{"total":61,"rows":[{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611,"area":"lr"},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388,"area":"lr"},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314,"area":"lr"},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279,"area":"lr"},{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183,"area":"lr"},{"id":"2506.09965","title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","created":"2025-06-11","cited_by_count":136,"area":"lr"},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97,"area":"lr"},{"id":"2404.06511","title":"MoReVQA: Exploring Modular Reasoning Models for Video Question Answering","created":"2024-04-09","cited_by_count":74,"area":"lr"},{"id":"2312.06722","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","created":"2023-12-11","cited_by_count":69,"area":"lr"},{"id":"2506.13654","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning","created":"2025-06-16","cited_by_count":68,"area":"lr"},{"id":"2409.13682","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","created":"2024-09-20","cited_by_count":67,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2406.19392","title":"ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos","created":"2024-06-27","cited_by_count":51,"area":"lr"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2506.16141","title":"GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning","created":"2025-06-19","cited_by_count":47,"area":"lr"},{"id":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"id":"2503.13444","title":"VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning","created":"2025-03-17","cited_by_count":43,"area":"lr"},{"id":"2412.04447","title":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","created":"2024-12-05","cited_by_count":41,"area":"lr"},{"id":"2412.01694","title":"Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation","created":"2024-12-02","cited_by_count":37,"area":"lr"},{"id":"2602.02994","title":"Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation","created":"2026-02-03","cited_by_count":36,"area":"lr"},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35,"area":"lr"},{"id":"2503.24376","title":"Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1","created":"2025-03-31","cited_by_count":25,"area":"lr"},{"id":"2503.12542","title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos","created":"2025-03-16","cited_by_count":21,"area":"lr"},{"id":"2507.18100","title":"Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"id":"2506.05414","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","created":"2025-06-04","cited_by_count":15,"area":"lr"},{"id":"2506.17629","title":"CLiViS: Unleashing Cognitive Map through Linguistic-Visual Synergy for Embodied Visual Reasoning","created":"2025-06-21","cited_by_count":13,"area":"lr"},{"id":"2503.22152","title":"EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos","created":"2025-03-28","cited_by_count":12,"area":"lr"},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"id":"2305.16602","title":"Discovering Novel Actions from Open World Egocentric Videos with Object-Grounded Visual Commonsense Reasoning","created":"2023-05-26","cited_by_count":6,"area":"lr"},{"id":"2505.24257","title":"Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames","created":"2025-05-30","cited_by_count":6,"area":"lr"},{"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,"area":"lr"},{"id":"2603.17312","title":"Recurrent Reasoning with Vision-Language Models for Estimating Long-Horizon Embodied Task Progress","created":"2026-03-18","cited_by_count":6,"area":"lr"},{"id":"2408.03160","title":"User-in-the-loop Evaluation of Multimodal LLMs for Activity Assistance","created":"2024-08-04","cited_by_count":5,"area":"lr"},{"id":"2508.07626","title":"AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning","created":"2025-08-11","cited_by_count":5,"area":"lr"},{"id":"2512.05513","title":"Know-Show: Benchmarking Video-Language Models on Spatio-Temporal Grounded Reasoning","created":"2025-12-05","cited_by_count":5,"area":"lr"},{"id":"2603.25021","title":"VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning","created":"2026-03-26","cited_by_count":3,"area":"lr"},{"id":"2606.09248","title":"Temporal-Aware Reasoning Optimization for Video Temporal Grounding","created":"2026-06-08","cited_by_count":3,"area":"lr"},{"id":"2510.13808","title":"VisCoP: Visual Probing for Video Domain Adaptation of Vision Language Models","created":"2025-10-15","cited_by_count":2,"area":"lr"},{"id":"2510.16442","title":"EDVD-LLaMA: Explainable Deepfake Video Detection via Multimodal Large Language Model Reasoning","created":"2025-10-18","cited_by_count":2,"area":"lr"},{"id":"2603.10652","title":"Are Video Reasoning Models Ready to Go Outside?","created":"2026-03-11","cited_by_count":2,"area":"lr"},{"id":"2603.22057","title":"SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2505.17645","title":"HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning","created":"2025-05-23","cited_by_count":1,"area":"lr"},{"id":"2601.12781","title":"VIRO: Robust and Efficient Neuro-Symbolic Reasoning with Verification for Referring Expression Comprehension","created":"2026-01-19","cited_by_count":1,"area":"lr"},{"id":"2602.20608","title":"VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2603.09731","title":"EXPLORE-Bench: Egocentric Scene Prediction with Long-Horizon Reasoning","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2604.04733","title":"Discovering Failure Modes in Vision-Language Models using RL","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.10517","title":"From Perception to Planning: Evolving Ego-Centric Task-Oriented Spatiotemporal Reasoning via Curriculum Learning","created":"2026-04-12","cited_by_count":1,"area":"lr"},{"id":"2606.25842","title":"Graph it first! Enabling Reasoning on Long-form Egocentric Videos through Scene Graphs","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2607.02425","title":"Learning to Evolve Scenes: Reasoning about Human Activities with Scene Graphs","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2608.15869","title":"Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2406.00307","title":"HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model","created":"2024-06-01","cited_by_count":0,"area":"lr"},{"id":"2509.18200","title":"Conversational Orientation Reasoning: Egocentric-to-Allocentric Navigation with Multimodal Chain-of-Thought","created":"2025-09-20","cited_by_count":0,"area":"lr"},{"id":"2601.08010","title":"CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2604.11177","title":"Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene Understanding","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.03927","title":"StateVLM: A State-Aware Vision-Language Model for Robotic Affordance Reasoning","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2606.00616","title":"Pause and Think: A Dataset and Benchmark for Video-Grounded Assistive Action Suggestion","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.23092","title":"PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2609.10815","title":"BodyCam-VQA: Enhanced Body-Worn Camera Video Captioning via Multimodal Reasoning and Probe Question Generation","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.31751","title":"EgoTSR++: Egocentric Spatiotemporal Reasoning for Task Progress Understanding","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.04506","title":"EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}