{"total":80,"rows":[{"id":"2406.02918","title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation","created":"2024-06-05","cited_by_count":179,"area":null},{"id":"2310.11829","title":"Graph Foundation Models: Concepts, Opportunities and Challenges","created":"2023-10-18","cited_by_count":103,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"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,"area":"mechinterp"},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56,"area":null},{"id":"2402.03526","title":"nnMamba: 3D Biomedical Image Segmentation, Classification and Landmark Detection with State Space Model","created":"2024-02-05","cited_by_count":45,"area":null},{"id":"2309.11420","title":"Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models","created":"2023-09-20","cited_by_count":39,"area":"diffusion"},{"id":"2310.12973","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","created":"2023-10-19","cited_by_count":39,"area":null},{"id":"2410.02338","title":"How Much Can RAG Help the Reasoning of LLM?","created":"2024-10-03","cited_by_count":31,"area":"lr"},{"id":"2402.12201","title":"Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT","created":"2024-02-19","cited_by_count":29,"area":"mechinterp"},{"id":"2308.16271","title":"Emergence of Segmentation with Minimalistic White-Box Transformers","created":"2023-08-30","cited_by_count":24,"area":null},{"id":"2508.17689","title":"On the Edge of Memorization in Diffusion Models","created":"2025-08-25","cited_by_count":22,"area":"diffusion"},{"id":"2502.10385","title":"Simplifying DINO via Coding Rate Regularization","created":"2025-02-14","cited_by_count":21,"area":null},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2404.18444","title":"U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models","created":"2024-04-29","cited_by_count":17,"area":"diffusion"},{"id":"2406.01909","title":"A Global Geometric Analysis of Maximal Coding Rate Reduction","created":"2024-06-04","cited_by_count":13,"area":null},{"id":"2403.17409","title":"Neural Clustering based Visual Representation Learning","created":"2024-03-26","cited_by_count":12,"area":null},{"id":"2508.04190","title":"RPCANet++: Deep Interpretable Robust PCA for Sparse Object Segmentation","created":"2025-08-06","cited_by_count":12,"area":null},{"id":"2312.15788","title":"Robust Stochastically-Descending Unrolled Networks","created":"2023-12-25","cited_by_count":9,"area":null},{"id":"2404.02446","title":"Masked Completion via Structured Diffusion with White-Box Transformers","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2405.14736","title":"GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost","created":"2024-05-23","cited_by_count":9,"area":null},{"id":"2405.20299","title":"Scaling White-Box Transformers for Vision","created":"2024-05-30","cited_by_count":9,"area":null},{"id":"2402.02334","title":"Arithmetic Feature Interaction Is Necessary for Deep Tabular Learning","created":"2024-02-04","cited_by_count":8,"area":null},{"id":"2406.04090","title":"Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors","created":"2024-06-06","cited_by_count":8,"area":null},{"id":"2410.12783","title":"Context-Scaling versus Task-Scaling in In-Context Learning","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2503.19260","title":"Linguistic Blind Spots of Large Language Models","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2403.01384","title":"On the Compressibility of Quantized Large Language Models","created":"2024-03-03","cited_by_count":5,"area":null},{"id":"2406.03944","title":"Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples","created":"2024-06-06","cited_by_count":5,"area":null},{"id":"2406.04999","title":"ProMotion: Prototypes As Motion Learners","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2506.03790","title":"Attention-Only Transformers via Unrolled Subspace Denoising","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2309.05224","title":"SparseSwin: Swin Transformer with Sparse Transformer Block","created":"2023-09-11","cited_by_count":4,"area":null},{"id":"2408.03651","title":"Path-SAM2: Transfer SAM2 for digital pathology semantic segmentation","created":"2024-08-07","cited_by_count":4,"area":null},{"id":"2409.03404","title":"KAN See In the Dark","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2411.17182","title":"An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2505.24293","title":"Equivalent Linear Mappings of Large Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2604.14442","title":"Hierarchical vs. Flat Iteration in Shared-Weight Transformers","created":"2026-04-15","cited_by_count":4,"area":null},{"id":"2309.08374","title":"Understanding the limitations of self-supervised learning for tabular anomaly detection","created":"2023-09-15","cited_by_count":3,"area":null},{"id":"2405.17412","title":"Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNE","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2411.03033","title":"Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2412.18288","title":"Towards