{"total":50,"rows":[{"id":"2509.06945","title":"Interleaving Reasoning for Better Text-to-Image Generation","created":"2025-09-08","cited_by_count":41,"area":null},{"id":"2503.08506","title":"ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews","created":"2025-03-11","cited_by_count":32,"area":null},{"id":"2502.13449","title":"Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2505.16836","title":"Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning","created":"2025-05-22","cited_by_count":14,"area":null},{"id":"2504.13275","title":"ChartQA-X: Generating Explanations for Visual Chart Reasoning","created":"2025-04-17","cited_by_count":10,"area":null},{"id":"2505.20873","title":"Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2509.19090","title":"Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoning","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2510.18214","title":"VLSU: Mapping the Limits of Joint Multimodal Understanding for AI Safety","created":"2025-10-21","cited_by_count":8,"area":null},{"id":"2604.02097","title":"LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model","created":"2026-04-02","cited_by_count":8,"area":null},{"id":"2503.02341","title":"GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2503.08549","title":"GoAI: Enhancing AI Students' Learning Paths and Idea Generation via Graph of AI Ideas","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2510.23727","title":"MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2502.15412","title":"Textual-to-Visual Iterative Self-Verification for Slide Generation","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2605.10761","title":"RadThinking: A Dataset for Longitudinal Clinical Reasoning in Radiology","created":"2026-05-11","cited_by_count":4,"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":"2602.17478","title":"QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2503.15807","title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2507.11099","title":"A Survey on Interpretability in Visual Recognition","created":"2025-07-15","cited_by_count":2,"area":null},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2511.02495","title":"DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2601.17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2603.21573","title":"Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs","created":"2026-03-23","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":"2603.06561","title":"EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured Thinking","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.17554","title":"Prompt-Free Universal Region Proposal Network","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.25326","title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2505.01450","title":"Towards Film-Making Production Dialogue, Narration, Monologue Adaptive Moving Dubbing Benchmarks","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.16279","title":"MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2505.18614","title":"MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2505.20038","title":"Towards Video to Piano Music Generation with Chain-of-Perform Support Benchmarks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2510.02922","title":"Multimodal Carotid Risk Stratification with Large Vision-Language Models: Benchmarking, Fine-Tuning, and Clinical Insights","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2601.01910","title":"MMP-A*: Multimodal Perception Enhanced Incremental Heuristic Search on Path Planning","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2603.07961","title":"SGG-R$^{\\rm 3}$: From Next-Token Prediction to End-to-End Unbiased Scene Graph Generation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.20354","title":"Leum-VL Technical Report","created":"2026-03-20","cited_by_count":0,"area":null},{"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":"2604.15210","title":"Learning to Think Like a Cartoon Captionist: Incongruity-Resolution Supervision for Multimodal Humor Understanding","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.09492","title":"APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.28604","title":"Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.25034","title":"Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.16259","title":"Defake-o3: From Speculative Rationales to Verifiable Evidence for Explainable AIGI Detection","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":"2608.21357","title":"VIALS: A Benchmark for Visual Interpretation of Artifacts in the Life Sciences","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.03206","title":"Learning to Zoom Efficiently with a Contrastive Curriculum","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.12202","title":"QuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterization","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2610.16452","title":"Not Every Cue Is Evidence: Cue Supportability for Forensic Distillation in Face Forgery Detection","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.16811","title":"X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}