{"total":109,"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":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466,"area":"lr"},{"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":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311,"area":null},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244,"area":"mllm"},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73,"area":"mllm"},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2506.23044","title":"Ovis-U1 Technical Report","created":"2025-06-29","cited_by_count":67,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2507.09404","title":"Scaling Laws for Optimal Data Mixtures","created":"2025-07-12","cited_by_count":52,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"id":"2503.20680","title":"Vision as LoRA","created":"2025-03-26","cited_by_count":37,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","cited_by_count":36,"area":null},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2503.18944","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","created":"2025-03-24","cited_by_count":31,"area":null},{"id":"2503.19903","title":"Scaling Vision Pre-Training to 4K Resolution","created":"2025-03-25","cited_by_count":28,"area":null},{"id":"2512.16922","title":"Next-Embedding Prediction Makes Strong Vision Learners","created":"2025-12-18","cited_by_count":23,"area":null},{"id":"2507.14137","title":"Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning","created":"2025-07-18","cited_by_count":21,"area":null},{"id":"2501.02576","title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","created":"2025-01-05","cited_by_count":19,"area":"diffusion"},{"id":"2501.03012","title":"Analyzing Finetuning Representation Shift for Multimodal LLMs Steering","created":"2025-01-06","cited_by_count":16,"area":"mllm"},{"id":"2505.04601","title":"OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning","created":"2025-05-07","cited_by_count":16,"area":null},{"id":"2508.19294","title":"Object Detection with Multimodal Large Vision-Language Models: An In-depth Review","created":"2025-08-25","cited_by_count":14,"area":"mllm"},{"id":"2509.14033","title":"SAIL-VL2 Technical Report","created":"2025-09-17","cited_by_count":14,"area":"mllm"},{"id":"2507.20025","title":"Region-based Cluster Discrimination for Visual Representation Learning","created":"2025-07-26","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":"2505.10917","title":"VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization","created":"2025-05-16","cited_by_count":12,"area":"mllm"},{"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":"2501.10834","title":"Visual RAG: Expanding MLLM visual knowledge without fine-tuning","created":"2025-01-18","cited_by_count":11,"area":"mllm"},{"id":"2503.06362","title":"Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs","created":"2025-03-09","cited_by_count":11,"area":"mllm"},{"id":"2506.10178","title":"Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency","created":"2025-06-11","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":"2505.14336","title":"Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach","created":"2025-05-20","cited_by_count":10,"area":"moe"},{"id":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2603.22387","title":"Efficient Universal Perception Encoder","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2509.17562","title":"Visual Instruction Pretraining for Domain-Specific Foundation Models","created":"2025-09-22","cited_by_count":9,"area":null},{"id":"2511.18262","title":"MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation","created":"2025-11-23","cited_by_count":9,"area":"diffusion"},{"id":"2506.08071","title":"CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systems","created":"2025-06-09","cited_by_count":8,"area":null},{"id":"2601.09954","title":"The Spatial Blindspot of Vision-Language Models","created":"2026-01-15","cited_by_count":8,"area":"mllm"},{"id":"2503.02597","title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs","created":"2025-03-04","cited_by_count":7,"area":"mllm"},{"id":"2509.01644","title":"OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning","created":"2025-09-01","cited_by_count":7,"area":null},{"id":"2503.18931","title":"Enhancing Vision Foundation Models via Multimodal Continual Pre-Training","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2506.09082","title":"AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2507.02279","title":"LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models","created":"2025-07-03","cited_by_count":5,"area":"mllm"},{"id":"2505.05626","title":"Perceiving Beyond Language Priors: Enhancing Visual Comprehension and Attention in Multimodal Models","created":"2025-05-08","cited_by_count":4,"area":"mllm"},{"id":"2505.09498","title":"Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput","created":"2025-05-14","cited_by_count":4,"area":"mllm"},{"id":"2507.01643","title":"SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement","created":"2025-07-02","cited_by_count":4,"area":"mllm"},{"id":"2511.07253","title":"Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2606.18249","title":"Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification","created":"2026-06-16","cited_by_count":4,"area":null},{"id":"2501.06708","title":"Evaluating Sample Utility for Efficient Data Selection by Mimicking Model Weights","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2504.01792","title":"UniViTAR: Unified Vision Transformer with Native Resolution","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2504.06486","title":"Mind the (Data) Gap: Evaluating Vision Systems in Small Data Applications","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2509.11662","title":"MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs","created":"2025-09-15","cited_by_count":3,"area":"mllm"},{"id":"2510.00063","title":"AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy","created":"2025-09-29","cited_by_count":3,"area":"mllm"},{"id":"2510.20860","title":"Data-Centric