{"total":64,"rows":[{"id":"2602.11858","title":"Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception","created":"2026-02-12","cited_by_count":50,"area":"mllm"},{"id":"2509.18095","title":"MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction","created":"2025-09-22","cited_by_count":39,"area":null},{"id":"2510.10921","title":"FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model","created":"2025-10-13","cited_by_count":13,"area":null},{"id":"2512.15715","title":"In Pursuit of Pixel Supervision for Visual Pre-training","created":"2025-12-17","cited_by_count":13,"area":null},{"id":"2603.01840","title":"FireRed-OCR Technical Report","created":"2026-03-02","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":"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":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"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":"2510.25947","title":"Revisiting Multilingual Data Mixtures in Language Model Pretraining","created":"2025-10-29","cited_by_count":10,"area":null},{"id":"2512.17951","title":"SuperFlow: Training Flow Matching Models with RL on the Fly","created":"2025-12-17","cited_by_count":10,"area":"diffusion"},{"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":"2602.02537","title":"WorldVQA: Measuring Atomic World Knowledge in Multimodal Large Language Models","created":"2026-01-28","cited_by_count":8,"area":"mllm"},{"id":"2601.15369","title":"OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation","created":"2026-01-21","cited_by_count":5,"area":null},{"id":"2604.21681","title":"Sapiens2","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2602.09839","title":"ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.26646","title":"Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.00809","title":"Let ViT Speak: Generative Language-Image Pre-training","created":"2026-05-01","cited_by_count":2,"area":"mllm"},{"id":"2508.09814","title":"On the dynamic evolution of CLIP texture-shape bias and its relationship to human alignment and model robustness","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2509.23370","title":"GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval","created":"2025-09-27","cited_by_count":1,"area":"lr"},{"id":"2510.13364","title":"Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcity","created":"2025-10-15","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":"2511.23170","title":"PowerCLIP: Powerset Alignment for Contrastive Pre-Training","created":"2025-11-28","cited_by_count":1,"area":"mllm"},{"id":"2512.12107","title":"EchoVLM: Measurement-Grounded Multimodal Learning for Echocardiography","created":"2025-12-13","cited_by_count":1,"area":"mllm"},{"id":"2604.03555","title":"HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2604.03558","title":"LOGER: Local--Global Ensemble for Robust Deepfake Detection in the Wild","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2605.12650","title":"CRAFT: Clinical Reward-Aligned Finetuning for Medical Image Synthesis","created":"2026-05-12","cited_by_count":1,"area":"mllm"},{"id":"2606.21496","title":"Decoupling the Declarative from the Procedural in Vision-Language-Action Models","created":"2026-06-19","cited_by_count":1,"area":"vla"},{"id":"2608.11002","title":"On the Limitations of Cross-Lingual Consistency in Multilingual Text-to-image Generation","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2512.10340","title":"Learning Ordinal Degradation Representations with Textual Priors for Diffusion-Based Blind Image Super-Resolution","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.10305","title":"DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset","created":"2026-01-15","cited_by_count":0,"area":"mllm"},{"id":"2602.01753","title":"ObjEmbed: Towards Universal Multimodal Object Embeddings","created":"2026-02-02","cited_by_count":0,"area":null},{"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":"2603.04598","title":"PinPoint: Evaluation of Composed Image Retrieval with Explicit Negatives, Multi-Image Queries, and Paraphrase Testing","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.27759","title":"When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models","created":"2026-03-29","cited_by_count":0,"area":"mllm"},{"id":"2604.08008","title":"SearchAD: Large-Scale Rare Image Retrieval Dataset for Autonomous Driving","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.12307","title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.13313","title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","created":"2026-04-14","cited_by_count":0,"area":"mllm"},{"id":"2605.13178","title":"CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2605.18029","title":"What Matters for Grocery Product Retrieval with Open Source Vision Language Models","created":"2026-05-18","cited_by_count":0,"area":"mllm"},{"id":"2606.04613","title":"Beyond Symmetric Alignment: Spectral Diagnostics of Modality Imbalance in Vision-Language Models in the Medical Domain","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2606.22749","title":"RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.26794","title":"ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP","created":"2026-06-25","cited_by_count":0,"area":"lr"},{"id":"2606.29888","title":"Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse Autoencoders","created":"2026-06-29","cited_by_count":0,"area":"mllm"},{"id":"2607.00684","title":"AdaBoosting Text Prompts for Vision-Language Models","created":"2026-07-01","cited_by_count":0,"area":"mllm"},{"id":"2607.23924","title":"DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.25794","title":"Fine-Grained Food Image Understanding via Target-Aware Data Alignment","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.28211","title":"Scaling Vision-Language Models Is Not Enough to Mitigate Bias","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.03875","title":"Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning","created":"2026-08-04","cited_by_count":0,"area":"alignment"},{"id":"2608.11367","title":"Gaze Target Estimation Anywhere with Concepts","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.12155","title":"Understanding Why Foundation Models Work for Diffusion-Generated Image Detection","created":"2026-08-12","cited_by_count":0,"area":"diffusion"},{"id":"2608.25653","title":"Towards Purified Multi-Label Test-Time Adaptation of Vision-Language Models","created":"2026-08-26","cited_by_count":0,"area":"mllm"},{"id":"2608.30725","title":"Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01027","title":"Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05730","title":"Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.07823","title":"SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"id":"2609.30739","title":"SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.34106","title":"The Devil is in the Spectrum Bias: Spectrum-Balanced Feature Matching for Robust Representation Distillation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35583","title":"What Paired Evaluations Reveal under Visual Perturbations","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.05413","title":"A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models","created":"2026-10-04","cited_by_count":0,"area":"mllm"},{"id":"2610.05718","title":"ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06919","title":"Anchor Divergence for Semantic Geometry in Contrastive Learning","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.16813","title":"Carve VFM: Carving Specialists out of Generalists, Automatic Task-Specific Compression of Vision Foundation Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}