoding for Multi-modal Chain-of-Thought","created":"2025-07-10","cited_by_count":0,"area":"lr"},{"id":"2601.09111","title":"Towards Open Environments and Instructions: General Vision-Language Navigation via Fast-Slow Interactive Reasoning","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.00165","title":"ConFoThinking: Consolidated Focused Attention Driven Thinking for Visual Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2604.20860","title":"RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm","created":"2026-03-02","cited_by_count":0,"area":"rag"},{"id":"2608.05631","title":"ChronoVision: Temporal Reasoning via Latent State Reconstruction","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"id":"2609.02002","title":"InsightSeg: Reusing Correction Insights for Guideline-Consistent Segmentation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.38383","title":"Learning to Plan from Random Exploration","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}