{"list":"other","total":55,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"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":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2305.05658","title":"TidyBot: Personalized Robot Assistance with Large Language Models","created":"2023-05-09","cited_by_count":221},{"id":"2502.07266","title":"When More is Less: Understanding Chain-of-Thought Length in LLMs","created":"2025-02-11","cited_by_count":183},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"2505.00127","title":"Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs","created":"2025-04-30","cited_by_count":117},{"id":"1801.01957","title":"From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots","created":"2018-01-06","cited_by_count":85},{"id":"2507.07966","title":"Scaling RL to Long Videos","created":"2025-07-10","cited_by_count":84},{"id":"2003.02501","title":"Detecting Attended Visual Targets in Video","created":"2020-03-05","cited_by_count":77},{"id":"2509.21100","title":"VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception","created":"2025-09-25","cited_by_count":65},{"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":"2604.05015","title":"Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding","created":"2026-04-06","cited_by_count":55},{"id":"2206.08219","title":"HaGRID - HAnd Gesture Recognition Image Dataset","created":"2022-06-16","cited_by_count":43},{"id":"1909.02144","title":"Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning","created":"2019-09-04","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":"2307.05158","title":"A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settings","created":"2023-07-11","cited_by_count":31},{"id":"2509.07447","title":"In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting","created":"2025-09-09","cited_by_count":22},{"id":"2602.13517","title":"Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens","created":"2026-02-13","cited_by_count":22},{"id":"2512.02231","title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","created":"2025-12-01","cited_by_count":20},{"id":"2510.16258","title":"Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset","created":"2025-10-17","cited_by_count":19},{"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":"2409.15316","title":"Towards Social AI: A Survey on Understanding Social Interactions","created":"2024-09-05","cited_by_count":16},{"id":"2403.12778","title":"ViTGaze: Gaze Following with Interaction Features in Vision Transformers","created":"2024-03-19","cited_by_count":15},{"id":"2406.03907","title":"Exploring the Zero-Shot Capabilities of Vision-Language Models for Improving Gaze Following","created":"2024-06-06","cited_by_count":14},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14},{"id":"2411.16173","title":"SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis","created":"2024-11-25","cited_by_count":13},{"id":"2603.16859","title":"SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models","created":"2026-03-17","cited_by_count":13},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12},{"id":"2504.02244","title":"SocialGesture: Delving into Multi-person Gesture Understanding","created":"2025-04-03","cited_by_count":11},{"id":"2505.23179","title":"DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes","created":"2025-05-29","cited_by_count":11},{"id":"2510.21356","title":"Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding","created":"2025-10-24","cited_by_count":11},{"id":"2412.17295","title":"Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding","created":"2024-12-23","cited_by_count":9},{"id":"2502.16671","title":"MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models","created":"2025-02-23","cited_by_count":9},{"id":"2504.10873","title":"Can Vision-Language Models Understand and Interpret Dynamic Gestures from Pedestrians? Pilot Datasets and Exploration Towards Instructive Nonverbal Commands for Cooperative Autonomous Vehicles","created":"2025-04-15","cited_by_count":9},{"id":"2511.06348","title":"GazeVLM: A Vision-Language Model for Multi-Task Gaze Understanding","created":"2025-11-09","cited_by_count":9},{"id":"2511.17952","title":"Multi-speaker Attention Alignment for Multimodal Social Interaction","created":"2025-11-22","cited_by_count":9},{"id":"2511.16221","title":"Can MLLMs Read the Room? A Multimodal Benchmark for Assessing Deception in Multi-Party Social Interactions","created":"2025-11-20","cited_by_count":6},{"id":"2604.00267","title":"Omni-MMSI: Toward Identity-attributed Social Interaction Understanding","created":"2026-03-31","cited_by_count":4},{"id":"2601.14569","title":"Social Caption: Evaluating Social Understanding in Multimodal Models","created":"2026-01-21","cited_by_count":2},{"id":"2510.21814","title":"Gestura: A LVLM-Powered System Bridging Motion and Semantics for Real-Time Free-Form Gesture Understanding","created":"2025-10-21","cited_by_count":1},{"id":"2512.01148","title":"SocialFusion: Addressing Social Degradation in Pre-trained Vision-Language Models","created":"2025-11-30","cited_by_count":1}],"next_cursor":null}