{"total":326,"rows":[{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809,"area":"wm"},{"id":"2506.01844","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","created":"2025-06-02","cited_by_count":530,"area":"mllm"},{"id":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64,"area":"mllm"},{"id":"2602.14486","title":"Revisiting the Platonic Representation Hypothesis: An Aristotelian View","created":"2026-02-16","cited_by_count":44,"area":null},{"id":"2509.07979","title":"Visual Representation Alignment for Multimodal Large Language Models","created":"2025-09-09","cited_by_count":41,"area":"lr"},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37,"area":"moe"},{"id":"2509.02722","title":"Planning with Reasoning using Vision Language World Model","created":"2025-09-02","cited_by_count":36,"area":"wm"},{"id":"2509.25162","title":"AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models","created":"2025-09-29","cited_by_count":36,"area":"diffusion"},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2601.09668","title":"STEP3-VL-10B Technical Report","created":"2026-01-14","cited_by_count":32,"area":null},{"id":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2601.19887","title":"VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction","created":"2026-01-27","cited_by_count":28,"area":null},{"id":"2602.13823","title":"Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings","created":"2026-02-14","cited_by_count":24,"area":"lr"},{"id":"2510.15042","title":"Comprehensive language-image pre-training for 3D medical image understanding","created":"2025-10-16","cited_by_count":22,"area":"mllm"},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2512.17909","title":"Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing","created":"2025-12-19","cited_by_count":22,"area":"diffusion"},{"id":"2602.07050","title":"Interpreting Physics in Video World Models","created":"2026-02-04","cited_by_count":22,"area":"wm"},{"id":"2508.06248","title":"Deepfake Detection that Generalizes Across Benchmarks","created":"2025-08-08","cited_by_count":21,"area":null},{"id":"2504.20734","title":"UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities","created":"2025-04-29","cited_by_count":20,"area":"rag"},{"id":"2505.18132","title":"BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models","created":"2025-05-23","cited_by_count":20,"area":null},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2507.19946","title":"SCALAR: Scale-wise Controllable Visual Autoregressive Learning","created":"2025-07-26","cited_by_count":18,"area":null},{"id":"2509.23082","title":"Follow-Your-Preference: Towards Preference-Aligned Image Inpainting","created":"2025-09-27","cited_by_count":18,"area":"alignment"},{"id":"2510.18457","title":"VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models","created":"2025-10-21","cited_by_count":17,"area":"diffusion"},{"id":"2512.08730","title":"SegEarth-OV3: Exploring SAM 3 for Open-Vocabulary Semantic Segmentation in Remote Sensing Images","created":"2025-12-09","cited_by_count":16,"area":null},{"id":"2604.18572","title":"Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale","created":"2026-04-20","cited_by_count":16,"area":null},{"id":"2505.13928","title":"LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts","created":"2025-05-20","cited_by_count":14,"area":null},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2512.15715","title":"In Pursuit of Pixel Supervision for Visual Pre-training","created":"2025-12-17","cited_by_count":13,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2604.12012","title":"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment","created":"2026-04-13","cited_by_count":13,"area":"mllm"},{"id":"2606.13674","title":"RepWAM: World Action Modeling with Representation Visual-Action Tokenizers","created":"2026-06-11","cited_by_count":13,"area":"wm"},{"id":"2505.15205","title":"Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection","created":"2025-05-21","cited_by_count":12,"area":null},{"id":"2509.24317","title":"Rethinking JEPA: Compute-Efficient Video SSL with Frozen Teachers","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2602.08683","title":"OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence","created":"2026-02-09","cited_by_count":12,"area":null},{"id":"2602.14974","title":"DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI","created":"2026-02-16","cited_by_count":12,"area":"vla"},{"id":"2603.28480","title":"INSID3: Training-Free In-Context Segmentation with DINOv3","created":"2026-03-30","cited_by_count":12,"area":null},{"id":"2510.21356","title":"Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding","created":"2025-10-24","cited_by_count":11,"area":null},{"id":"2607.02375","title":"Representation Distribution Matching for One-Step Visual Generation","created":"2026-07-02","cited_by_count":11,"area":null},{"id":"2505.07634","title":"Neural Brain: A Neuroscience-inspired Framework for Embodied Agents","created":"2025-05-12","cited_by_count":10,"area":"agents"},{"id":"2509.12995","title":"Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detection","created":"2025-09-16","cited_by_count":10,"area":null},{"id":"2512.17817","title":"Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding","created":"2025-12-19","cited_by_count":10,"area":null},{"id":"2603.22387","title":"Efficient Universal Perception Encoder","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2607.14935","title":"VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding","created":"2026-07-16","cited_by_count":10,"area":null},{"id":"2507.02798","title":"No time to train! Training-Free Reference-Based Instance Segmentation","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2509.10151","title":"BenchECG and xECG: a benchmark and baseline for ECG foundation models","created":"2025-09-12","cited_by_count":9,"area":null},{"id":"2510.27571","title":"Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2512.04585","title":"SAM3-I: Segment Anything with