{"list":"other","total":130,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"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":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"1301.2300","title":"Direct and Indirect Effects","created":"2013-01-10","cited_by_count":280},{"id":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196},{"id":"1802.08129","title":"Multimodal Explanations: Justifying Decisions and Pointing to the Evidence","created":"2018-02-15","cited_by_count":179},{"id":"2306.08877","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","created":"2023-06-15","cited_by_count":171},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"2311.12092","title":"Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models","created":"2023-11-20","cited_by_count":153},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147},{"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":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126},{"id":"2004.11207","title":"Self-Attention Attribution: Interpreting Information Interactions Inside Transformer","created":"2020-04-23","cited_by_count":125},{"id":"1812.09355","title":"What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models","created":"2018-12-21","cited_by_count":124},{"id":"2310.00902","title":"DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models","created":"2023-10-02","cited_by_count":123},{"id":"1909.07913","title":"Learning to Deceive with Attention-Based Explanations","created":"2019-09-17","cited_by_count":111},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108},{"id":"2010.02695","title":"Analyzing Individual Neurons in Pre-trained Language Models","created":"2020-10-06","cited_by_count":97},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91},{"id":"2402.17811","title":"TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space","created":"2024-02-27","cited_by_count":91},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88},{"id":"2405.08366","title":"Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control","created":"2024-05-14","cited_by_count":86},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81},{"id":"2307.09476","title":"Overthinking the Truth: Understanding how Language Models Process False Demonstrations","created":"2023-07-18","cited_by_count":81},{"id":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80},{"id":"2402.17700","title":"RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations","created":"2024-02-27","cited_by_count":79},{"id":"2402.00357","title":"Safety of Multimodal Large Language Models on Images and Texts","created":"2024-02-01","cited_by_count":75},{"id":"1909.11218","title":"Attention Interpretability Across NLP Tasks","created":"2019-09-24","cited_by_count":71},{"id":"2412.05276","title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation","created":"2024-12-06","cited_by_count":68},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62},{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62},{"id":"2404.15736","title":"What Makes Multimodal In-Context Learning Work?","created":"2024-04-24","cited_by_count":56},{"id":"2310.13730","title":"Localizing and Editing Knowledge in Text-to-Image Generative Models","created":"2023-10-20","cited_by_count":54},{"id":"2403.07809","title":"pyvene: A Library for Understanding and Improving PyTorch Models via Interventions","created":"2024-03-12","cited_by_count":54},{"id":"2203.17247","title":"VL-InterpreT: An Interactive Visualization Tool for Interpreting Vision-Language Transformers","created":"2022-03-30","cited_by_count":53},{"id":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48},{"id":"2311.00500","title":"Intriguing Properties of Data Attribution on Diffusion Models","created":"2023-11-01","cited_by_count":47},{"id":"2010.02812","title":"Intrinsic Probing through Dimension Selection","created":"2020-10-06","cited_by_count":45},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45},{"id":"2405.00740","title":"Modeling Caption Diversity in Contrastive Vision-Language Pretraining","created":"2024-04-30","cited_by_count":42},{"id":"2403.17064","title":"Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions","created":"2024-03-25","cited_by_count":41},{"id":"2310.00108","title":"Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study","created":"2023-09-29","cited_by_count":38},{"id":"2406.02366","title":"Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models","created":"2024-06-04","cited_by_count":37},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","cited_by_count":36},{"id":"2203.02013","title":"DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations","created":"2022-03-03","cited_by_count":34},{"id":"1910.05276","title":"exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models","created":"2019-10-11","cited_by_count":33},{"id":"2410.13850","title":"Influence Functions for Scalable Data Attribution in Diffusion Models","created":"2024-10-17","cited_by_count":33}],"next_cursor":"100"}