Lessons To Improve Speech-Language Pretraining","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2511.12331","title":"SpaceVLM: Sub-Space Modeling of Negation in Vision-Language Models","created":"2025-11-15","cited_by_count":3,"area":"mllm"},{"id":"2601.08078","title":"Exploiting DINOv3-Based Self-Supervised Features for Robust Few-Shot Medical Image Segmentation","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2503.20662","title":"AutoRad-Lung: A Radiomic-Guided Prompting Autoregressive Vision-Language Model for Lung Nodule Malignancy Prediction","created":"2025-03-26","cited_by_count":2,"area":"mllm"},{"id":"2511.02280","title":"SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2512.06281","title":"Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models","created":"2025-12-06","cited_by_count":2,"area":"mllm"},{"id":"2512.17221","title":"DAVE: A VLM Vision Encoder for Document Understanding and Web Agents","created":"2025-12-19","cited_by_count":2,"area":"mllm"},{"id":"2601.20075","title":"Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning","created":"2026-01-27","cited_by_count":2,"area":"mllm"},{"id":"2603.12433","title":"Revisiting Model Stitching In the Foundation Model Era","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2603.22057","title":"SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2605.00809","title":"Let ViT Speak: Generative Language-Image Pre-training","created":"2026-05-01","cited_by_count":2,"area":"mllm"},{"id":"2605.08985","title":"LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?","created":"2026-05-09","cited_by_count":2,"area":"mllm"},{"id":"2607.26860","title":"Amortized Moment Matching for Visual Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2504.11895","title":"Search is All You Need for Few-shot Anomaly Detection","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2505.19779","title":"Advancements in Medical Image Classification through Fine-Tuning Natural Domain Foundation Models","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2510.21501","title":"GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs","created":"2025-10-23","cited_by_count":1,"area":"mllm"},{"id":"2511.20770","title":"Text-Guided Semantic Image Encoder","created":"2025-11-25","cited_by_count":1,"area":"mllm"},{"id":"2512.14102","title":"Neurosymbolic Inference On Foundation Models For Remote Sensing Text-to-image Retrieval With Complex Queries","created":"2025-12-16","cited_by_count":1,"area":"mllm"},{"id":"2603.04950","title":"Location-Aware Pretraining for Medical Difference Visual Question Answering","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.12545","title":"Spatial Reasoning is Not a Free Lunch: A Controlled Study on LLaVA","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2605.09422","title":"Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs","created":"2026-05-10","cited_by_count":1,"area":"mllm"},{"id":"2605.09485","title":"SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2605.26641","title":"OmniRetriever: Any-to-Any Audio-Video-Text Retrieval via Fusion-as-Teacher Distillation","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.27313","title":"ViQ: Text-Aligned Visual Quantized Representations at Any Resolution","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2608.17402","title":"MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding","created":"2026-08-18","cited_by_count":1,"area":"mllm"},{"id":"2509.04834","title":"TemporalFlowViz: Parameter-Aware Visual Analytics for Interpreting Scramjet Combustion Evolution","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2510.08775","title":"Re-Identifying K\\={a}k\\={a} with AI-Automated Video Key Frame Extraction","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2511.16315","title":"BioBench: A Blueprint to Move Beyond ImageNet for Scientific ML Benchmarks","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.19846","title":"Face, Whole-Person, and Object Classification in a Unified Space Via The Interleaved Multi-Domain Identity Curriculum","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.22489","title":"Tracking by Predicting 3-D Gaussians Over Time","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2602.05262","title":"ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.13961","title":"MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Mars","created":"2026-02-15","cited_by_count":0,"area":"mllm"},{"id":"2602.16918","title":"Xray-Visual Models: Scaling Vision models on Industry Scale Data","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.03806","title":"Separators in Enhancing Autoregressive Pretraining for Vision Mamba","created":"2026-03-04","cited_by_count":0,"area":"ssm"},{"id":"2603.17326","title":"FineViT: Progressively Unlocking Fine-Grained Perception with Dense Recaptions","created":"2026-03-18","cited_by_count":0,"area":"mllm"},{"id":"2603.20020","title":"Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2604.00086","title":"Hierarchical Pre-Training of Vision Encoders with Large Language Model","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.17376","title":"Towards Generalizable Deepfake Image Detection with Vision Transformers","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2604.17961","title":"DifFoundMAD: Foundation Models meet Differential Morphing Attack Detection","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.18160","title":"Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2606.29451","title":"The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2607.00687","title":"LUMA: Benchmarking Segmentation via a Lightweight Universal Mask Adapter","created":"2026-07-01","cited_by_count":0,"area":null}],"next_cursor":"100"}