{"list":"other","total":65,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604},{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241},{"id":"2406.09411","title":"MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding","created":"2024-06-13","cited_by_count":188},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138},{"id":"2506.17218","title":"Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens","created":"2025-06-20","cited_by_count":124},{"id":"2509.24704","title":"MemGen: Weaving Generative Latent Memory for Self-Evolving Agents","created":"2025-09-29","cited_by_count":109},{"id":"2509.24251","title":"Latent Visual Reasoning","created":"2025-09-29","cited_by_count":104},{"id":"2511.20639","title":"Latent Collaboration in Multi-Agent Systems","created":"2025-11-25","cited_by_count":73},{"id":"2511.19418","title":"Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens","created":"2025-11-24","cited_by_count":71},{"id":"2503.13964","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","created":"2025-03-18","cited_by_count":67},{"id":"2502.13059","title":"SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models","created":"2025-02-18","cited_by_count":66},{"id":"2510.18632","title":"Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views","created":"2025-10-21","cited_by_count":65},{"id":"2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","created":"2025-10-03","cited_by_count":61},{"id":"2512.03043","title":"OneThinker: All-in-one Reasoning Model for Image and Video","created":"2025-12-02","cited_by_count":56},{"id":"2408.12574","title":"MuMA-ToM: Multi-modal Multi-Agent Theory of Mind","created":"2024-08-22","cited_by_count":51},{"id":"2412.12359","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","created":"2024-12-16","cited_by_count":51},{"id":"2510.24514","title":"Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs","created":"2025-10-28","cited_by_count":43},{"id":"2412.12094","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","created":"2024-12-16","cited_by_count":41},{"id":"2510.14545","title":"Agentic Entropy-Balanced Policy Optimization","created":"2025-10-16","cited_by_count":40},{"id":"1909.07405","title":"BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle","created":"2019-09-16","cited_by_count":39},{"id":"2506.14766","title":"ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM","created":"2025-06-17","cited_by_count":37},{"id":"2511.11007","title":"VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models","created":"2025-11-14","cited_by_count":37},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35},{"id":"2502.17651","title":"METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling","created":"2025-02-24","cited_by_count":34},{"id":"2508.12587","title":"Multimodal Chain of Continuous Thought for Latent-Space Reasoning in Vision-Language Models","created":"2025-08-18","cited_by_count":32},{"id":"2508.03404","title":"Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling","created":"2025-08-05","cited_by_count":30},{"id":"2510.20733","title":"Thought Communication in Multiagent Collaboration","created":"2025-10-23","cited_by_count":30},{"id":"2510.23925","title":"Latent Chain-of-Thought for Visual Reasoning","created":"2025-10-27","cited_by_count":29},{"id":"2512.12623","title":"Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space","created":"2025-12-14","cited_by_count":28},{"id":"2505.21298","title":"Large Language Models Miss the Multi-Agent Mark","created":"2025-05-27","cited_by_count":26},{"id":"2407.00092","title":"Visual Reasoning and Multi-Agent Approach in Multimodal Large Language Models (MLLMs): Solving TSP and mTSP Combinatorial Challenges","created":"2024-06-26","cited_by_count":21},{"id":"2512.16918","title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","created":"2025-12-18","cited_by_count":21},{"id":"2508.01832","title":"MLP Memory: A Retriever-Pretrained Memory for Large Language Models","created":"2025-08-03","cited_by_count":20},{"id":"2510.09038","title":"Auto-scaling Continuous Memory for GUI Agent","created":"2025-10-10","cited_by_count":20},{"id":"2508.09874","title":"Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models","created":"2025-08-13","cited_by_count":16},{"id":"2403.14783","title":"Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answering","created":"2024-03-21","cited_by_count":15},{"id":"2505.17670","title":"Towards General Continuous Memory for Vision-Language Models","created":"2025-05-23","cited_by_count":15},{"id":"2601.10129","title":"LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning","created":"2026-01-15","cited_by_count":15},{"id":"2509.21789","title":"Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow","created":"2025-09-26","cited_by_count":13},{"id":"2501.02790","title":"Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model","created":"2025-01-06","cited_by_count":12},{"id":"2509.25185","title":"PixelCraft: A Multi-Agent System for High-Fidelity Visual Reasoning on Structured Images","created":"2025-09-29","cited_by_count":12},{"id":"2311.17331","title":"Towards Top-Down Reasoning: An Explainable Multi-Agent Approach for Visual Question Answering","created":"2023-11-29","cited_by_count":11},{"id":"2109.09531","title":"Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge","created":"2021-09-20","cited_by_count":10},{"id":"2408.05478","title":"Multi-Agent Planning Using Visual Language Models","created":"2024-08-10","cited_by_count":7},{"id":"2506.15889","title":"Entropy-Driven Pre-Tokenization for Byte-Pair Encoding","created":"2025-06-18","cited_by_count":6},{"id":"2511.19417","title":"Be My Eyes: Extending Large Language Models to New Modalities Through Multi-Agent Collaboration","created":"2025-11-24","cited_by_count":5},{"id":"2511.21042","title":"LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules","created":"2025-11-26","cited_by_count":4},{"id":"2310.02650","title":"Active Visual Localization for Multi-Agent Collaboration: A Data-Driven Approach","created":"2023-10-04","cited_by_count":3},{"id":"2508.06382","title":"Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning","created":"2025-08-08","cited_by_count":3},{"id":"2406.07812","title":"To be Continuous, or to be Discrete, Those are Bits of Questions","created":"2024-06-12","cited_by_count":2},{"id":"2508.09230","title":"Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems","created":"2025-08-12","cited_by_count":1}],"next_cursor":null}