{"list":"other","total":69,"rows":[{"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":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1506.03340","title":"Teaching Machines to Read and Comprehend","created":"2015-06-10","cited_by_count":1049},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"1511.06349","title":"Generating Sentences from a Continuous Space","created":"2015-11-19","cited_by_count":612},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"1602.02068","title":"From Softmax to Sparsemax: A Sparse Model of Attention and Multi-Label Classification","created":"2016-02-05","cited_by_count":341},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"1907.04907","title":"Topic Modeling in Embedding Spaces","created":"2019-07-08","cited_by_count":224},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"1703.01488","title":"Autoencoding Variational Inference For Topic Models","created":"2017-03-04","cited_by_count":169},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2008.09470","title":"Top2Vec: Distributed Representations of Topics","created":"2020-08-19","cited_by_count":126},{"id":"2503.09532","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","created":"2025-03-12","cited_by_count":124},{"id":"2004.03974","title":"Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence","created":"2020-04-08","cited_by_count":121},{"id":"1511.06038","title":"Neural Variational Inference for Text Processing","created":"2015-11-19","cited_by_count":111},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91},{"id":"1706.00359","title":"Discovering Discrete Latent Topics with Neural Variational Inference","created":"2017-06-01","cited_by_count":79},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75},{"id":"2107.02173","title":"Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence","created":"2021-07-05","cited_by_count":74},{"id":"2004.14914","title":"Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too!","created":"2020-04-30","cited_by_count":73},{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73},{"id":"2404.07204","title":"BRAVE: Broadening the visual encoding of vision-language models","created":"2024-04-10","cited_by_count":69},{"id":"2004.07737","title":"Cross-lingual Contextualized Topic Models with Zero-shot Learning","created":"2020-04-16","cited_by_count":67},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61},{"id":"1907.12374","title":"Topic Modeling with Wasserstein Autoencoders","created":"2019-07-24","cited_by_count":53},{"id":"2304.02828","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","created":"2023-04-06","cited_by_count":52},{"id":"2008.13537","title":"Neural Topic Model via Optimal Transport","created":"2020-08-12","cited_by_count":50},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49},{"id":"2110.12764","title":"Contrastive Learning for Neural Topic Model","created":"2021-10-25","cited_by_count":48},{"id":"2412.03561","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","created":"2024-12-04","cited_by_count":48},{"id":"1705.09296","title":"Neural Models for Documents with Metadata","created":"2017-05-25","cited_by_count":46},{"id":"2306.04217","title":"Effective Neural Topic Modeling with Embedding Clustering Regularization","created":"2023-06-07","cited_by_count":46},{"id":"2410.14670","title":"Decomposing The Dark Matter of Sparse Autoencoders","created":"2024-10-18","cited_by_count":45},{"id":"2010.12626","title":"Topic Modeling with Contextualized Word Representation Clusters","created":"2020-10-23","cited_by_count":41},{"id":"2211.12878","title":"Mitigating Data Sparsity for Short Text Topic Modeling by Topic-Semantic Contrastive Learning","created":"2022-11-23","cited_by_count":38},{"id":"2203.01570","title":"Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings","created":"2022-03-03","cited_by_count":36},{"id":"2204.09874","title":"Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics","created":"2022-04-21","cited_by_count":35},{"id":"2405.17978","title":"FASTopic: Pretrained Transformer is a Fast, Adaptive, Stable, and Transferable Topic Model","created":"2024-05-28","cited_by_count":35},{"id":"1803.01328","title":"WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling","created":"2018-03-04","cited_by_count":32},{"id":"2309.06908","title":"Towards the TopMost: A Topic Modeling System Toolkit","created":"2023-09-13","cited_by_count":21},{"id":"2305.14587","title":"Contextualized Topic Coherence Metrics","created":"2023-05-23","cited_by_count":19},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19},{"id":"2401.15351","title":"A Survey on Neural Topic Models: Methods, Applications, and Challenges","created":"2024-01-27","cited_by_count":18},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16},{"id":"2506.01197","title":"Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures","created":"2025-06-01","cited_by_count":14},{"id":"1810.09079","title":"Sparsemax and Relaxed Wasserstein for Topic Sparsity","created":"2018-10-22","cited_by_count":9},{"id":"2412.06244","title":"Unbiased Region-Language Alignment for Open-Vocabulary Dense Prediction","created":"2024-12-09","cited_by_count":9},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8},{"id":"2502.18326","title":"Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks","created":"2025-02-17","cited_by_count":7},{"id":"2510.26186","title":"ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts","created":"2025-10-30","cited_by_count":5},{"id":"2509.11465","title":"CEMTM: Contextual Embedding-based Multimodal Topic Modeling","created":"2025-09-14","cited_by_count":4},{"id":"2509.17401","title":"Interpreting vision transformers via residual replacement model","created":"2025-09-22","cited_by_count":4},{"id":"2410.12379","title":"Stylistic Multi-Task Analysis of Ukiyo-e Woodblock Prints","created":"2024-10-16","cited_by_count":2}],"next_cursor":null}