{"list":"other","total":78,"rows":[{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550},{"id":"2312.14135","title":"V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs","created":"2023-12-21","cited_by_count":482},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2412.18319","title":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search","created":"2024-12-24","cited_by_count":175},{"id":"2408.15556","title":"Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models","created":"2024-08-28","cited_by_count":161},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"2410.02712","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","created":"2024-10-03","cited_by_count":134},{"id":"2312.10665","title":"Silkie: Preference Distillation for Large Visual Language Models","created":"2023-12-17","cited_by_count":130},{"id":"2503.05379","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","created":"2025-03-07","cited_by_count":100},{"id":"2311.07362","title":"Volcano: Mitigating Multimodal Hallucination through Self-Feedback Guided Revision","created":"2023-11-13","cited_by_count":98},{"id":"2408.02032","title":"Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models","created":"2024-08-04","cited_by_count":94},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91},{"id":"2411.17451","title":"VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models","created":"2024-11-26","cited_by_count":86},{"id":"2408.08632","title":"A Survey on Benchmarks of Multimodal Large Language Models","created":"2024-08-16","cited_by_count":82},{"id":"2406.11303","title":"VideoVista: A Versatile Benchmark for Video Understanding and Reasoning","created":"2024-06-17","cited_by_count":72},{"id":"2410.03577","title":"Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models","created":"2024-10-04","cited_by_count":72},{"id":"2312.11420","title":"Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning","created":"2023-12-18","cited_by_count":64},{"id":"2311.06612","title":"PerceptionGPT: Effectively Fusing Visual Perception into LLM","created":"2023-11-11","cited_by_count":59},{"id":"2410.09421","title":"VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment","created":"2024-10-12","cited_by_count":58},{"id":"2408.00765","title":"MM-Vet v2: A Challenging Benchmark to Evaluate Large Multimodal Models for Integrated Capabilities","created":"2024-08-01","cited_by_count":57},{"id":"2412.10471","title":"VCA: Video Curious Agent for Long Video Understanding","created":"2024-12-12","cited_by_count":56},{"id":"2410.09575","title":"Reconstructive Visual Instruction Tuning","created":"2024-10-12","cited_by_count":55},{"id":"2312.12423","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","created":"2023-12-19","cited_by_count":53},{"id":"2311.13601","title":"Visual In-Context Prompting","created":"2023-11-22","cited_by_count":52},{"id":"2408.13890","title":"Making Large Language Models Better Planners with Reasoning-Decision Alignment","created":"2024-08-25","cited_by_count":52},{"id":"2404.07449","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","created":"2024-04-11","cited_by_count":49},{"id":"2408.10433","title":"CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs","created":"2024-08-19","cited_by_count":49},{"id":"2412.08635","title":"Multimodal Latent Language Modeling with Next-Token Diffusion","created":"2024-12-11","cited_by_count":48},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45},{"id":"2312.09251","title":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation","created":"2023-12-14","cited_by_count":41},{"id":"2403.11085","title":"m&m's: A Benchmark to Evaluate Tool-Use for multi-step multi-modal Tasks","created":"2024-03-17","cited_by_count":38},{"id":"2412.18108","title":"Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach","created":"2024-12-24","cited_by_count":35},{"id":"2406.16620","title":"OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer","created":"2024-06-24","cited_by_count":34},{"id":"2402.15527","title":"PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain","created":"2024-02-21","cited_by_count":29},{"id":"2403.09333","title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","created":"2024-03-14","cited_by_count":29},{"id":"2406.00645","title":"FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning","created":"2024-06-02","cited_by_count":26},{"id":"2408.02034","title":"Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid","created":"2024-08-04","cited_by_count":26},{"id":"2402.07384","title":"Exploring Perceptual Limitation of Multimodal Large Language