{"total":237,"rows":[{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724,"area":"mechinterp"},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300,"area":null},{"id":"2308.06767","title":"A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations","created":"2023-08-13","cited_by_count":202,"area":null},{"id":"2109.04838","title":"Block Pruning For Faster Transformers","created":"2021-09-10","cited_by_count":177,"area":null},{"id":"2402.16842","title":"Asymmetry in Low-Rank Adapters of Foundation Models","created":"2024-02-26","cited_by_count":86,"area":null},{"id":"2211.02633","title":"A Theoretical Study on Solving Continual Learning","created":"2022-11-04","cited_by_count":80,"area":null},{"id":"2410.20672","title":"Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA","created":"2024-10-28","cited_by_count":78,"area":null},{"id":"2106.09129","title":"A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness","created":"2021-06-16","cited_by_count":62,"area":null},{"id":"2310.08915","title":"Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs","created":"2023-10-13","cited_by_count":61,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null},{"id":"2103.09377","title":"Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network","created":"2021-03-17","cited_by_count":55,"area":null},{"id":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2203.08392","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","created":"2022-03-16","cited_by_count":49,"area":null},{"id":"2105.01571","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","created":"2021-05-03","cited_by_count":45,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"area":null},{"id":"2103.06460","title":"Recent Advances on Neural Network Pruning at Initialization","created":"2021-03-11","cited_by_count":41,"area":null},{"id":"2203.04466","title":"The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks","created":"2022-03-09","cited_by_count":41,"area":null},{"id":"2210.03044","title":"Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?","created":"2022-10-06","cited_by_count":38,"area":null},{"id":"2209.07529","title":"On the Soft-Subnetwork for Few-shot Class Incremental Learning","created":"2022-09-15","cited_by_count":37,"area":null},{"id":"2202.12002","title":"Rare Gems: Finding Lottery Tickets at Initialization","created":"2022-02-24","cited_by_count":34,"area":null},{"id":"2110.14402","title":"Learning where to learn: Gradient sparsity in meta and continual learning","created":"2021-10-27","cited_by_count":33,"area":null},{"id":"2209.15328","title":"Sparse Random Networks for Communication-Efficient Federated Learning","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30,"area":null},{"id":"2111.11146","title":"On the Existence of Universal Lottery Tickets","created":"2021-11-22","cited_by_count":30,"area":null},{"id":"2110.14068","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","created":"2021-10-26","cited_by_count":29,"area":null},{"id":"2210.02412","title":"Why Random Pruning Is All We Need to Start Sparse","created":"2022-10-05","cited_by_count":26,"area":null},{"id":"2403.04861","title":"A Survey of Lottery Ticket Hypothesis","created":"2024-03-07","cited_by_count":24,"area":null},{"id":"2312.01397","title":"Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2212.11110","title":"Lifelong Reinforcement Learning with Modulating Masks","created":"2022-12-21","cited_by_count":22,"area":null},{"id":"2304.10038","title":"Open-World Continual Learning: Unifying Novelty Detection and Continual Learning","created":"2023-04-20","cited_by_count":22,"area":null},{"id":"2204.02738","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","created":"2022-04-06","cited_by_count":21,"area":null},{"id":"2205.02321","title":"Most Activation Functions Can Win the Lottery Without Excessive Depth","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2106.09269","title":"Pruning Randomly Initialized Neural Networks with Iterative Randomization","created":"2021-06-17","cited_by_count":20,"area":null},{"id":"2206.00843","title":"DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2206.04270","title":"A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis","created":"2022-06-09","cited_by_count":19,"area":null},{"id":"2103.05152","title":"Knowledge Evolution in Neural Networks","created":"2021-03-09","cited_by_count":18,"area":null},{"id":"2305.17682","title":"One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning","created":"2023-05-28","cited_by_count":18,"area":null},{"id":"2308.02066","title":"Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives","created":"2023-08-03","cited_by_count":18,"area":null},{"id":"2402.06323","title":"How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers","created":"2024-02-09","cited_by_count":18,"area":null},{"id":"2306.12230","title":"Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2410.04368","title":"Algorithmic Capabilities of Random Transformers","created":"2024-10-06","cited_by_count":17,"area":null},{"id":"2411.09702","title":"On the Surprising Effectiveness of Attention Transfer for Vision Transformers","created":"2024-11-14","cited_by_count":17,"area":null},{"id":"2203.07808","title":"Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs","created":"2022-03-15","cited_by_count":16,"area":null},{"id":"2205.02343","title":"Convolutional and Residual Networks Provably Contain Lottery Tickets","created":"2022-05-04","cited_by_count":16,"area":null},{"id":"2301.05219","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","created":"2023-01-12","cited_by_count":16,"area":null},{"id":"2306.03715","title":"Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability","created":"2023-06-06","cited_by_count":16,"area":null},{"id":"2405.15743","title":"Sparse maximal update parameterization: A holistic approach to sparse training dynamics","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2409.06703","title":"LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation","created":"2024-09-10","cited_by_count":16,"area":null},{"id":"2105.10065","title":"A