{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"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":"2407.15754","title":"LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding","created":"2024-07-22","cited_by_count":665},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"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":"2508.15487","title":"Dream 7B: Diffusion Large Language Models","created":"2025-08-21","cited_by_count":544},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2505.22618","title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding","created":"2025-05-28","cited_by_count":420},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2501.13826","title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","created":"2025-01-23","cited_by_count":236},{"id":"2210.17432","title":"SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control","created":"2022-10-31","cited_by_count":194},{"id":"2512.15745","title":"LLaDA2.0: Scaling Up Diffusion Language Models to 100B","created":"2025-12-10","cited_by_count":166},{"id":"2505.16933","title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","created":"2025-05-22","cited_by_count":148},{"id":"2404.01258","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","created":"2024-04-01","cited_by_count":147},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127},{"id":"2402.03620","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","created":"2024-02-06","cited_by_count":110},{"id":"2410.05643","title":"TRACE: Temporal Grounding Video LLM via Causal Event Modeling","created":"2024-10-08","cited_by_count":89},{"id":"2510.06308","title":"Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding","created":"2025-10-07","cited_by_count":88},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"2309.00398","title":"VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation","created":"2023-09-01","cited_by_count":74},{"id":"2509.24389","title":"LLaDA-MoE: A Sparse MoE Diffusion Language Model","created":"2025-09-29","cited_by_count":57},{"id":"2406.19392","title":"ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos","created":"2024-06-27","cited_by_count":51},{"id":"2409.17647","title":"MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning","created":"2024-09-26","cited_by_count":23},{"id":"2510.08510","title":"To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models","created":"2025-10-09","cited_by_count":20},{"id":"2512.22615","title":"Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone","created":"2025-12-27","cited_by_count":18},{"id":"2408.07728","title":"Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies","created":"2024-08-14","cited_by_count":15},{"id":"2510.06133","title":"CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit","created":"2025-10-07","cited_by_count":13},{"id":"2512.14068","title":"SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding","created":"2025-12-16","cited_by_count":13},{"id":"2510.11538","title":"Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers","created":"2025-10-13","cited_by_count":7},{"id":"2601.07290","title":"VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding","created":"2026-01-12","cited_by_count":5}],"next_cursor":null}