{"total":43,"rows":[{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2209.15055","title":"Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions","created":"2022-09-29","cited_by_count":38,"area":null},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34,"area":null},{"id":"2408.11804","title":"Approaching Deep Learning through the Spectral Dynamics of Weights","created":"2024-08-21","cited_by_count":31,"area":null},{"id":"2411.04551","title":"Measure-to-measure interpolation using Transformers","created":"2024-11-07","cited_by_count":29,"area":null},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"area":null},{"id":"2305.16534","title":"Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2405.14468","title":"Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?","created":"2024-05-23","cited_by_count":17,"area":null},{"id":"2304.00933","title":"Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting","created":"2023-04-03","cited_by_count":16,"area":null},{"id":"2412.02682","title":"The Asymptotic Behavior of Attention in Transformers","created":"2024-12-03","cited_by_count":16,"area":null},{"id":"2306.01485","title":"Robust low-rank training via approximate orthonormal constraints","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2507.22857","title":"Synchronization of mean-field models on the circle","created":"2025-07-30","cited_by_count":12,"area":null},{"id":"2402.03991","title":"Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2510.11709","title":"Adversarial Attacks Leverage Interference Between Features in Superposition","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2512.14366","title":"Optimizing Rank for High-Fidelity Implicit Neural Representations","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2402.15415","title":"Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2410.07687","title":"Learning to Compress: Local Rank and Information Compression in Deep Neural Networks","created":"2024-10-10","cited_by_count":7,"area":null},{"id":"2505.19985","title":"Structured Initialization for Vision Transformers","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2505.21732","title":"LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2506.21263","title":"DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2603.03597","title":"NuMuon: Nuclear-Norm-Constrained Muon for Compressible LLM Training","created":"2026-03-04","cited_by_count":4,"area":null},{"id":"2410.15858","title":"Towards Optimal Adapter Placement for Efficient Transfer Learning","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2410.24023","title":"RAM: Replace Attention with MLP for Efficient Multivariate Time Series Forecasting","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2505.22355","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2410.15578","title":"Generalized Probabilistic Attention Mechanism in Transformers","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2605.30741","title":"Is the Last Layer Sufficient for Uncertainty Quantification?","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2607.14018","title":"Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2501.16322","title":"Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2505.24592","title":"A Flat Minima Perspective on Understanding Augmentations and Model Robustness","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2602.03586","title":"APEX: Probing Neural Networks via Activation Perturbation","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2606.22589","title":"Training-free Task Classification for Multi-Task Model Merging","created":"2026-06-21","cited_by_count":1,"area":null},{"id":"2211.12339","title":"Neural Dependencies Emerging from Learning Massive Categories","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2507.07675","title":"Some Theoretical Results on Layerwise Effective Dimension Oscillations in Finite Width ReLU Networks","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2508.09223","title":"Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2602.09057","title":"SVD-Preconditioned Gradient Descent Method for Solving Nonlinear Least Squares Problems","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2602.19845","title":"I Dropped a Neural Net","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.28142","title":"RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.02659","title":"Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2605.17692","title":"Exact Convex Reformulations of Linear Neural Networks via Completely Positive Lifting","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.03879","title":"Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.04754","title":"Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.16384","title":"Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training","created":"2026-06-15","cited_by_count":0,"area":null}],"next_cursor":null}