{"total":53,"rows":[{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2405.18415","title":"Why are Visually-Grounded Language Models Bad at Image Classification?","created":"2024-05-28","cited_by_count":102,"area":null},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2506.07491","title":"SpatialLM: Training Large Language Models for Structured Indoor Modeling","created":"2025-06-09","cited_by_count":65,"area":null},{"id":"2507.06119","title":"Omni-Video: Democratizing Unified Video Understanding and Generation","created":"2025-07-08","cited_by_count":40,"area":null},{"id":"2412.14480","title":"GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering","created":"2024-12-19","cited_by_count":37,"area":null},{"id":"2503.11117","title":"Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering","created":"2025-03-14","cited_by_count":30,"area":null},{"id":"2506.05904","title":"Proactive Assistant Dialogue Generation from Streaming Egocentric Videos","created":"2025-06-06","cited_by_count":28,"area":null},{"id":"2409.15250","title":"ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models","created":"2024-09-23","cited_by_count":27,"area":null},{"id":"2511.07732","title":"ViPRA: Video Prediction for Robot Actions","created":"2025-11-11","cited_by_count":26,"area":null},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2507.06219","title":"Is Diversity All You Need for Scalable Robotic Manipulation?","created":"2025-07-08","cited_by_count":20,"area":null},{"id":"2410.20263","title":"EfficientEQA: An Efficient Approach to Open-Vocabulary Embodied Question Answering","created":"2024-10-26","cited_by_count":15,"area":null},{"id":"2404.01331","title":"LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model","created":"2024-03-29","cited_by_count":14,"area":null},{"id":"2406.13193","title":"PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes","created":"2024-06-19","cited_by_count":14,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2503.08686","title":"OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models","created":"2025-03-11","cited_by_count":12,"area":null},{"id":"2505.13948","title":"Memory-Centric Embodied Question Answering","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2410.01220","title":"Effective Tuning Strategies for Generalist Robot Manipulation Policies","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2510.09507","title":"PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs","created":"2025-10-10","cited_by_count":9,"area":null},{"id":"2407.03967","title":"Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2503.22215","title":"Learning to Instruct for Visual Instruction Tuning","created":"2025-03-28","cited_by_count":8,"area":null},{"id":"2604.28192","title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","created":"2026-04-30","cited_by_count":8,"area":null},{"id":"2410.05090","title":"HyperINF: Unleashing the HyperPower of the Schulz's Method for Data Influence Estimation","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2510.01934","title":"Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2512.22208","title":"Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2605.25547","title":"TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation","created":"2026-05-25","cited_by_count":5,"area":null},{"id":"2608.19613","title":"What Matters for Latent Actions in Robot Learning","created":"2026-08-20","cited_by_count":4,"area":null},{"id":"2407.17974","title":"What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language models","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2412.18224","title":"Expand VSR Benchmark for VLLM to Expertize in Spatial Rules","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2510.26006","title":"CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2604.04133","title":"Learning Robust Visual Features in Computed Tomography Enables Efficient Transfer Learning for Clinical Tasks","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2511.17411","title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2601.06309","title":"VideoWeave: A Data-Centric Approach for Efficient Video Understanding","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2503.07603","title":"Should VLMs be Pre-trained with Image Data?","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2511.19647","title":"Robot-Powered Data Flywheels: Deploying Robots in the Wild for Continual Data Collection and Foundation Model Adaptation","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2512.06013","title":"VAT: Vision Action Transformer by Unlocking Full Representation of ViT","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2512.08548","title":"Bridging Scale Discrepancies in Robotic Control via Language-Based Action Representations","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2602.19096","title":"The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2603.07474","title":"Cross-Modal Taxonomic Generalization in (Vision-) Language Models","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2604.17019","title":"Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2606.01649","title":"PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2508.12466","title":"Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping","created":"2025-08-17","cited_by_count":0,"area":null},{"id":"2510.19373","title":"Using Temperature Sampling to Effectively Train Robot Learning Policies on Imbalanced Datasets","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2512.14188","title":"Optimizing the Adversarial Perturbation with a Momentum-based Adaptive Matrix","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2603.19209","title":"Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2606.00145","title":"Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.03879","title":"Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.21139","title":"PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.16165","title":"An Exam for Active Observers","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.14986","title":"GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2610.06078","title":"Do VLAs Understand and Adapt to the Objects They Handle, or Simply Replay Learned Behaviors?","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}