{"total":148,"rows":[{"id":"2412.04468","title":"NVILA: Efficient Frontier Visual Language Models","created":"2024-12-05","cited_by_count":209,"area":"mllm"},{"id":"2601.08584","title":"Ministral 3","created":"2026-01-13","cited_by_count":114,"area":null},{"id":"2504.03624","title":"Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models","created":"2025-04-04","cited_by_count":100,"area":"lr"},{"id":"2408.11796","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","created":"2024-08-21","cited_by_count":82,"area":null},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2502.08606","title":"Distillation Scaling Laws","created":"2025-02-12","cited_by_count":67,"area":"lr"},{"id":"2410.12013","title":"MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router","created":"2024-10-15","cited_by_count":62,"area":"moe"},{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"area":null},{"id":"2408.16737","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","created":"2024-08-29","cited_by_count":61,"area":"lr"},{"id":"2502.14866","title":"LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention","created":"2025-02-20","cited_by_count":41,"area":"inference"},{"id":"2412.04315","title":"Densing Law of LLMs","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2506.04301","title":"The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective","created":"2025-06-04","cited_by_count":39,"area":"lr"},{"id":"2410.17215","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","created":"2024-10-22","cited_by_count":29,"area":"distill"},{"id":"2512.11130","title":"Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching","created":"2025-12-11","cited_by_count":28,"area":"distill"},{"id":"2411.15558","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","created":"2024-11-23","cited_by_count":24,"area":null},{"id":"2501.16937","title":"TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models","created":"2025-01-28","cited_by_count":22,"area":"distill"},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2412.07583","title":"Mobile Video Diffusion","created":"2024-12-10","cited_by_count":18,"area":"diffusion"},{"id":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2505.17272","title":"Zebra-Llama: Towards Extremely Efficient Hybrid Models","created":"2025-05-22","cited_by_count":18,"area":"inference"},{"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":"2505.12781","title":"A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone","created":"2025-05-19","cited_by_count":15,"area":"distill"},{"id":"2510.02091","title":"Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","cited_by_count":14,"area":"inference"},{"id":"2605.07721","title":"Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models","created":"2026-05-08","cited_by_count":14,"area":"inference"},{"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":"2507.00390","title":"MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE","created":"2025-07-01","cited_by_count":13,"area":"moe"},{"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":"2605.07711","title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","created":"2026-05-08","cited_by_count":12,"area":"distill"},{"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":"2412.01822","title":"VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models","created":"2024-12-02","cited_by_count":10,"area":"mllm"},{"id":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2502.12292","title":"Independence Tests for Language Models","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2506.15681","title":"GenRecal: Generation after Recalibration from Large to Small Vision-Language Models","created":"2025-06-18","cited_by_count":10,"area":"mllm"},{"id":"2510.14436","title":"MergeMoE: Efficient Compression of MoE Models via Expert Output Merging","created":"2025-10-16","cited_by_count":10,"area":"moe"},{"id":"2510.22026","title":"Normalization in Attention Dynamics","created":"2025-10-24","cited_by_count":9,"area":null},{"id":"2505.22135","title":"RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding","created":"2025-05-28","cited_by_count":8,"area":"inference"},{"id":"2607.13124","title":"ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation","created":"2026-07-14","cited_by_count":8,"area":"distill"},{"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":"2511.16156","title":"Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers","created":"2025-11-20","cited_by_count":7,"area":"diffusion"},{"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":"2605.08738","title":"SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training","created":"2026-05-09","cited_by_count":7,"area":"moe"},{"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":"2511.16664","title":"Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs","created":"2025-11-20","cited_by_count":6,"area":"lr"},{"id":"2410.09804","title":"BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models","created":"2024-10-13","cited_by_count":5,"area":"safety"},{"id":"2507.05934","title":"BlueLM-2.5-3B Technical Report","created":"2025-07-08","cited_by_count":5,"area":"lr"},{"id":"2507.15198","title":"Collaborative Distillation Strategies for Parameter-Efficient Language Model Deployment","created":"2025-07-21","cited_by_count":5,"area":"distill"},{"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":"2510.22228","title":"When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs","created":"2025-10-25","cited_by_count":5,"area":"lr"},{"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":"2505.09498","title":"Flash-VL 2B: Optimizing Vision-Language Model Performance for Ultra-Low Latency and High Throughput","created":"2025-05-14","cited_by_count":4,"area":"mllm"},{"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":"2603.11881","title":"Bielik-Minitron-7B: Compressing Large Language Models via Structured Pruning and Knowledge Distillation for the Polish Language","created":"2026-03-12","cited_by_count":4,"area":"distill"},{"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":"2508.02801","title":"Adaptive Knowledge Distillation for Device-Directed Speech Detection","created":"2025-08-04","cited_by_count":3,"area":"distill"},{"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":"2602.01997","title":"On the Limits of Layer Pruning for Generative Reasoning in Large Language Models","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2604.24380","title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","created":"2026-04-27","cited_by_count":3,"area":"mllm"},{"id":"2605.07182","title":"Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2605.23857","title":"Strong Teacher Not Needed? On Distillation in LLM Pretraining","created":"2026-05-22","cited_by_count":3,"area":"distill"},{"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":"2511.16047","title":"AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers","created":"2025-11-20","cited_by_count":2,"area":"inference"},{"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":"2602.01167","title":"Do All Individual Layers Help? An Empirical Study of Task-Interfering Layers in Vision-Language Models","created":"2026-02-01","cited_by_count":2,"area":"mllm"},{"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":"2608.03796","title":"Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss","created":"2026-08-04","cited_by_count":2,"area":"distill"},{"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":"2504.07965","title":"Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments","created":"2025-04-10","cited_by_count":1,"area":"alignment"},{"id":"2505.21077","title":"Efficient Large Language Model Inference with Neural Block Linearization","created":"2025-05-27","cited_by_count":1,"area":"inference"},{"id":"2506.15702","title":"Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-Distillation","created":"2025-05-30","cited_by_count":1,"area":"distill"},{"id":"2507.10155","title":"What Should Feature Distillation Transfer in LLMs? A Task-Tangent Geometry View","created":"2025-07-14","cited_by_count":1,"area":"distill"},{"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}],"next_cursor":"100"}