understanding how attention mechanism works in deep learning","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2507.13540","title":"Provable Low-Frequency Bias of In-Context Learning of Representations","created":"2025-07-17","cited_by_count":3,"area":null},{"id":"2507.20853","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","created":"2025-07-28","cited_by_count":3,"area":"deeprl"},{"id":"2507.21040","title":"Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps: An Interpretation and Potential Improvements","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2511.00907","title":"Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2405.02583","title":"Explainable Interface for Human-Autonomy Teaming: A Survey","created":"2024-05-04","cited_by_count":2,"area":null},{"id":"2408.08682","title":"LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2509.16875","title":"Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2310.01568","title":"Defending Against Authorship Identification Attacks","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2404.00648","title":"SpiralMLP: A Lightweight Vision MLP Architecture","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2410.09749","title":"EMWaveNet: Physically Explainable Neural Network Based on Electromagnetic Propagation for SAR Target Recognition","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2411.06785","title":"White-Box Diffusion Transformer for single-cell RNA-seq generation","created":"2024-11-11","cited_by_count":1,"area":"diffusion"},{"id":"2411.17961","title":"ESS-ReduNet: Enhancing Subspace Separability of ReduNet via Dynamic Expansion with Bayesian Inference","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2412.07704","title":"GEXIA: Granularity Expansion and Iterative Approximation for Scalable Multi-grained Video-language Learning","created":"2024-12-10","cited_by_count":1,"area":null},{"id":"2503.13935","title":"SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2504.18929","title":"Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity","created":"2025-04-26","cited_by_count":1,"area":null},{"id":"2509.08685","title":"Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2608.10251","title":"Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2308.09721","title":"A new solution and concrete implementation steps for Artificial General Intelligence","created":"2023-08-12","cited_by_count":0,"area":"wm"},{"id":"2409.19933","title":"CCDepth: A Lightweight Self-supervised Depth Estimation Network with Enhanced Interpretability","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2410.00132","title":"CVVLSNet: Vehicle Location and Speed Estimation Using Partial Connected Vehicle Trajectory Data","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2501.02559","title":"KM-UNet KAN Mamba UNet for medical image segmentation","created":"2025-01-05","cited_by_count":0,"area":"ssm"},{"id":"2505.13102","title":"Lightweight and Interpretable Transformer via Mixed Graph Algorithm Unrolling for Traffic Forecast","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2506.01980","title":"Surgical Foundation Model Leveraging Compression and Entropy Maximization for Image-Guided Surgical Assistance","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2508.04051","title":"Towards Globally Predictable k-Space Interpolation: A White-box Transformer Approach","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2509.00395","title":"Double-Constraint Diffusion Model with Nuclear Regularization for Ultra-low-dose PET Reconstruction","created":"2025-08-30","cited_by_count":0,"area":"diffusion"},{"id":"2509.11926","title":"Unrolling Graph-based Douglas-Rachford Algorithm for Image Interpolation with Informed Initialization","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.03027","title":"Lightweight Transformer for EEG Classification via Balanced Signed Graph Algorithm Unrolling","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2510.11910","title":"Simplifying Optimal Transport through Schatten-$p$ Regularization","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.20284","title":"Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.06345","title":"CLUENet: Cluster Attention Makes Neural Networks Have Eyes","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2601.17257","title":"A Constrained Optimization Perspective of Unrolled Transformers","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2601.21280","title":"Token Entropy Regularization for Multi-modal Antenna Affiliation Identification","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2609.01787","title":"CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.03001","title":"Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04413","title":"Specific Algorithmic Interpretability of Neural Networks: A Case Study on Textures","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.19033","title":"How Many Ranks Does a Token Need? A Noise-Floor Squelch for Rank-One LoRA Experts","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}