{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"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":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"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":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2403.20330","title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","created":"2024-03-29","cited_by_count":914},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"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":"2402.14804","title":"Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset","created":"2024-02-22","cited_by_count":526},{"id":"1805.01070","title":"What you can cram into a single vector: Probing sentence embeddings for linguistic properties","created":"2018-05-03","cited_by_count":457},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"2502.02013","title":"Layer by Layer: Uncovering Hidden Representations in Language Models","created":"2025-02-04","cited_by_count":311},{"id":"1812.08951","title":"Analysis Methods in Neural Language Processing: A Survey","created":"2018-12-21","cited_by_count":277},{"id":"2410.02355","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","created":"2024-10-03","cited_by_count":236},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200},{"id":"2412.07825","title":"3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark","created":"2024-12-10","cited_by_count":139},{"id":"2402.11004","title":"The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains","created":"2024-02-16","cited_by_count":118},{"id":"2505.21523","title":"More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models","created":"2025-05-23","cited_by_count":86},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72},{"id":"2404.19205","title":"TableVQA-Bench: A Visual Question Answering Benchmark on Multiple Table Domains","created":"2024-04-30","cited_by_count":69},{"id":"2502.14010","title":"Which Attention Heads Matter for In-Context Learning?","created":"2025-02-19","cited_by_count":61},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52},{"id":"2406.04236","title":"Understanding Information Storage and Transfer in Multi-modal Large Language Models","created":"2024-06-06","cited_by_count":49},{"id":"2311.05928","title":"The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models","created":"2023-11-10","cited_by_count":39},{"id":"2511.16518","title":"MiMo-Embodied: X-Embodied Foundation Model Technical Report","created":"2025-11-20","cited_by_count":38},{"id":"2401.17139","title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","created":"2024-01-30","cited_by_count":35},{"id":"2302.00456","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","created":"2023-02-01","cited_by_count":33},{"id":"2504.13169","title":"Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling","created":"2025-04-17","cited_by_count":33},{"id":"2411.06646","title":"Understanding Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data","created":"2024-11-11","cited_by_count":30},{"id":"2501.03225","title":"Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation","created":"2025-01-06","cited_by_count":30},{"id":"2505.18129","title":"One RL to See Them All: Visual Triple Unified Reinforcement Learning","created":"2025-05-23","cited_by_count":30},{"id":"2311.13110","title":"White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?","created":"2023-11-22","cited_by_count":23},{"id":"2509.11986","title":"Lost in Embeddings: Information Loss in Vision-Language Models","created":"2025-09-15","cited_by_count":20},{"id":"2410.17194","title":"Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing","created":"2024-10-22","cited_by_count":19},{"id":"2412.11965","title":"Inferring Functionality of Attention Heads from their Parameters","created":"2024-12-16","cited_by_count":17},{"id":"2510.21518","title":"Head Pursuit: Probing Attention Specialization in Multimodal Transformers","created":"2025-10-24","cited_by_count":17},{"id":"2505.13737","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","created":"2025-05-19","cited_by_count":16},{"id":"2506.08817","title":"Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought","created":"2025-06-10","cited_by_count":14},{"id":"2410.11042","title":"Persistent Topological Features in Large Language Models","created":"2024-10-14","cited_by_count":12},{"id":"2505.15807","title":"The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation","created":"2025-05-21","cited_by_count":11},{"id":"2402.12233","title":"Empirical Study on Updating Key-Value Memories in Transformer Feed-forward Layers","created":"2024-02-19","cited_by_count":8},{"id":"2108.03418","title":"Information Bottleneck Approach to Spatial Attention Learning","created":"2021-08-07","cited_by_count":6},{"id":"2603.14251","title":"Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring","created":"2026-03-15","cited_by_count":6},{"id":"2406.15812","title":"Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations","created":"2024-06-22","cited_by_count":4}],"next_cursor":null}