{"list":"other","total":64,"rows":[{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2406.12793","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","created":"2024-06-18","cited_by_count":1121},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2411.16594","title":"From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge","created":"2024-11-25","cited_by_count":494},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"2402.04788","title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark","created":"2024-02-07","cited_by_count":372},{"id":"2310.17631","title":"JudgeLM: Fine-tuned Large Language Models are Scalable Judges","created":"2023-10-26","cited_by_count":367},{"id":"2408.16500","title":"CogVLM2: Visual Language Models for Image and Video Understanding","created":"2024-08-29","cited_by_count":217},{"id":"2406.12624","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","created":"2024-06-18","cited_by_count":205},{"id":"2403.15412","title":"Towards Measuring and Modeling \"Culture\" in LLMs: A Survey","created":"2024-03-05","cited_by_count":167},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2402.13231","title":"Investigating Cultural Alignment of Large Language Models","created":"2024-02-20","cited_by_count":143},{"id":"2410.02712","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","created":"2024-10-03","cited_by_count":134},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127},{"id":"2504.16072","title":"Describe Anything: Detailed Localized Image and Video Captioning","created":"2025-04-22","cited_by_count":84},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83},{"id":"2312.02439","title":"Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation","created":"2023-12-05","cited_by_count":56},{"id":"2405.04655","title":"Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsense","created":"2024-05-07","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":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46},{"id":"2406.06004","title":"FLEUR: An Explainable Reference-Free Evaluation Metric for Image Captioning Using a Large Multimodal Model","created":"2024-06-10","cited_by_count":45},{"id":"2503.12329","title":"CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era","created":"2025-03-16","cited_by_count":41},{"id":"2503.17489","title":"Judge Anything: MLLM as a Judge Across Any Modality","created":"2025-03-21","cited_by_count":34},{"id":"2412.08614","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","created":"2024-12-11","cited_by_count":31},{"id":"2412.19326","title":"Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment","created":"2024-12-26","cited_by_count":29},{"id":"2502.13146","title":"Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization","created":"2025-02-18","cited_by_count":29},{"id":"2402.10884","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","created":"2024-02-16","cited_by_count":26},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26},{"id":"2502.08045","title":"Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs","created":"2025-02-12","cited_by_count":26},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24},{"id":"2405.01474","title":"Understanding Figurative Meaning through Explainable Visual Entailment","created":"2024-05-02","cited_by_count":19},{"id":"2406.10522","title":"Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning","created":"2024-06-15","cited_by_count":19},{"id":"2502.12501","title":"Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge","created":"2025-02-18","cited_by_count":19},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16},{"id":"2508.06125","title":"SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning","created":"2025-08-08","cited_by_count":16},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","cited_by_count":15},{"id":"2407.17152","title":"XMeCap: Meme Caption Generation with Sub-Image Adaptability","created":"2024-07-24","cited_by_count":14},{"id":"2401.17910","title":"ControlCap: Controllable Region-level Captioning","created":"2024-01-31","cited_by_count":13},{"id":"2506.18369","title":"RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models","created":"2025-06-23","cited_by_count":13},{"id":"2509.19274","title":"DRISHTIKON: A Multimodal Multilingual Benchmark for Testing Language Models' Understanding on Indian Culture","created":"2025-09-23","cited_by_count":13},{"id":"2303.06338","title":"Learning Combinatorial Prompts for Universal Controllable Image Captioning","created":"2023-03-11","cited_by_count":12},{"id":"2502.20356","title":"Bridging the Creativity Understanding Gap: Small-Scale Human Alignment Enables Expert-Level Humor Ranking in LLMs","created":"2025-02-27","cited_by_count":12},{"id":"2307.11636","title":"OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?","created":"2023-07-21","cited_by_count":9},{"id":"2407.20454","title":"CoMMIT: Coordinated Multimodal Instruction Tuning","created":"2024-07-29","cited_by_count":8},{"id":"2409.09318","title":"ODE: Open-Set Evaluation of Hallucinations in Multimodal Large Language Models","created":"2024-09-14","cited_by_count":8},{"id":"2412.05243","title":"CompCap: Improving Multimodal Large Language Models with Composite Captions","created":"2024-12-06","cited_by_count":8},{"id":"2406.13564","title":"HumorDB: Can AI understand graphical humor?","created":"2024-06-19","cited_by_count":6},{"id":"2502.18331","title":"BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle","created":"2025-02-22","cited_by_count":6},{"id":"2507.01409","title":"CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning","created":"2025-07-02","cited_by_count":5},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","cited_by_count":5},{"id":"2509.12248","title":"Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comics","created":"2025-09-12","cited_by_count":5},{"id":"2307.16399","title":"Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences","created":"2023-07-31","cited_by_count":4},{"id":"2511.21732","title":"HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation","created":"2025-11-21","cited_by_count":4},{"id":"2407.11449","title":"Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights","created":"2024-07-16","cited_by_count":3},{"id":"2511.20604","title":"On Evaluating LLM Alignment by Evaluating LLMs as Judges","created":"2025-11-25","cited_by_count":3},{"id":"2602.06423","title":"On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption Generation","created":"2026-02-06","cited_by_count":3}],"next_cursor":null}