Instructions","created":"2025-12-04","cited_by_count":9,"area":null},{"id":"2602.05951","title":"Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching","created":"2026-02-05","cited_by_count":9,"area":"diffusion"},{"id":"2603.12254","title":"Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing","created":"2026-03-12","cited_by_count":9,"area":"mllm"},{"id":"2601.06843","title":"Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models","created":"2026-01-11","cited_by_count":8,"area":"mllm"},{"id":"2603.15026","title":"Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2505.23769","title":"TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2509.06467","title":"Does DINOv3 Set a New Medical Vision Standard? Benchmarking 2D and 3D Classification, Segmentation, and Registration","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2510.05782","title":"Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection","created":"2025-10-07","cited_by_count":7,"area":null},{"id":"2602.01738","title":"Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models","created":"2026-02-02","cited_by_count":7,"area":null},{"id":"2605.27772","title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox","created":"2026-05-26","cited_by_count":7,"area":null},{"id":"2506.07209","title":"HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance","created":"2025-06-08","cited_by_count":6,"area":null},{"id":"2506.08456","title":"Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2510.07915","title":"MARC: Memory-Augmented RL Token Compression for Efficient Video Understanding","created":"2025-10-09","cited_by_count":6,"area":"inference"},{"id":"2511.18452","title":"NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering","created":"2025-11-23","cited_by_count":6,"area":null},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2512.24731","title":"EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation","created":"2025-12-31","cited_by_count":6,"area":null},{"id":"2604.05418","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","created":"2026-04-07","cited_by_count":6,"area":"mllm"},{"id":"2604.06912","title":"Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models","created":"2026-04-08","cited_by_count":6,"area":"mllm"},{"id":"2605.01517","title":"VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation","created":"2026-05-02","cited_by_count":6,"area":null},{"id":"2605.21028","title":"DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation","created":"2026-05-20","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2505.18660","title":"So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2509.12818","title":"Data Scaling Laws for Radiology Foundation Models","created":"2025-09-16","cited_by_count":5,"area":null},{"id":"2510.13768","title":"Scaling Vision Transformers for Functional MRI with Flat Maps","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2511.02767","title":"Dynamic Reflections: Probing Video Representations with Text Alignment","created":"2025-11-04","cited_by_count":5,"area":null},{"id":"2511.17309","title":"MuM: Multi-View Masked Image Modeling for 3D Vision","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2512.11225","title":"VFMF: World Modeling by Forecasting Vision Foundation Model Features","created":"2025-12-12","cited_by_count":5,"area":"wm"},{"id":"2512.23592","title":"Same or Not? Enhancing Visual Perception in Vision-Language Models","created":"2025-12-29","cited_by_count":5,"area":"mllm"},{"id":"2602.09009","title":"ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling","created":"2026-02-09","cited_by_count":5,"area":null},{"id":"2603.05235","title":"Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learning","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2604.22984","title":"BrickNet: Graph-Backed Generative Brick Assembly","created":"2026-04-24","cited_by_count":5,"area":null},{"id":"2606.24888","title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","created":"2026-06-23","cited_by_count":5,"area":"diffusion"},{"id":"2607.21522","title":"GS-Agent: Creating 4D Physical Worlds With Generative Simulation","created":"2026-07-23","cited_by_count":5,"area":"agents"},{"id":"2507.07104","title":"Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models","created":"2025-07-09","cited_by_count":4,"area":"mllm"},{"id":"2510.07310","title":"MATRIX: Mask Track Alignment for Interaction-aware Video Generation","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2512.01789","title":"SAM3-UNet: Simplified Adaptation of Segment Anything Model 3","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2512.24385","title":"Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2601.04778","title":"CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models","created":"2026-01-08","cited_by_count":4,"area":null},{"id":"2601.09322","title":"Attentive multilayer fusion for vision transformers","created":"2026-01-14","cited_by_count":4,"area":null},{"id":"2601.12193","title":"VeRVE: Versatile Retrieval for Videos via Unified Embeddings","created":"2026-01-17","cited_by_count":4,"area":null},{"id":"2601.16210","title":"PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2602.06333","title":"Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation","created":"2026-02-06","cited_by_count":4,"area":null},{"id":"2602.08099","title":"VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval","created":"2026-02-08","cited_by_count":4,"area":"mllm"},{"id":"2602.08626","title":"Revisiting [CLS] and Patch Token Interaction in Vision Transformers","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2603.13341","title":"Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learning","created":"2026-03-07","cited_by_count":4,"area":"mllm"},{"id":"2603.16423","title":"SF-Mamba: Rethinking State Space Model for Vision","created":"2026-03-17","cited_by_count":4,"area":"ssm"},{"id":"2603.17655","title":"Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment","created":"2026-03-18","cited_by_count":4,"area":"mllm"}],"next_cursor":"100"}