{"total":82,"rows":[{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148,"area":"distill"},{"id":"2406.01733","title":"Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching","created":"2024-06-03","cited_by_count":142,"area":"diffusion"},{"id":"2408.11796","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","created":"2024-08-21","cited_by_count":82,"area":null},{"id":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2412.01199","title":"TinyFusion: Diffusion Transformers Learned Shallow","created":"2024-12-02","cited_by_count":45,"area":"diffusion"},{"id":"2503.24377","title":"Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models","created":"2025-03-31","cited_by_count":36,"area":"lr"},{"id":"2411.15558","title":"Reassessing Layer Pruning in LLMs: New Insights and Methods","created":"2024-11-23","cited_by_count":24,"area":null},{"id":"2404.03865","title":"FFN-SkipLLM: A Hidden Gem for Autoregressive Decoding with Adaptive Feed Forward Skipping","created":"2024-04-05","cited_by_count":23,"area":"inference"},{"id":"2407.16286","title":"A deeper look at depth pruning of LLMs","created":"2024-07-23","cited_by_count":23,"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":"2501.02086","title":"Instruction-Following Pruning for Large Language Models","created":"2025-01-03","cited_by_count":17,"area":null},{"id":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2504.00502","title":"ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers","created":"2025-04-01","cited_by_count":14,"area":"mllm"},{"id":"2509.04467","title":"PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference","created":"2025-08-29","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":"2411.10606","title":"AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment","created":"2024-11-15","cited_by_count":12,"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":"2506.04179","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2601.18091","title":"From LLMs to LRMs: Rethinking Pruning for Reasoning-Centric Models","created":"2026-01-26","cited_by_count":10,"area":"lr"},{"id":"2407.19126","title":"Greedy Output Approximation: Towards Efficient Structured Pruning for LLMs Without Retraining","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2507.03865","title":"OrthoRank: Token Selection via Sink Token Orthogonality for Efficient LLM inference","created":"2025-07-05","cited_by_count":8,"area":"inference"},{"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":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2406.10576","title":"Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient","created":"2024-06-15","cited_by_count":6,"area":null},{"id":"2409.11057","title":"KVPruner: Structural Pruning for Faster and Memory-Efficient Large Language Models","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2505.24584","title":"AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up","created":"2025-05-30","cited_by_count":6,"area":"agents"},{"id":"2510.15304","title":"Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation","created":"2025-10-17","cited_by_count":6,"area":null},{"id":"2512.02185","title":"Think Before You Prune: Self-Reflective Structured Pruning for Reasoning Language Models","created":"2025-12-01","cited_by_count":6,"area":"lr"},{"id":"2504.21174","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning","created":"2025-04-29","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":"2411.01179","title":"Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models","created":"2024-11-02","cited_by_count":4,"area":"diffusion"},{"id":"2411.06839","title":"LLM-NEO: Parameter Efficient Knowledge Distillation for Large Language Models","created":"2024-11-11","cited_by_count":4,"area":"distill"},{"id":"2505.24680","title":"A Simple Linear Patch Revives Layer-Pruned Large Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2502.01717","title":"Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation","created":"2025-02-03","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":"2506.20480","title":"GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2602.07804","title":"Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models","created":"2026-02-08","cited_by_count":3,"area":null},{"id":"2410.19185","title":"Tailored-LLaMA: Optimizing Few-Shot Learning in Pruned LLaMA Models with Task-Specific Prompts","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2411.07066","title":"Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2411.14507","title":"From Pruning to Grafting: Dynamic Knowledge Redistribution via Learnable Layer Fusion","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2503.11164","title":"Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2503.18646","title":"ZeroLM: Data-Free Transformer Architecture Search for Language Models","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2508.08446","title":"OverFill: Two-Stage Models for Efficient Language Model Decoding","created":"2025-08-11","cited_by_count":2,"area":null},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2510.07782","title":"RCPU: Rotation-Constrained Error Compensation for Structured Pruning of Large Language Models","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2510.22767","title":"TELL-TALE: Task Efficient LLMs with Task Aware Layer Elimination","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2510.23652","title":"The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2602.08858","title":"FlattenGPT: Depth Compression for Transformer with Layer Flattening","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2605.07271","title":"Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions","created":"2026-05-08","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":"2606.24970","title":"Don't Go Breaking My LLM: The Impact of Pruning Attention Layers on Explanation Faithfulness and Confidence Calibration","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2411.15281","title":"ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation","created":"2024-11-22","cited_by_count":1,"area":"lr"},{"id":"2505.07893","title":"Channel Fingerprint Construction for Massive MIMO: A Deep Conditional Generative Approach","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2507.01900","title":"High-Layer Attention Pruning with Rescaling","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2507.09428","title":"On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2507.21976","title":"Compression Strategies for Efficient Multimodal LLMs in Medical Contexts","created":"2025-07-29","cited_by_count":1,"area":"mllm"},{"id":"2508.18430","title":"CLARIFY: A Specialist-Generalist Framework for Accurate and Lightweight Dermatological Visual Question Answering","created":"2025-08-25","cited_by_count":1,"area":"mllm"},{"id":"2602.00161","title":"LLM Compression by Block Removal with Constrained Binary Optimization","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2602.02891","title":"TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2604.19520","title":"SimDiff: Depth Pruning via Similarity and Difference","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.25842","title":"MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning","created":"2026-05-25","cited_by_count":1,"area":"lr"},{"id":"2606.09514","title":"BUDDY: BUdget-Driven DYnamic Depth Routing for Adaptive Large Language Model Inference","created":"2026-06-08","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":"2411.14345","title":"Layer Pruning with Consensus: A Triple-Win Solution","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2412.15127","title":"Adaptive Pruning for Large Language Models with Structural Importance Awareness","created":"2024-12-19","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":"2511.17205","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":"2602.06127","title":"Compressing LLMs with MoP: Mixture of Pruners","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.10431","title":"QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.20991","title":"Structural Sensitivity in Compressed Transformers: Relative Error Propagation and Layer Removal","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.27574","title":"Statistical Channel Fingerprint Construction for Massive MIMO: A Unified Tensor Learning Framework","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2606.14695","title":"Persona-Pruner: Sculpting Lightweight Models for Role-Playing","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.21847","title":"UniRank: Unified Rank Allocation for Low-Rank LLM Compression","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.22583","title":"Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2608.14003","title":"Batch-wise Adaptive Pruning: Periodic Neuron Activation-Aware Weight Pruning for Language Reasoning Model","created":"2026-08-14","cited_by_count":0,"area":"lr"},{"id":"2609.21666","title":"Samsone: A Family of Open Small Audio Language Models for On-Device Inference","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.31098","title":"The Residual Stream's Effective Depth","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.02418","title":"Mitigating Private Data Leakage in LLMs with Whiteout","created":"2026-10-01","cited_by_count":0,"area":"safety"}],"next_cursor":null}