{"total":50,"rows":[{"id":"2405.12819","title":"Large Language Models Meet NLP: A Survey","created":"2024-05-21","cited_by_count":103,"area":null},{"id":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"area":null},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2412.15678","title":"Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2503.12560","title":"Multi-Granular Multimodal Clue Fusion for Meme Understanding","created":"2025-03-16","cited_by_count":14,"area":null},{"id":"2504.02454","title":"Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation","created":"2025-04-03","cited_by_count":14,"area":null},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13,"area":null},{"id":"2503.07635","title":"Cross-modal Causal Relation Alignment for Video Question Grounding","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2412.02402","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2503.15005","title":"Universal Scene Graph Generation","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2508.09486","title":"Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2506.17633","title":"Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection","created":"2025-06-21","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":"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":"2502.19868","title":"C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2503.15019","title":"Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2501.14194","title":"ENTER: Event Based Interpretable Reasoning for VideoQA","created":"2025-01-24","cited_by_count":5,"area":null},{"id":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","cited_by_count":5,"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":"2503.13707","title":"Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2504.02227","title":"VEGAS: Towards Visually Explainable and Grounded Artificial Social Intelligence","created":"2025-04-03","cited_by_count":4,"area":null},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2511.10953","title":"Language-Guided Graph Representation Learning for Video Summarization","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2603.06213","title":"Cut to the Chase: Training-free Multimodal Summarization via Chain-of-Events","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2603.25423","title":"From Manipulation to Mistrust: Explaining Diverse Micro-Video Misinformation for Robust Debunking in the Wild","created":"2026-03-26","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":"2507.03038","title":"Cautious Next Token Prediction","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2410.15312","title":"Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2508.17932","title":"See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2508.19024","title":"ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.24445","title":"Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2512.22603","title":"Structured Prompting and LLM Ensembling for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2025-12-27","cited_by_count":1,"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":"2603.23902","title":"Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.14692","title":"Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2608.08820","title":"LogiShot: Logically Coherent Cross-Shot Video Generation","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2609.15128","title":"Omni-Streaming Thinking","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2504.05463","title":"REVEAL: Relation-based Video Representation Learning for Video-Question-Answering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2601.04563","title":"A Vision for Multisensory Intelligence: Sensing, Science, and Synergy","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2606.02724","title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.09181","title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.15570","title":"An Extensive Benchmark for Single-round and Multi-round Instruction-based Image Editing","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2608.05825","title":"MoCA: Implicit Social Context Analysis","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.13794","title":"SyRHM: Symbolic-Language-Enhanced Reasoning with Associative Retrieval for Zero-shot Harmful Meme Detection","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}