{"list":"other","total":78,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"id":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"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":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255},{"id":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"2501.06186","title":"LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs","created":"2025-01-10","cited_by_count":147},{"id":"2101.09624","title":"A Review of Speaker Diarization: Recent Advances with Deep Learning","created":"2021-01-24","cited_by_count":124},{"id":"2503.17352","title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","created":"2025-03-21","cited_by_count":124},{"id":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121},{"id":"2505.18079","title":"Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding","created":"2025-05-23","cited_by_count":98},{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91},{"id":"2504.13055","title":"NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation","created":"2025-04-17","cited_by_count":86},{"id":"2003.02501","title":"Detecting Attended Visual Targets in Video","created":"2020-03-05","cited_by_count":77},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63},{"id":"2504.09641","title":"TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning","created":"2025-04-13","cited_by_count":62},{"id":"2501.15111","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","created":"2025-01-25","cited_by_count":60},{"id":"2510.15870","title":"OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM","created":"2025-10-17","cited_by_count":59},{"id":"2412.15606","title":"Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage","created":"2024-12-20","cited_by_count":51},{"id":"2204.08997","title":"A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets","created":"2022-04-19","cited_by_count":45},{"id":"2501.16566","title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":44},{"id":"2206.08219","title":"HaGRID - HAnd Gesture Recognition Image Dataset","created":"2022-06-16","cited_by_count":43},{"id":"2312.10908","title":"CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update","created":"2023-12-18","cited_by_count":43},{"id":"2504.01886","title":"GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning","created":"2025-04-02","cited_by_count":41},{"id":"2303.04439","title":"A Light Weight Model for Active Speaker Detection","created":"2023-03-08","cited_by_count":40},{"id":"2412.09586","title":"Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders","created":"2024-12-12","cited_by_count":36},{"id":"2307.01630","title":"ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviour","created":"2023-07-04","cited_by_count":35},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33},{"id":"2111.06647","title":"Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations","created":"2021-11-12","cited_by_count":31},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28},{"id":"2307.09662","title":"Object-aware Gaze Target Detection","created":"2023-07-18","cited_by_count":27},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25},{"id":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23},{"id":"2005.02134","title":"IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition","created":"2020-04-20","cited_by_count":22},{"id":"2109.04919","title":"EmoWOZ: A Large-Scale Corpus and Labelling Scheme for Emotion Recognition in Task-Oriented Dialogue Systems","created":"2021-09-10","cited_by_count":20},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18},{"id":"2403.02090","title":"Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations","created":"2024-03-04","cited_by_count":18},{"id":"2410.01495","title":"OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition","created":"2024-10-02","cited_by_count":17},{"id":"2409.15316","title":"Towards Social AI: A Survey on Understanding Social Interactions","created":"2024-09-05","cited_by_count":16},{"id":"2501.16643","title":"An LLM Benchmark for Addressee Recognition in Multi-modal Multi-party Dialogue","created":"2025-01-28","cited_by_count":15},{"id":"2210.13404","title":"Contrastive Representation Learning for Gaze Estimation","created":"2022-10-24","cited_by_count":14},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14},{"id":"2410.21411","title":"SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization","created":"2024-10-28","cited_by_count":14},{"id":"2310.16301","title":"Is ChatGPT a Good Multi-Party Conversation Solver?","created":"2023-10-25","cited_by_count":13},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12},{"id":"2305.12831","title":"Target Active Speaker Detection with Audio-visual Cues","created":"2023-05-22","cited_by_count":11},{"id":"2504.02244","title":"SocialGesture: Delving into Multi-person Gesture Understanding","created":"2025-04-03","cited_by_count":11},{"id":"2205.05177","title":"ConfLab: A Data Collection Concept, Dataset, and Benchmark for Machine Analysis of Free-Standing Social Interactions in the Wild","created":"2022-05-10","cited_by_count":10},{"id":"2512.10359","title":"Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task","created":"2025-12-11","cited_by_count":10},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9},{"id":"2311.05669","title":"Multi-Modal Gaze Following in Conversational Scenarios","created":"2023-11-09","cited_by_count":6},{"id":"2404.17205","title":"Two in One Go: Single-stage Emotion Recognition with Decoupled Subject-context Transformer","created":"2024-04-26","cited_by_count":5},{"id":"2304.06977","title":"DeePoint: Visual Pointing Recognition and Direction Estimation","created":"2023-04-14","cited_by_count":3},{"id":"2502.06012","title":"Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings","created":"2025-02-09","cited_by_count":3},{"id":"2409.05659","title":"Audio-Visual Speaker Diarization: Current Databases, Approaches and Challenges","created":"2024-09-09","cited_by_count":1},{"id":"2507.21924","title":"MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning","created":"2025-07-29","cited_by_count":1}],"next_cursor":null}