{"list":"other","total":88,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"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":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"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":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"1910.10699","title":"Contrastive Representation Distillation","created":"2019-10-23","cited_by_count":748},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2305.07895","title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","created":"2023-05-13","cited_by_count":476},{"id":"2003.10286","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","created":"2020-03-07","cited_by_count":475},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2310.14152","title":"Orthogonal Subspace Learning for Language Model Continual Learning","created":"2023-10-22","cited_by_count":312},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291},{"id":"2410.10594","title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","created":"2024-10-14","cited_by_count":245},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2003.07333","title":"RSVQA: Visual Question Answering for Remote Sensing Data","created":"2020-03-16","cited_by_count":203},{"id":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197},{"id":"2404.16006","title":"MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGI","created":"2024-04-24","cited_by_count":193},{"id":"2002.00718","title":"Modeling the Background for Incremental Learning in Semantic Segmentation","created":"2020-02-03","cited_by_count":190},{"id":"2011.11390","title":"PLOP: Learning without Forgetting for Continual Semantic Segmentation","created":"2020-11-23","cited_by_count":177},{"id":"1810.12440","title":"TallyQA: Answering Complex Counting Questions","created":"2018-10-29","cited_by_count":153},{"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":"2404.03384","title":"LongVLM: Efficient Long Video Understanding via Large Language Models","created":"2024-04-04","cited_by_count":147},{"id":"2304.13731","title":"Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model","created":"2023-04-24","cited_by_count":145},{"id":"2406.17294","title":"Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models","created":"2024-06-25","cited_by_count":133},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119},{"id":"2407.08739","title":"MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine","created":"2024-07-11","cited_by_count":113},{"id":"2312.14074","title":"LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding","created":"2023-12-21","cited_by_count":95},{"id":"1910.03723","title":"Knowledge Distillation from Internal Representations","created":"2019-10-08","cited_by_count":87},{"id":"2206.06888","title":"CERT: Continual Pre-Training on Sketches for Library-Oriented Code Generation","created":"2022-06-14","cited_by_count":87},{"id":"2211.08545","title":"MapQA: A Dataset for Question Answering on Choropleth Maps","created":"2022-11-15","cited_by_count":85},{"id":"2205.09357","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","created":"2022-05-19","cited_by_count":83},{"id":"2209.08199","title":"ScreenQA: Large-Scale Question-Answer Pairs over Mobile App Screenshots","created":"2022-09-16","cited_by_count":66},{"id":"2504.09795","title":"VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documents","created":"2025-04-14","cited_by_count":59},{"id":"2108.03267","title":"BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation","created":"2021-08-06","cited_by_count":31},{"id":"2503.12941","title":"HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model","created":"2025-03-17","cited_by_count":31},{"id":"2311.15206","title":"Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding","created":"2023-11-26","cited_by_count":29},{"id":"1810.10612","title":"Continual Classification Learning Using Generative Models","created":"2018-10-24","cited_by_count":28},{"id":"2304.02135","title":"FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding","created":"2023-04-04","cited_by_count":27},{"id":"2203.08512","title":"ConTinTin: Continual Learning from Task Instructions","created":"2022-03-16","cited_by_count":26},{"id":"2203.07667","title":"SATS: Self-Attention Transfer for Continual Semantic Segmentation","created":"2022-03-15","cited_by_count":25},{"id":"2305.05010","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","created":"2023-05-08","cited_by_count":25},{"id":"2402.03327","title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","created":"2024-01-09","cited_by_count":25},{"id":"2212.09710","title":"Continual Learning for Instruction Following from Realtime Feedback","created":"2022-12-19","cited_by_count":22},{"id":"2503.10627","title":"SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems","created":"2025-03-13","cited_by_count":22},{"id":"2510.15103","title":"Continual Learning via Sparse Memory Finetuning","created":"2025-10-16","cited_by_count":20},{"id":"2410.07739","title":"SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture","created":"2024-10-10","cited_by_count":19},{"id":"2411.18042","title":"HyperGLM: HyperGraph for Video Scene Graph Generation and Anticipation","created":"2024-11-27","cited_by_count":19},{"id":"2305.15700","title":"Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments","created":"2023-05-25","cited_by_count":16},{"id":"2311.15965","title":"FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding","created":"2023-11-27","cited_by_count":13},{"id":"2501.16497","title":"Smoothed Embeddings for Robust Language Models","created":"2025-01-27","cited_by_count":8},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7},{"id":"2502.09906","title":"Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding","created":"2025-02-14","cited_by_count":7},{"id":"2406.01429","title":"EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding","created":"2024-06-03","cited_by_count":6},{"id":"2507.15882","title":"Document Haystack: A Long Context Multimodal Image/Document Understanding Vision LLM Benchmark","created":"2025-07-18","cited_by_count":6},{"id":"2004.13135","title":"Local Lipschitz Bounds of Deep Neural Networks","created":"2020-04-27","cited_by_count":5},{"id":"2508.14264","title":"Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models","created":"2025-08-19","cited_by_count":5},{"id":"2502.17920","title":"C-LoRA: Continual Low-Rank Adaptation for Pre-trained Visual Models","created":"2025-02-25","cited_by_count":3},{"id":"2508.10133","title":"MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning","created":"2025-08-13","cited_by_count":3},{"id":"2405.09820","title":"Densely Distilling Cumulative Knowledge for Continual Learning","created":"2024-05-16","cited_by_count":1},{"id":"2505.24649","title":"BIMA: Bijective Maximum Likelihood Learning Approach to Hallucination Prediction and Mitigation in Large Vision-Language Models","created":"2025-05-30","cited_by_count":1},{"id":"2508.09170","title":"Multimodal RAG Enhanced Visual Description","created":"2025-08-06","cited_by_count":1}],"next_cursor":null}