{"total":108,"rows":[{"id":"2603.01990","title":"According to Me: Long-Term Personalized Referential Memory QA","created":"2026-03-02","cited_by_count":14,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2608.24053","title":"WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report","created":"2026-08-25","cited_by_count":8,"area":null},{"id":"2602.07595","title":"TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2604.07296","title":"OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2604.19141","title":"Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation","created":"2026-04-21","cited_by_count":5,"area":null},{"id":"2603.21937","title":"MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation","created":"2026-03-23","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":"2605.05134","title":"Low-Cost Black-Box Detection of LLM Hallucinations via Dynamical System Prediction","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2607.18237","title":"The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric","created":"2026-07-20","cited_by_count":3,"area":null},{"id":"2607.18666","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2602.13704","title":"Pailitao-VL: Unified Embedding and Reranker for Real-Time Multi-Modal Industrial Search","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2603.01493","title":"PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.08648","title":"CAST: Modeling Visual State Transitions for Consistent Video Retrieval","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2603.14827","title":"SemanticFace: Semantic Facial Action Estimation via Semantic Distillation in Interpretable Space","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.00677","title":"CL-VISTA: Benchmarking Continual Learning in Video Large Language Models","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2605.06053","title":"Towards Generation-Efficient Uncertainty Estimation in Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.06460","title":"MINER: Mining Multimodal Internal Representation for Efficient Retrieval","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2607.15205","title":"MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2608.02148","title":"Douyin Multimodal Embedding Model Technical Report","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.29607","title":"SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions","created":"2026-08-30","cited_by_count":2,"area":null},{"id":"2602.02444","title":"RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.11539","title":"CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.18508","title":"Document-as-Image Representations Fall Short for Scientific Retrieval","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.24938","title":"Your Embedding Model is SMARTer Than You Think","created":"2026-05-24","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":"2606.02120","title":"Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.14958","title":"MVEB: Massive Video Embedding Benchmark","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.30682","title":"ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.00446","title":"VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.00371","title":"Decoding Children's Gait Behavior","created":"2026-08-01","cited_by_count":1,"area":null},{"id":"2608.00962","title":"PMMC: Prospective Multimodal Memory Compilation for Long-Term LVLM Agents","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2608.09474","title":"FaLCon: Facet-Anchored Retrieval with Late Consensus for Sim2Real Text-Based Person Anomaly Search","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2608.28695","title":"Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.01778","title":"Allocate Before You Embed: Adaptive Visual Input Allocation for Video Embeddings","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.10410","title":"Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2609.15152","title":"PACE: Progressive Angular-to-Norm Contrastive Embedding","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2602.01753","title":"ObjEmbed: Towards Universal Multimodal Object Embeddings","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2603.07497","title":"AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2603.29897","title":"UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2604.06063","title":"EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.26565","title":"DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.03456","title":"VL-SAM-v3: Memory-Guided Visual Priors for Open-World Object Detection","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.08188","title":"Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.14581","title":"A Picture is Worth a Thousand Words? An Empirical Study of Aggregation Strategies for Visual Financial Document Retrieval","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.14787","title":"Do Composed Image Retrieval Benchmarks Require Multimodal Composition?","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15868","title":"SOLAR: Self-supervised Joint Learning for Symmetric Multimodal Retrieval","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.18434","title":"TIGER-FG: Text-Guided Implicit Fine-Grained Grounding for E-commerce Retrieval","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.18547","title":"VISAFF: Speaker-Centered Visual Affective Feature Learning for Emotion Recognition in Conversation","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.20731","title":"TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.27931","title":"DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.28822","title":"Lightweight Multimodal LLM-Enabled Cost-Effective Defect Grading of Power Transmission Equipment","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2605.29287","title":"UniNote: A Unified Embedding Model for Multimodal Representation and Ranking","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.29765","title":"MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2605.30131","title":"CCS: Clinical Consensus Selection for Radiology Report Generation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.03635","title":"VidMsg: A Benchmark for Implicit Message Inference in Short Videos","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.09331","title":"Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.14747","title":"MMLongEmbed: Benchmarking Multimodal Embedding Models in Long-Context Scenarios","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.05927","title":"CMDR: Contextual Multimodal Document Retrieval","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.09428","title":"Multimodal Scenario Similarity Search for Autonomous Driving","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.11798","title":"StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.14631","title":"Knowing You at First Glance: Inferring Apparent Personality from Faces","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.25041","title":"ScoreShield: Differentially Private Release of Similarity Scores","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.28751","title":"ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.01389","title":"KoVRE: Training an Efficient Embedding Model for Korean Visual Document Retrieval","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.03826","title":"Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.04676","title":"SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06972","title":"Generative Embedding Benchmark: How Much Information Survives in a Dense Embedding?","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.10524","title":"Rethinking Text-Based Image Retrieval in Specific Domain","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.10636","title":"DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.12748","title":"Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.13495","title":"TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.14841","title":"What the Reranker Sees: Multi-Aspect Page Annotation for Long-Document Multimodal Question Answering","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.16927","title":"Hierarchical Data Selection via Manifold Coverage and Sparse Feature Coverage in LLM Post-training","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.20840","title":"KoViDoRe: A Benchmark for Korean Visual Document Retrieval","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.25412","title":"AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal Retrieval","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.26658","title":"PailitaoGR: Latent Think-with-Images for Generative Image Retrieval","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.30709","title":"RailSyn: Diagnosis-Guided Image Generation for Traceable Data Completion in Railway Foreign Object Detection","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2608.31005","title":"From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.08850","title":"DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.10008","title":"Beyond Similarity: Foundation Models as an Efficient Backbone for Training-Free Composed Video Retrieval","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.11373","title":"Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.18521","title":"VoiceTrace: A Benchmark and Retrieval Framework for Who-Said-What Speech Retrieval","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20508","title":"Grounded Product Understanding in Livestream Videos","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21018","title":"MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.25165","title":"Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.25738","title":"OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.26182","title":"Modality-Gated Deep Adapters: Adding a Modality to a Frozen Embedding Model with Exact Preservation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.28086","title":"LAYERSCOPE: A Layerwise Characterization of Video and Multimodal Learned Representations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.28437","title":"MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29560","title":"Is Reasoning Always Useful? Rethinking Reasoning Utility in Universal Multimodal Embeddings","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.31714","title":"OmniFysics-Captioner Technical Report: Grounding Omni-Modal Understanding in the Physical World for Better Captioning","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.36190","title":"FigAct: Turning Scientific Figures into Active Canvases for Explanation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.00973","title":"Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01389","title":"AiSearch: Interactive Multi-Modal Search with VLMs","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02148","title":"Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05852","title":"RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.05896","title":"TasteRoute: Personalized Routing for Video Generation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.09742","title":"SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":"100"}