{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2304.06712","title":"What does CLIP know about a red circle? Visual prompt engineering for VLMs","created":"2023-04-13","cited_by_count":218},{"id":"2502.17422","title":"MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs","created":"2025-02-24","cited_by_count":176},{"id":"1904.11574","title":"TVQA+: Spatio-Temporal Grounding for Video Question Answering","created":"2019-04-25","cited_by_count":154},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2303.11040","title":"Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving","created":"2023-03-20","cited_by_count":114},{"id":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83},{"id":"2412.03563","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","created":"2024-12-04","cited_by_count":82},{"id":"2508.10333","title":"ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver","created":"2025-08-14","cited_by_count":81},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75},{"id":"2406.12718","title":"Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention","created":"2024-06-18","cited_by_count":74},{"id":"2410.15926","title":"Mitigating Object Hallucination via Concentric Causal Attention","created":"2024-10-21","cited_by_count":49},{"id":"2505.16652","title":"Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding","created":"2025-05-22","cited_by_count":43},{"id":"2505.18657","title":"MLLMs are Deeply Affected by Modality Bias","created":"2025-05-24","cited_by_count":40},{"id":"2403.18346","title":"Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective","created":"2024-03-27","cited_by_count":39},{"id":"2412.18108","title":"Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach","created":"2024-12-24","cited_by_count":35},{"id":"2407.21534","title":"ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models","created":"2024-07-31","cited_by_count":33},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28},{"id":"2401.09454","title":"Voila-A: Aligning Vision-Language Models with User's Gaze Attention","created":"2023-12-22","cited_by_count":28},{"id":"2502.15109","title":"Social Genome: Grounded Social Reasoning Abilities of Multimodal Models","created":"2025-02-21","cited_by_count":26},{"id":"1801.06055","title":"Detecting Low Rapport During Natural Interactions in Small Groups from Non-Verbal Behaviour","created":"2018-01-08","cited_by_count":24},{"id":"2407.02477","title":"Understanding Alignment in Multimodal LLMs: A Comprehensive Study","created":"2024-07-02","cited_by_count":23},{"id":"2408.12763","title":"Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models","created":"2024-08-22","cited_by_count":23},{"id":"2404.11023","title":"Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions","created":"2024-04-17","cited_by_count":22},{"id":"2207.12817","title":"Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation","created":"2022-07-26","cited_by_count":19},{"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":"2506.05425","title":"SIV-Bench: A Video Benchmark for Social Interaction Understanding and Reasoning","created":"2025-06-05","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":"2412.12718","title":"ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding","created":"2024-12-17","cited_by_count":15},{"id":"2312.12870","title":"The Audio-Visual Conversational Graph: From an Egocentric-Exocentric Perspective","created":"2023-12-20","cited_by_count":14},{"id":"2503.17928","title":"Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization","created":"2025-03-23","cited_by_count":14},{"id":"2503.19355","title":"ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models","created":"2025-03-25","cited_by_count":13},{"id":"2408.12867","title":"Semantic Alignment for Multimodal Large Language Models","created":"2024-08-23","cited_by_count":12},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12},{"id":"2504.18039","title":"MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind","created":"2025-04-25","cited_by_count":12},{"id":"2504.02244","title":"SocialGesture: Delving into Multi-person Gesture Understanding","created":"2025-04-03","cited_by_count":11},{"id":"2406.09295","title":"AlignMMBench: Evaluating Chinese Multimodal Alignment in Large Vision-Language Models","created":"2024-06-13","cited_by_count":8},{"id":"2407.07402","title":"ActionVOS: Actions as Prompts for Video Object Segmentation","created":"2024-07-10","cited_by_count":8},{"id":"2503.04250","title":"An Egocentric Vision-Language Model based Portable Real-time Smart Assistant","created":"2025-03-06","cited_by_count":8},{"id":"2503.02597","title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs","created":"2025-03-04","cited_by_count":7},{"id":"2510.27195","title":"Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions","created":"2025-10-31","cited_by_count":6},{"id":"2505.17536","title":"Multimodal Conversation Structure Understanding","created":"2025-05-23","cited_by_count":4},{"id":"2505.24389","title":"Leadership Assessment in Pediatric Intensive Care Unit Team Training","created":"2025-05-30","cited_by_count":3},{"id":"2507.20409","title":"Cognitive Chain-of-Thought (CoCoT): Structured Multimodal Reasoning about Social Situations","created":"2025-07-27","cited_by_count":3},{"id":"2508.03144","title":"LORE: Latent Optimization for Precise Semantic Control in Rectified Flow-based Image Editing","created":"2025-08-05","cited_by_count":3},{"id":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","cited_by_count":2},{"id":"2505.14346","title":"Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance","created":"2025-05-20","cited_by_count":2},{"id":"2508.00332","title":"Improving Multimodal Contrastive Learning of Sentence Embeddings with Object-Phrase Alignment","created":"2025-08-01","cited_by_count":1}],"next_cursor":null}