Probabilistic Approach to Neural Network Pruning","created":"2021-05-20","cited_by_count":15,"area":null},{"id":"2402.19262","title":"Masks, Signs, And Learning Rate Rewinding","created":"2024-02-29","cited_by_count":15,"area":null},{"id":"2110.05667","title":"Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks","created":"2021-10-12","cited_by_count":14,"area":null},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2211.15335","title":"You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets","created":"2022-11-28","cited_by_count":14,"area":null},{"id":"2504.04626","title":"Exact Unlearning of Finetuning Data via Model Merging at Scale","created":"2025-04-06","cited_by_count":14,"area":"safety"},{"id":"2111.11153","title":"Plant 'n' Seek: Can You Find the Winning Ticket?","created":"2021-11-22","cited_by_count":13,"area":null},{"id":"2202.06438","title":"Learning from Randomly Initialized Neural Network Features","created":"2022-02-13","cited_by_count":12,"area":null},{"id":"2204.12266","title":"Attentive Fine-Grained Structured Sparsity for Image Restoration","created":"2022-04-26","cited_by_count":12,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"id":"2207.03677","title":"SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning","created":"2022-07-08","cited_by_count":12,"area":null},{"id":"2208.13092","title":"Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge","created":"2022-08-27","cited_by_count":12,"area":null},{"id":"2211.10155","title":"Structured Pruning Adapters","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2410.02159","title":"Mitigating Memorization In Language Models","created":"2024-10-03","cited_by_count":12,"area":"safety"},{"id":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11,"area":null},{"id":"2208.10842","title":"Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost","created":"2022-08-23","cited_by_count":11,"area":null},{"id":"2505.20154","title":"UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2506.14530","title":"Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters","created":"2025-06-17","cited_by_count":11,"area":null},{"id":"2104.08700","title":"Lottery Jackpots Exist in Pre-trained Models","created":"2021-04-18","cited_by_count":10,"area":null},{"id":"2112.13208","title":"Neural Network Module Decomposition and Recomposition","created":"2021-12-25","cited_by_count":10,"area":null},{"id":"2305.10997","title":"Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2112.03406","title":"Equal Bits: Enforcing Equally Distributed Binary Network Weights","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2112.04002","title":"SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2203.14328","title":"On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks","created":"2022-03-27","cited_by_count":9,"area":null},{"id":"2205.07320","title":"Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective","created":"2022-05-15","cited_by_count":9,"area":null},{"id":"2210.06699","title":"Parameter-Efficient Masking Networks","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2408.02672","title":"Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics","created":"2024-08-05","cited_by_count":9,"area":null},{"id":"2110.04350","title":"FRL: Federated Rank Learning","created":"2021-10-08","cited_by_count":8,"area":null},{"id":"2303.11525","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2308.04637","title":"Sparse Binary Transformers for Multivariate Time Series Modeling","created":"2023-08-09","cited_by_count":8,"area":null},{"id":"2402.01089","title":"No Free Prune: Information-Theoretic Barriers to Pruning at Initialization","created":"2024-02-02","cited_by_count":8,"area":null},{"id":"2108.11939","title":"Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics","created":"2021-08-26","cited_by_count":7,"area":null},{"id":"2111.11165","title":"Graph-Based Similarity of Neural Network Representations","created":"2021-11-22","cited_by_count":7,"area":null},{"id":"2201.13361","title":"Signing the Supermask: Keep, Hide, Invert","created":"2022-01-31","cited_by_count":7,"area":null},{"id":"2207.07858","title":"The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network","created":"2022-07-16","cited_by_count":7,"area":null},{"id":"2207.08148","title":"Improving Deep Neural Network Random Initialization Through Neuronal Rewiring","created":"2022-07-17","cited_by_count":7,"area":null},{"id":"2211.01522","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2304.10036","title":"Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2310.09436","title":"Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2412.00143","title":"Is Oracle Pruning the True Oracle?","created":"2024-11-28","cited_by_count":7,"area":null},{"id":"2206.04385","title":"HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask","created":"2022-06-09","cited_by_count":6,"area":null},{"id":"2206.13336","title":"Continual Learning of Dynamical Systems with Competitive Federated Reservoir Computing","created":"2022-06-27","cited_by_count":6,"area":null},{"id":"2209.06116","title":"Patching Weak Convolutional Neural Network Models through Modularization and Composition","created":"2022-09-11","cited_by_count":6,"area":null},{"id":"2310.19470","title":"Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2312.11973","title":"Continual Learning: Forget-free Winning Subnetworks for Video Representations","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2406.13131","title":"When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2410.08540","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2101.06475","title":"Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks","created":"2021-01-16","cited_by_count":5,"area":null},{"id":"2105.02551","title":"Structured Ensembles: an Approach to Reduce the Memory Footprint of Ensemble Methods","created":"2021-05-06","cited_by_count":5,"area":null},{"id":"2106.04767","title":"Ex uno plures: Splitting One Model into an Ensemble of Subnetworks","created":"2021-06-09","cited_by_count":5,"area":null}],"next_cursor":"100"}