{"total":84,"rows":[{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747,"area":"moe"},{"id":"2404.02258","title":"Mixture-of-Depths: Dynamically allocating compute in transformer-based language models","created":"2024-04-02","cited_by_count":258,"area":null},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179,"area":"mechinterp"},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"area":"moe"},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72,"area":"moe"},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66,"area":"diffusion"},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"area":null},{"id":"2107.11817","title":"Go Wider Instead of Deeper","created":"2021-07-25","cited_by_count":57,"area":"moe"},{"id":"2408.14690","title":"Training-Free Activation Sparsity in Large Language Models","created":"2024-08-26","cited_by_count":55,"area":"inference"},{"id":"2106.10715","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","created":"2021-06-20","cited_by_count":52,"area":null},{"id":"2407.12861","title":"CiteME: Can Language Models Accurately Cite Scientific Claims?","created":"2024-07-10","cited_by_count":48,"area":null},{"id":"2305.18378","title":"Disentanglement via Latent Quantization","created":"2023-05-28","cited_by_count":40,"area":null},{"id":"2406.05955","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","created":"2024-06-10","cited_by_count":38,"area":"moe"},{"id":"2206.02713","title":"Is a Modular Architecture Enough?","created":"2022-06-06","cited_by_count":36,"area":null},{"id":"2108.07668","title":"Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation","created":"2021-08-17","cited_by_count":35,"area":null},{"id":"2309.13850","title":"Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts","created":"2023-09-25","cited_by_count":29,"area":"moe"},{"id":"2407.19985","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","created":"2024-07-29","cited_by_count":25,"area":"moe"},{"id":"2402.02526","title":"CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition","created":"2024-02-04","cited_by_count":23,"area":"moe"},{"id":"2109.12520","title":"Entity Linking Meets Deep Learning: Techniques and Solutions","created":"2021-09-26","cited_by_count":22,"area":null},{"id":"2407.13460","title":"SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders","created":"2024-07-18","cited_by_count":19,"area":null},{"id":"2305.07572","title":"Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts","created":"2023-05-12","cited_by_count":17,"area":"moe"},{"id":"2405.06394","title":"Memory Mosaics","created":"2024-05-10","cited_by_count":16,"area":null},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16,"area":"mechinterp"},{"id":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2404.10282","title":"Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning","created":"2024-04-16","cited_by_count":13,"area":null},{"id":"2504.11609","title":"Towards Interpretable Deep Generative Models via Causal Representation Learning","created":"2025-04-15","cited_by_count":13,"area":null},{"id":"2102.05185","title":"Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement","created":"2021-02-09","cited_by_count":12,"area":null},{"id":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2506.16506","title":"Subspace-Boosted Model Merging","created":"2025-06-19","cited_by_count":9,"area":null},{"id":"2111.01744","title":"UnProjection: Leveraging Inverse-Projections for Visual Analytics of High-Dimensional Data","created":"2021-11-02","cited_by_count":8,"area":null},{"id":"2209.10080","title":"Deep Double Descent via Smooth Interpolation","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2209.03415","title":"A Survey of Neural Trees","created":"2022-09-07","cited_by_count":7,"area":null},{"id":"2009.10622","title":"Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts","created":"2020-09-22","cited_by_count":6,"area":"moe"},{"id":"2205.05871","title":"Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2303.05161","title":"Inversion dynamics of class manifolds in deep learning reveals tradeoffs underlying generalisation","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2305.01713","title":"Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks","created":"2023-05-02","cited_by_count":6,"area":null},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2402.14230","title":"MerRec: A Large-scale Multipurpose Mercari Dataset for Consumer-to-Consumer Recommendation Systems","created":"2024-02-22","cited_by_count":6,"area":null},{"id":"2210.06230","title":"Quasi-symbolic Semantic Geometry over Transformer-based Variational AutoEncoder","created":"2022-10-12","cited_by_count":5,"area":null},{"id":"2312.16610","title":"Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation","created":"2023-12-27","cited_by_count":5,"area":"moe"},{"id":"2506.03696","title":"Comprehensive Attribute Encoding and Dynamic LSTM HyperModels for Outcome Oriented Predictive Business Process Monitoring","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2507.12990","title":"Teach Old SAEs New Domain Tricks with Boosting","created":"2025-07-17","cited_by_count":5,"area":"mechinterp"},{"id":"2110.03498","title":"On the relationship between disentanglement and multi-task learning","created":"2021-10-07","cited_by_count":4,"area":null},{"id":"2111.14724","title":"Encoding