{"list":"other","total":98,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2302.00093","title":"Large Language Models Can Be Easily Distracted by Irrelevant Context","created":"2023-01-31","cited_by_count":841},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2310.01801","title":"Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs","created":"2023-10-03","cited_by_count":474},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324},{"id":"1503.04069","title":"LSTM: A Search Space Odyssey","created":"2015-03-13","cited_by_count":316},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"1812.05038","title":"Long-Term Feature Banks for Detailed Video Understanding","created":"2018-12-12","cited_by_count":239},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2403.11481","title":"VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding","created":"2024-03-18","cited_by_count":229},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203},{"id":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178},{"id":"2402.14848","title":"Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models","created":"2024-02-19","cited_by_count":152},{"id":"2304.03738","title":"Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models","created":"2023-04-07","cited_by_count":148},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117},{"id":"1805.04623","title":"Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context","created":"2018-05-12","cited_by_count":113},{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111},{"id":"2203.07852","title":"Block-Recurrent Transformers","created":"2022-03-11","cited_by_count":110},{"id":"2101.08833","title":"SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation","created":"2021-01-21","cited_by_count":106},{"id":"1507.05738","title":"Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos","created":"2015-07-21","cited_by_count":93},{"id":"2402.13250","title":"Video ReCap: Recursive Captioning of Hour-Long Videos","created":"2024-02-20","cited_by_count":89},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74},{"id":"2212.14546","title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training","created":"2022-12-30","cited_by_count":72},{"id":"2112.06197","title":"Video as Conditional Graph Hierarchy for Multi-Granular Question Answering","created":"2021-12-12","cited_by_count":68},{"id":"2206.02349","title":"Invariant Grounding for Video Question Answering","created":"2022-06-06","cited_by_count":68},{"id":"2207.05342","title":"Video Graph Transformer for Video Question Answering","created":"2022-07-12","cited_by_count":63},{"id":"1803.01457","title":"Less Is More: Picking Informative Frames for Video Captioning","created":"2018-03-05","cited_by_count":52},{"id":"2310.15747","title":"Large Language Models are Temporal and Causal Reasoners for Video Question Answering","created":"2023-10-24","cited_by_count":51},{"id":"2312.05269","title":"LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos","created":"2023-12-07","cited_by_count":51},{"id":"2402.05861","title":"Memory Consolidation Enables Long-Context Video Understanding","created":"2024-02-08","cited_by_count":45},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40},{"id":"2312.00937","title":"Zero-Shot Video Question Answering with Procedural Programs","created":"2023-12-01","cited_by_count":37},{"id":"1904.02870","title":"Fast Spatio-Temporal Residual Network for Video Super-Resolution","created":"2019-04-05","cited_by_count":34},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34},{"id":"2302.13668","title":"Contrastive Video Question Answering via Video Graph Transformer","created":"2023-02-27","cited_by_count":32},{"id":"1712.01938","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","created":"2017-12-05","cited_by_count":30},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25},{"id":"2301.11507","title":"Semi-Parametric Video-Grounded Text Generation","created":"2023-01-27","cited_by_count":13}],"next_cursor":null}