{"total":61,"rows":[{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2507.04447","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","created":"2025-07-06","cited_by_count":213,"area":"vla"},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89,"area":null},{"id":"2411.18623","title":"Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation","created":"2024-11-27","cited_by_count":46,"area":null},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32,"area":"distill"},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2410.11402","title":"M2Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenes","created":"2024-10-15","cited_by_count":27,"area":"diffusion"},{"id":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","cited_by_count":27,"area":null},{"id":"2509.11417","title":"Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations","created":"2025-09-14","cited_by_count":25,"area":"mllm"},{"id":"2410.22325","title":"Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets","created":"2024-10-29","cited_by_count":23,"area":null},{"id":"2410.01680","title":"PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation","created":"2024-10-02","cited_by_count":21,"area":"distill"},{"id":"2506.20966","title":"Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends","created":"2025-06-26","cited_by_count":17,"area":"mllm"},{"id":"2512.15715","title":"In Pursuit of Pixel Supervision for Visual Pre-training","created":"2025-12-17","cited_by_count":13,"area":null},{"id":"2509.15733","title":"GP3: A 3D Geometry-Aware Policy with Multi-View Images for Robotic Manipulation","created":"2025-09-19","cited_by_count":12,"area":null},{"id":"2410.19989","title":"On-Robot Reinforcement Learning with Goal-Contrastive Rewards","created":"2024-10-25","cited_by_count":8,"area":"deeprl"},{"id":"2512.17853","title":"AnyTask: an Automated Task and Data Generation Framework for Advancing Sim-to-Real Policy Learning","created":"2025-12-19","cited_by_count":8,"area":null},{"id":"2410.14633","title":"Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning","created":"2024-10-18","cited_by_count":7,"area":null},{"id":"2503.02844","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2502.16025","title":"FeatSharp: Your Vision Model Features, Sharper","created":"2025-02-22","cited_by_count":6,"area":null},{"id":"2510.05213","title":"VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2511.19704","title":"RADSeg: Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models","created":"2025-11-24","cited_by_count":5,"area":null},{"id":"2508.15663","title":"Mind and Motion Aligned: A Joint Evaluation IsaacSim Benchmark for Task Planning and Low-Level Policies in Mobile Manipulation","created":"2025-08-21","cited_by_count":4,"area":null},{"id":"2503.16413","title":"M3: 3D-Spatial MultiModal Memory","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2503.24298","title":"Order Matters: On Parameter-Efficient Image-to-Video Probing for Recognizing Nearly Symmetric Actions","created":"2025-03-31","cited_by_count":3,"area":null},{"id":"2504.01959","title":"Slot-Level Robotic Placement via Visual Imitation from Single Human Video","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2504.02351","title":"Agglomerating Large Vision Encoders via Distillation for VFSS Segmentation","created":"2025-04-03","cited_by_count":3,"area":null},{"id":"2506.19408","title":"Is an object-centric representation beneficial for robotic manipulation ?","created":"2025-06-24","cited_by_count":3,"area":null},{"id":"2507.09029","title":"Model Parallelism With Subnetwork Data Parallelism","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2512.20157","title":"SigLino: Efficient Multi-Teacher Distillation for Agglomerative Vision Foundation Models","created":"2025-12-23","cited_by_count":3,"area":"moe"},{"id":"2601.18923","title":"DeFM: Learning Foundation Representations from Depth for Robotics","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2601.21718","title":"When Does Predictive Inverse Dynamics Outperform Behavior Cloning?","created":"2026-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2511.10762","title":"Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues","created":"2025-11-13","cited_by_count":2,"area":null},{"id":"2601.11269","title":"X-Distill: Cross-Architecture Vision Distillation for Visuomotor Learning","created":"2026-01-16","cited_by_count":2,"area":null},{"id":"2502.19544","title":"Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data","created":"2025-02-26","cited_by_count":1,"area":"wm"},{"id":"2509.11791","title":"Synthetic vs. Real Training Data for Visual Navigation","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2512.02609","title":"SAM2Grasp: Resolve Multi-modal Grasping via Prompt-conditioned Temporal Action Prediction","created":"2025-12-02","cited_by_count":1,"area":"offlinerl"},{"id":"2603.15956","title":"ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors","created":"2026-03-16","cited_by_count":1,"area":"diffusion"},{"id":"2604.10677","title":"LIDEA: Human-to-Robot Imitation Learning via Implicit Feature Distillation and Explicit Geometry Alignment","created":"2026-04-12","cited_by_count":1,"area":"offlinerl"},{"id":"2607.07101","title":"GeoProp: Grounding Robot State in Vision for Generalist Manipulation","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2607.10762","title":"TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.28205","title":"Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2508.07144","title":"Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models","created":"2025-08-10","cited_by_count":0,"area":"moe"},{"id":"2510.15510","title":"Exploring Conditions for Diffusion models in Robotic Control","created":"2025-10-17","cited_by_count":0,"area":"diffusion"},{"id":"2512.16896","title":"Sceniris: A Fast Procedural Scene Generation Framework","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2604.22992","title":"Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.12491","title":"Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2606.03335","title":"A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2606.03444","title":"PRISM: Synergizing Vision Foundation Models via Self-organized Expert Specialization","created":"2026-06-02","cited_by_count":0,"area":"moe"},{"id":"2606.04046","title":"Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation","created":"2026-06-02","cited_by_count":0,"area":"vla"},{"id":"2606.14153","title":"Encoder Winners Do Not Reliably Transfer Across VLA Backbone Scale: A Frozen-Backbone Grafting Diagnostic","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.20559","title":"UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.14200","title":"Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games","created":"2026-07-15","cited_by_count":0,"area":"offlinerl"},{"id":"2609.18663","title":"VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.23673","title":"Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.29252","title":"IronViT: Toward Efficient Generalist Visual Representation Learning","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.36413","title":"One from Infinity: Actualizing Futures from Pretrained World Models into Robot Actions","created":"2026-09-29","cited_by_count":0,"area":"wm"},{"id":"2610.02597","title":"GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation","created":"2026-10-01","cited_by_count":0,"area":"distill"},{"id":"2610.12574","title":"Scaling Multi-Teacher Distillation for Digital Pathology","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13578","title":"RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation","created":"2026-10-09","cited_by_count":0,"area":"vla"},{"id":"2610.16908","title":"ConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder for End-to-End Autonomous Driving","created":"2026-10-12","cited_by_count":0,"area":"driving"}],"next_cursor":null}