{"list":"other","total":77,"rows":[{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"1809.02156","title":"Object Hallucination in Image Captioning","created":"2018-09-06","cited_by_count":669},{"id":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"1704.04497","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","created":"2017-04-14","cited_by_count":378},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363},{"id":"1712.00377","title":"Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering","created":"2017-12-01","cited_by_count":339},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2006.04315","title":"Counterfactual VQA: A Cause-Effect Look at Language Bias","created":"2020-06-08","cited_by_count":266},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2502.08177","title":"SycEval: Evaluating LLM Sycophancy","created":"2025-02-12","cited_by_count":108},{"id":"1810.03649","title":"Overcoming Language Priors in Visual Question Answering with Adversarial Regularization","created":"2018-10-08","cited_by_count":105},{"id":"2505.23840","title":"Measuring Sycophancy of Language Models in Multi-turn Dialogues","created":"2025-05-28","cited_by_count":104},{"id":"2411.15287","title":"Sycophancy in Large Language Models: Causes and Mitigations","created":"2024-11-22","cited_by_count":101},{"id":"1705.01359","title":"FOIL it! Find One mismatch between Image and Language caption","created":"2017-05-03","cited_by_count":95},{"id":"2406.16338","title":"VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models","created":"2024-06-24","cited_by_count":90},{"id":"1802.08195","title":"Adversarial Examples that Fool both Computer Vision and Time-Limited Humans","created":"2018-02-22","cited_by_count":73},{"id":"2501.02955","title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","created":"2025-01-06","cited_by_count":70},{"id":"2412.03735","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","created":"2024-12-04","cited_by_count":68},{"id":"2505.23941","title":"Vision Language Models are Biased","created":"2025-05-29","cited_by_count":66},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57},{"id":"2409.16597","title":"EventHallusion: Diagnosing Event Hallucinations in Video LLMs","created":"2024-09-25","cited_by_count":57},{"id":"2405.17820","title":"Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models","created":"2024-05-28","cited_by_count":47},{"id":"2406.08702","title":"VLind-Bench: Measuring Language Priors in Large Vision-Language Models","created":"2024-06-13","cited_by_count":45},{"id":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42},{"id":"2410.02763","title":"Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos","created":"2024-10-03","cited_by_count":38},{"id":"2002.05123","title":"Over-the-Air Adversarial Flickering Attacks against Video Recognition Networks","created":"2020-02-12","cited_by_count":36},{"id":"2503.11656","title":"TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Models","created":"2025-02-04","cited_by_count":33},{"id":"2505.01481","title":"VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding","created":"2025-05-02","cited_by_count":32},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30},{"id":"2012.10210","title":"On Modality Bias in the TVQA Dataset","created":"2020-12-18","cited_by_count":24},{"id":"2408.12763","title":"Assessing Modality Bias in Video Question Answering Benchmarks with Multimodal Large Language Models","created":"2024-08-22","cited_by_count":23},{"id":"2505.14640","title":"VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation","created":"2025-05-20","cited_by_count":21},{"id":"2506.07180","title":"Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs","created":"2025-06-08","cited_by_count":21},{"id":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19},{"id":"2411.12951","title":"On the Consistency of Video Large Language Models in Temporal Comprehension","created":"2024-11-20","cited_by_count":18},{"id":"1912.04538","title":"Appending Adversarial Frames for Universal Video Attack","created":"2019-12-10","cited_by_count":17},{"id":"2110.15629","title":"Attacking Video Recognition Models with Bullet-Screen Comments","created":"2021-10-29","cited_by_count":16},{"id":"2503.07298","title":"ALLVB: All-in-One Long Video Understanding Benchmark","created":"2025-03-10","cited_by_count":16},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16},{"id":"2410.11302","title":"Have the VLMs Lost Confidence? A Study of Sycophancy in VLMs","created":"2024-10-15","cited_by_count":15},{"id":"2410.14248","title":"Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models","created":"2024-10-18","cited_by_count":11},{"id":"2503.18923","title":"Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models","created":"2025-03-24","cited_by_count":11},{"id":"2504.03970","title":"VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models","created":"2025-04-04","cited_by_count":11},{"id":"2505.21472","title":"Mitigating Hallucination in Large Vision-Language Models via Adaptive Attention Calibration","created":"2025-05-27","cited_by_count":11},{"id":"2508.21496","title":"ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding","created":"2025-08-29","cited_by_count":10},{"id":"2412.05725","title":"Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events","created":"2024-12-07","cited_by_count":9},{"id":"2509.20146","title":"EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models","created":"2025-09-24","cited_by_count":9},{"id":"2506.10297","title":"\"Check My Work?\": Measuring Sycophancy in a Simulated Educational Context","created":"2025-06-12","cited_by_count":7},{"id":"2508.19650","title":"Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models","created":"2025-08-27","cited_by_count":6},{"id":"2304.01441","title":"NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression","created":"2023-04-04","cited_by_count":2},{"id":"2504.06580","title":"Exploring Ordinal Bias in Action Recognition for Instructional Videos","created":"2025-04-09","cited_by_count":1},{"id":"2505.19125","title":"RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models","created":"2025-05-25","cited_by_count":1}],"next_cursor":null}