{"list":"other","total":71,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"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":"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":"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":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"1906.07337","title":"Measuring Bias in Contextualized Word Representations","created":"2019-06-18","cited_by_count":276},{"id":"1601.03764","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","created":"2016-01-14","cited_by_count":165},{"id":"2302.00070","title":"Debiasing Vision-Language Models via Biased Prompts","created":"2023-01-31","cited_by_count":149},{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143},{"id":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122},{"id":"2203.11933","title":"A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning","created":"2022-03-22","cited_by_count":104},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104},{"id":"2005.07310","title":"Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models","created":"2020-05-15","cited_by_count":90},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90},{"id":"1908.04913","title":"FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age","created":"2019-08-14","cited_by_count":87},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71},{"id":"2303.10431","title":"DeAR: Debiasing Vision-Language Models with Additive Residuals","created":"2023-03-18","cited_by_count":70},{"id":"2411.18620","title":"Cross-modal Information Flow in Multimodal Large Language Models","created":"2024-11-27","cited_by_count":67},{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62},{"id":"2304.02828","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","created":"2023-04-06","cited_by_count":52},{"id":"2006.08315","title":"Mitigating Gender Bias in Captioning Systems","created":"2020-06-15","cited_by_count":50},{"id":"2105.02317","title":"A Step Toward More Inclusive People Annotations for Fairness","created":"2021-05-05","cited_by_count":46},{"id":"2410.22366","title":"One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models","created":"2024-10-28","cited_by_count":33},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30},{"id":"2405.20152","title":"Uncovering Bias in Large Vision-Language Models at Scale with Counterfactuals","created":"2024-05-30","cited_by_count":28},{"id":"2411.00997","title":"Identifying Implicit Social Biases in Vision-Language Models","created":"2024-11-01","cited_by_count":27},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26},{"id":"2503.20483","title":"Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability","created":"2025-03-26","cited_by_count":26},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25},{"id":"2410.06967","title":"$\\texttt{ModSCAN}$: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities","created":"2024-10-09","cited_by_count":22},{"id":"2411.19187","title":"Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs","created":"2024-11-28","cited_by_count":22},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20},{"id":"2408.10202","title":"SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP","created":"2024-08-19","cited_by_count":19},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19},{"id":"2410.07593","title":"A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks","created":"2024-10-10","cited_by_count":18},{"id":"2411.12785","title":"Joint Vision-Language Social Bias Removal for CLIP","created":"2024-11-19","cited_by_count":18},{"id":"2411.04420","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","created":"2024-11-07","cited_by_count":17},{"id":"2410.19314","title":"Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)","created":"2024-10-25","cited_by_count":15},{"id":"2407.02814","title":"Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective","created":"2024-07-03","cited_by_count":13},{"id":"2412.14384","title":"I0T: Embedding Standardization Method Towards Zero Modality Gap","created":"2024-12-18","cited_by_count":8},{"id":"2503.09446","title":"Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models","created":"2025-03-12","cited_by_count":8},{"id":"2410.04819","title":"MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models","created":"2024-10-07","cited_by_count":7},{"id":"2504.01589","title":"Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models","created":"2025-04-02","cited_by_count":5},{"id":"2502.14888","title":"Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models","created":"2025-02-16","cited_by_count":4},{"id":"2508.02241","title":"Isolating Culture Neurons in Multilingual Large Language Models","created":"2025-08-04","cited_by_count":4},{"id":"2509.17401","title":"Interpreting vision transformers via residual replacement model","created":"2025-09-22","cited_by_count":4},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3},{"id":"2503.13369","title":"Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram Descriptions","created":"2025-03-17","cited_by_count":3},{"id":"2503.16826","title":"When Tom Eats Kimchi: Evaluating Cultural Bias of Multimodal Large Language Models in Cultural Mixture Contexts","created":"2025-03-21","cited_by_count":3},{"id":"2507.20973","title":"Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder","created":"2025-07-28","cited_by_count":3},{"id":"2508.07111","title":"Investigating Intersectional Bias in Large Language Models using Confidence Disparities in Coreference Resolution","created":"2025-08-09","cited_by_count":3},{"id":"2510.00766","title":"Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?","created":"2025-10-01","cited_by_count":1},{"id":"2512.04981","title":"Aligned but Stereotypical? How System Prompts Shape Demographic Bias in LLM-Based Text-to-Image Models","created":"2025-12-04","cited_by_count":1}],"next_cursor":null}