Models","created":"2024-02-12","cited_by_count":25},{"id":"2407.06189","title":"Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision","created":"2024-07-08","cited_by_count":25},{"id":"2403.09394","title":"GiT: Towards Generalist Vision Transformer through Universal Language Interface","created":"2024-03-14","cited_by_count":24},{"id":"2408.17150","title":"Look, Compare, Decide: Alleviating Hallucination in Large Vision-Language Models via Multi-View Multi-Path Reasoning","created":"2024-08-30","cited_by_count":23},{"id":"2401.07529","title":"MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception","created":"2024-01-15","cited_by_count":21},{"id":"2412.07012","title":"ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models","created":"2024-12-09","cited_by_count":21},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20},{"id":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","cited_by_count":19},{"id":"2408.11813","title":"SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs","created":"2024-08-21","cited_by_count":19},{"id":"2404.01911","title":"VLRM: Vision-Language Models act as Reward Models for Image Captioning","created":"2024-04-02","cited_by_count":18},{"id":"2401.17981","title":"From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information","created":"2024-01-31","cited_by_count":16},{"id":"2409.17523","title":"EAGLE: Egocentric AGgregated Language-video Engine","created":"2024-09-26","cited_by_count":16},{"id":"2402.14767","title":"DualFocus: Integrating Macro and Micro Perspectives in Multi-modal Large Language Models","created":"2024-02-22","cited_by_count":15},{"id":"2410.04734","title":"TLDR: Token-Level Detective Reward Model for Large Vision Language Models","created":"2024-10-07","cited_by_count":15},{"id":"2310.07932","title":"What Matters to You? Towards Visual Representation Alignment for Robot Learning","created":"2023-10-11","cited_by_count":14},{"id":"2401.03105","title":"Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models","created":"2024-01-06","cited_by_count":12},{"id":"2407.11422","title":"Reflective Instruction Tuning: Mitigating Hallucinations in Large Vision-Language Models","created":"2024-07-16","cited_by_count":12},{"id":"2408.05019","title":"Instruction Tuning-free Visual Token Complement for Multimodal LLMs","created":"2024-08-09","cited_by_count":12},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11},{"id":"2409.08202","title":"What Makes a Maze Look Like a Maze?","created":"2024-09-12","cited_by_count":11},{"id":"2410.04659","title":"ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models","created":"2024-10-07","cited_by_count":11},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11},{"id":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10},{"id":"2408.03940","title":"How Well Can Vision Language Models See Image Details?","created":"2024-08-07","cited_by_count":10},{"id":"2402.01345","title":"Skip \\n: A Simple Method to Reduce Hallucination in Large Vision-Language Models","created":"2024-02-02","cited_by_count":9},{"id":"2410.08209","title":"Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision","created":"2024-10-10","cited_by_count":9},{"id":"2501.07214","title":"TimeLogic: A Temporal Logic Benchmark for Video QA","created":"2025-01-13","cited_by_count":9},{"id":"2412.04903","title":"EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation","created":"2024-12-06","cited_by_count":8},{"id":"2406.09390","title":"LLAVIDAL: A Large LAnguage VIsion Model for Daily Activities of Living","created":"2024-06-13","cited_by_count":7},{"id":"2409.19339","title":"Visual Question Decomposition on Multimodal Large Language Models","created":"2024-09-28","cited_by_count":7},{"id":"2412.18072","title":"MMFactory: A Universal Solution Search Engine for Vision-Language Tasks","created":"2024-12-24","cited_by_count":7},{"id":"2407.11522","title":"FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models","created":"2024-07-16","cited_by_count":6},{"id":"2412.04531","title":"MageBench: Bridging Large Multimodal Models to Agents","created":"2024-12-05","cited_by_count":6},{"id":"2312.07532","title":"Interfacing Foundation Models' Embeddings","created":"2023-12-12","cited_by_count":4},{"id":"2404.18033","title":"Exposing Text-Image Inconsistency Using Diffusion Models","created":"2024-04-28","cited_by_count":4},{"id":"2406.18227","title":"GUIDE: A Guideline-Guided Dataset for Instructional Video Comprehension","created":"2024-06-26","cited_by_count":4},{"id":"2502.00382","title":"Masked Generative Nested Transformers with Decode Time Scaling","created":"2025-02-01","cited_by_count":4}],"next_cursor":null}