Causal Macrovariables","created":"2021-11-29","cited_by_count":4,"area":null},{"id":"2207.09638","title":"Doge Tickets: Uncovering Domain-general Language Models by Playing Lottery Tickets","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2305.19802","title":"Neuro-Causal Factor Analysis","created":"2023-05-31","cited_by_count":4,"area":null},{"id":"2201.05809","title":"Weighting and Pruning based Ensemble Deep Random Vector Functional Link Network for Tabular Data Classification","created":"2022-01-15","cited_by_count":3,"area":null},{"id":"2104.05171","title":"Deep Recursive Embedding for High-Dimensional Data","created":"2021-04-12","cited_by_count":2,"area":null},{"id":"2109.03615","title":"Tactile Image-to-Image Disentanglement of Contact Geometry from Motion-Induced Shear","created":"2021-09-08","cited_by_count":2,"area":null},{"id":"2110.15489","title":"GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL","created":"2021-10-29","cited_by_count":2,"area":null},{"id":"2206.05810","title":"Analysis of Branch Specialization and its Application in Image Decomposition","created":"2022-06-12","cited_by_count":2,"area":null},{"id":"2304.02335","title":"Correcting Flaws in Common Disentanglement Metrics","created":"2023-04-05","cited_by_count":2,"area":null},{"id":"2410.08003","title":"More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing","created":"2024-10-10","cited_by_count":2,"area":"moe"},{"id":"2410.09094","title":"Reflections on Disentanglement and the Latent Space","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2502.17520","title":"On Neural Inertial Classification Networks for Pedestrian Activity Recognition","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2105.06679","title":"Dynamic Multi-Branch Layers for On-Device Neural Machine Translation","created":"2021-05-14","cited_by_count":1,"area":null},{"id":"2106.03631","title":"Unsupervised Representation Disentanglement of Text: An Evaluation on Synthetic Datasets","created":"2021-06-07","cited_by_count":1,"area":null},{"id":"2210.10920","title":"DOT-VAE: Disentangling One Factor at a Time","created":"2022-10-19","cited_by_count":1,"area":null},{"id":"2306.16029","title":"Lightweight Modeling of User Context Combining Physical and Virtual Sensor Data","created":"2023-06-28","cited_by_count":1,"area":null},{"id":"2407.11514","title":"ColorwAI: Generative Colorways of Textiles through GAN and Diffusion Disentanglement","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2507.04754","title":"Intervening to Learn and Compose Causally Disentangled Representations","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2601.08097","title":"AdaJudge: Adaptive Multi-Perspective Judging for Reward Modeling","created":"2026-01-13","cited_by_count":1,"area":"alignment"},{"id":"2102.04225","title":"Concepts, Properties and an Approach for Compositional Generalization","created":"2021-02-08","cited_by_count":0,"area":null},{"id":"2110.01458","title":"Designing Complex Experiments by Applying Unsupervised Machine Learning","created":"2021-09-29","cited_by_count":0,"area":null},{"id":"2111.00622","title":"Deep Recursive Embedding for High-Dimensional Data","created":"2021-10-31","cited_by_count":0,"area":null},{"id":"2208.12500","title":"Semi-Supervised Disentanglement of Tactile Contact~Geometry from Sliding-Induced Shear","created":"2022-08-26","cited_by_count":0,"area":null},{"id":"2210.07857","title":"Commutativity and Disentanglement from the Manifold Perspective","created":"2022-10-14","cited_by_count":0,"area":null},{"id":"2305.09092","title":"ProtoVAE: Prototypical Networks for Unsupervised Disentanglement","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2402.08345","title":"Conditional Information Gain Trellis","created":"2024-02-13","cited_by_count":0,"area":null},{"id":"2407.01570","title":"Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL","created":"2024-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2409.09169","title":"Curricula for Learning Robust Policies with Factored State Representations in Changing Environments","created":"2024-09-13","cited_by_count":0,"area":"deeprl"},{"id":"2410.09687","title":"MoIN: Mixture of Introvert Experts to Upcycle an LLM","created":"2024-10-13","cited_by_count":0,"area":"moe"},{"id":"2501.08057","title":"Optimizing Speech Multi-View Feature Fusion through Conditional Computation","created":"2025-01-14","cited_by_count":0,"area":null},{"id":"2503.24230","title":"GPU-centric Communication Schemes for HPC and ML Applications","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2505.09366","title":"Personalized Control for Lower Limb Prosthesis Using Kolmogorov-Arnold Networks","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2509.18216","title":"nDNA -- the Semantic Helix of Artificial Cognition","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2510.17383","title":"The Evolving Nature of Latent Spaces: From GANs to Diffusion","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2601.19811","title":"Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts","created":"2026-01-27","cited_by_count":0,"area":"moe"},{"id":"2602.07997","title":"Fast Model Selection and Stable Optimization for Softmax-Gated Multinomial-Logistic Mixture of Experts Models","created":"2026-02-08","cited_by_count":0,"area":"moe"}],"next_cursor":null}