{"total":87,"rows":[{"id":"2601.08584","title":"Ministral 3","created":"2026-01-13","cited_by_count":114,"area":null},{"id":"2408.11796","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","created":"2024-08-21","cited_by_count":82,"area":null},{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"area":null},{"id":"2412.04315","title":"Densing Law of LLMs","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2411.15558","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","created":"2024-11-23","cited_by_count":24,"area":null},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2505.22689","title":"SlimLLM: Accurate Structured Pruning for Large Language Models","created":"2025-05-28","cited_by_count":18,"area":null},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"area":null},{"id":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2505.02819","title":"ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2501.17771","title":"2SSP: A Two-Stage Framework for Structured Pruning of LLMs","created":"2025-01-29","cited_by_count":12,"area":null},{"id":"2503.13572","title":"VeriContaminated: Assessing LLM-Driven Verilog Coding for Data Contamination","created":"2025-03-17","cited_by_count":12,"area":null},{"id":"2408.07337","title":"KIND: Knowledge Integration and Diversion for Training Decomposable Models","created":"2024-08-14","cited_by_count":10,"area":null},{"id":"2410.04501","title":"Leveraging Large Language Models for Suicide Detection on Social Media with Limited Labels","created":"2024-10-06","cited_by_count":10,"area":null},{"id":"2411.00308","title":"GPT for Games: An Updated Scoping Review (2020-2024)","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2502.12292","title":"Independence Tests for Language Models","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2510.22026","title":"Normalization in Attention Dynamics","created":"2025-10-24","cited_by_count":9,"area":null},{"id":"2504.11409","title":"Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2602.20816","title":"Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2409.18850","title":"Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2505.23807","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2510.18546","title":"EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2601.09066","title":"Mi:dm 2.0 Korea-centric Bilingual Language Models","created":"2026-01-14","cited_by_count":5,"area":null},{"id":"2408.12396","title":"Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2501.18015","title":"A Proximal Operator for Inducing 2:4-Sparsity","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2503.09657","title":"T\\'yr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2503.19123","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2506.01042","title":"Probing Neural Topology of Large Language Models","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2510.18680","title":"Learning Task-Agnostic Representations through Multi-Teacher Distillation","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2608.10837","title":"TACTICL: Task-Aware Compression of Tabular ICL Models","created":"2026-08-11","cited_by_count":4,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2504.16394","title":"ConTextual: Improving Clinical Text Summarization in LLMs with Context-preserving Token Filtering and Knowledge Graphs","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2505.20155","title":"Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs","created":"2025-05-26","cited_by_count":3,"area":null},{"id":"2507.03117","title":"BLaST: High Performance Inference and Pretraining using BLock Sparse Transformers","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2510.22101","title":"Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search","created":"2025-10-25","cited_by_count":3,"area":null},{"id":"2511.11683","title":"Stratified Knowledge-Density Super-Network for Scalable Vision Transformers","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2601.19503","title":"GradPruner: Gradient-Guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2410.19456","title":"Computational Bottlenecks of Training Small-scale Large Language Models","created":"2024-10-25","cited_by_count":2,"area":null},{"id":"2506.22389","title":"Towards Distributed Neural Architectures","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2507.01035","title":"Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2510.05064","title":"Boomerang Distillation Enables Zero-Shot Model Size Interpolation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2510.22951","title":"Hankel Singular Value Regularization for Highly Compressible State Space Models","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2512.22671","title":"Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2","created":"2025-12-27","cited_by_count":2,"area":null},{"id":"2605.15491","title":"Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2605.27786","title":"Locality-Aware Redundancy Pruning for LLM Depth Compression","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2501.04211","title":"CURing Large Models: Compression via CUR Decomposition","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2503.05920","title":"IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2504.06323","title":"Mosaic: Composite Projection Pruning for Resource-efficient LLMs","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2510.07227","title":"Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.13832","title":"Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2602.00161","title":"LLM Compression by Block Removal with Constrained Binary Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2603.08083","title":"High-Fidelity Pruning for Large Language Models","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2606.14150","title":"Small LLMs: Pruning vs. Training from Scratch","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.07670","title":"Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2607.08170","title":"Understanding Layer Patching in Model Size Interpolation","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2608.13596","title":"Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning","created":"2026-07-31","cited_by_count":1,"area":null},{"id":"2608.13721","title":"Capacity-Dependent Effects of Data Selection for Reasoning","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2504.03118","title":"NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2506.04513","title":"Pruning Everything, Everywhere, All at Once","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2509.06836","title":"COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2511.16450","title":"Optimizing Federated Learning in the Era of LLMs: Message Quantization and Streaming","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2511.17205","title":"E$^3$-Pruner: Towards Efficient, Economical, and Effective Layer Pruning for Large Language Models","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.22307","title":"LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2602.06127","title":"Compressing LLMs with MoP: Mixture of Pruners","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.03508","title":"Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.03808","title":"Vector-Quantized Soft Label Compression for Dataset Distillation","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2604.10627","title":"Computational Lesions in Multilingual Language Models Separate Shared and Language-specific Brain Alignment","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.07783","title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08885","title":"Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.17508","title":"BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.18860","title":"Spectral structural distortion reveals redundant neurons in neural networks","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.30018","title":"Latent Performance Profiling of Large Language Models","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.04063","title":"LLM Compression with Jointly Optimizing Architectural and Quantization choices","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.14346","title":"Squeeze-Release: Iterative Pruning with Exact Structural Minimization","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.24747","title":"Scaling Laws for Task-Specific LLM Distillation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.25366","title":"Reliability-Asymmetric Spacecraft Autonomy: Co-Designing a Capable Learned GNC Stack with a Verified, Adaptation-Aware Runtime Shield","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.16246","title":"Let the Data Decide: Supervision Analysis, Capability Trade-offs, and Adaptive Objective Routing in Continued Pre-Training via Off-Policy Distillation","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.02829","title":"Wiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.02006","title":"Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.11149","title":"Break Step: Recursive Training Resonates with Replayed Sampling Noise","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.13846","title":"Affinity-Aware Sharding for Delayed Tensor Parallelism","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.36842","title":"Does the VGGT Family Need All Its Layers?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03109","title":"Emergent Structure in the Marginal Attention Space of Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.15028","title":"UltraBERT: Beyond the Limit of BERT Pre-Training","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}