{"total":59,"rows":[{"id":"2506.04308","title":"RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics","created":"2025-06-04","cited_by_count":127,"area":"lr"},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102,"area":"vla"},{"id":"2411.16575","title":"Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression","created":"2024-11-25","cited_by_count":85,"area":null},{"id":"2506.24086","title":"MotionGPT3: Human Motion as a Second Modality","created":"2025-06-30","cited_by_count":37,"area":null},{"id":"2505.19377","title":"Absolute Coordinates Make Motion Generation Easy","created":"2025-05-26","cited_by_count":29,"area":null},{"id":"2510.07181","title":"TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2510.14952","title":"From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2504.09209","title":"EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation","created":"2025-04-12","cited_by_count":17,"area":null},{"id":"2504.19189","title":"Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation","created":"2025-04-27","cited_by_count":17,"area":null},{"id":"2511.19217","title":"ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment","created":"2025-11-24","cited_by_count":13,"area":"alignment"},{"id":"2602.12370","title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","created":"2026-02-12","cited_by_count":11,"area":null},{"id":"2507.05419","title":"Motion Generation: A Survey of Generative Approaches and Benchmarks","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2503.21775","title":"StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion","created":"2025-03-27","cited_by_count":7,"area":"diffusion"},{"id":"2508.03343","title":"WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval","created":"2025-08-05","cited_by_count":7,"area":null},{"id":"2512.23649","title":"RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion","created":"2025-12-29","cited_by_count":7,"area":null},{"id":"2512.10730","title":"IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2502.18536","title":"FilterRAG: Zero-Shot Informed Retrieval-Augmented Generation to Mitigate Hallucinations in VQA","created":"2025-02-25","cited_by_count":5,"area":"rag"},{"id":"2510.00483","title":"MathSticks: A Benchmark for Visual Symbolic Compositional Reasoning with Matchstick Puzzles","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2502.16175","title":"Mojito: LLM-Aided Motion Instructor with Jitter-Reduced Inertial Tokens","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2508.12081","title":"VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models","created":"2025-08-16","cited_by_count":4,"area":"rag"},{"id":"2509.04058","title":"SMooGPT: Stylized Motion Generation using Large Language Models","created":"2025-09-04","cited_by_count":4,"area":"diffusion"},{"id":"2601.01618","title":"Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation","created":"2026-01-04","cited_by_count":4,"area":"vla"},{"id":"2602.07967","title":"EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation","created":"2026-02-08","cited_by_count":4,"area":null},{"id":"2603.19227","title":"Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer","created":"2026-03-19","cited_by_count":4,"area":"diffusion"},{"id":"2603.22282","title":"UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2510.14954","title":"OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2512.21237","title":"SegMo: Segment-aligned Text to 3D Human Motion Generation","created":"2025-12-24","cited_by_count":3,"area":null},{"id":"2601.12126","title":"UniMo: Unified Motion Generation and Understanding with Chain of Thought","created":"2026-01-17","cited_by_count":3,"area":"lr"},{"id":"2412.09901","title":"MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow","created":"2024-12-13","cited_by_count":2,"area":null},{"id":"2506.14428","title":"Toward Rich Video Human-Motion2D Generation","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2602.08337","title":"Language-Guided Transformer Tokenizer for Human Motion Generation","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2602.23739","title":"U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation","created":"2026-02-27","cited_by_count":2,"area":null},{"id":"2603.29655","title":"Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2603.09611","title":"ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2603.11605","title":"LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.27185","title":"MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2505.04974","title":"ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment","created":"2025-05-08","cited_by_count":0,"area":"diffusion"},{"id":"2505.18465","title":"BiomechGPT: Extending Motion-Language Models to Clinical Motion Understanding","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2505.23886","title":"Generating Fit Check Videos with a Handheld Camera","created":"2025-05-29","cited_by_count":0,"area":"diffusion"},{"id":"2510.13044","title":"SceneAdapt: Scene-aware Adaptation of Human Motion Diffusion","created":"2025-10-14","cited_by_count":0,"area":null},{"id":"2601.07632","title":"GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.14788","title":"Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation","created":"2026-01-21","cited_by_count":0,"area":"diffusion"},{"id":"2602.08462","title":"TriC-Motion: Tri-Domain Causal Modeling Grounded Text-to-Motion Generation","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.11064","title":"Motion Capture is Not the Target Domain: Scaling Synthetic Data for Learning Motion Representations","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.14534","title":"MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation","created":"2026-02-16","cited_by_count":0,"area":"lr"},{"id":"2603.23684","title":"MoCHA: Denoising Caption Supervision for Motion-Text Retrieval","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.17090","title":"Marrying Text-to-Motion Generation with Skeleton-Based Action Recognition","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2604.21668","title":"Encoder-Free Human Motion Understanding via Structured Motion Descriptions","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2605.14935","title":"Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.18956","title":"MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation","created":"2026-05-18","cited_by_count":0,"area":"lr"},{"id":"2607.22702","title":"MIME: Multimodal Interactive Motion Encoder","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.27581","title":"MUGEN: A Unified Framework for Efficient Motion Understanding and Generation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.08365","title":"ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation","created":"2026-09-08","cited_by_count":0,"area":"rag"},{"id":"2609.11439","title":"Multi-Modal Controlled Coherent Motion Generation","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.14615","title":"Open-UniMo: Towards Unified Motion-Language Understanding and Generation in the Open World","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2609.14965","title":"MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion Generation","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.32551","title":"Harnessing Coupled Stream Completion For Human-Object Interaction Modeling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35407","title":"BiMoGen: Bidirectional Motion-Text Generation via Unified Masked Discrete Diffusion","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2610.05411","title":"CleanMDM: Clean Motion Diffusion Model for Multimodal Motion Cleanup","created":"2026-10-04","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}