{"total":62,"rows":[{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2310.05175","title":"Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity","created":"2023-10-08","cited_by_count":165,"area":null},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137,"area":"mllm"},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102,"area":"inference"},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57,"area":null},{"id":"2412.05270","title":"APOLLO: SGD-like Memory, AdamW-level Performance","created":"2024-12-06","cited_by_count":54,"area":null},{"id":"2404.15381","title":"Advances and Open Challenges in Federated Foundation Models","created":"2024-04-23","cited_by_count":36,"area":null},{"id":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"area":null},{"id":"2407.04965","title":"Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2407.09141","title":"Accuracy is Not All You Need","created":"2024-07-12","cited_by_count":31,"area":null},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"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":"2407.20584","title":"Pruning Large Language Models with Semi-Structural Adaptive Sparse Training","created":"2024-07-30","cited_by_count":20,"area":null},{"id":"2504.05586","title":"Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations","created":"2025-04-08","cited_by_count":20,"area":"moe"},{"id":"2311.09335","title":"Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2410.17711","title":"Beware of Calibration Data for Pruning Large Language Models","created":"2024-10-23","cited_by_count":15,"area":null},{"id":"2312.15230","title":"PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs","created":"2023-12-23","cited_by_count":14,"area":"lr"},{"id":"2409.11055","title":"Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2405.16057","title":"SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models","created":"2024-05-25","cited_by_count":11,"area":null},{"id":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"id":"2510.10618","title":"Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization","created":"2025-10-12","cited_by_count":9,"area":null},{"id":"2505.01731","title":"Efficient Shapley Value-based Non-Uniform Pruning of Large Language Models","created":"2025-05-03","cited_by_count":8,"area":null},{"id":"2505.18164","title":"Model-Distributed Inference for Large Language Models at the Edge","created":"2025-05-13","cited_by_count":8,"area":null},{"id":"2310.04680","title":"The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning","created":"2023-10-07","cited_by_count":7,"area":null},{"id":"2402.09360","title":"HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference","created":"2024-02-14","cited_by_count":7,"area":"inference"},{"id":"2410.06718","title":"MatMamba: A Matryoshka State Space Model","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2408.14398","title":"On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning","created":"2024-08-26","cited_by_count":6,"area":null},{"id":"2505.03031","title":"Radio: Rate-Distortion Optimization for Large Language Model Compression","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2603.20224","title":"Beyond Test-Time Compute Strategies: Advocating Energy-per-Token in LLM Inference","created":"2026-03-04","cited_by_count":5,"area":"lr"},{"id":"2508.18088","title":"How Quantization Shapes Bias in Large Language Models","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2409.11233","title":"Evaluating the Impact of Compression Techniques on Task-Specific Performance of Large Language Models","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2411.03171","title":"Navigating Extremes: Dynamic Sparsity in Large Output Spaces","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2506.05647","title":"Learning to Weight Parameters for Training Data Attribution","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2606.19558","title":"Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment","created":"2026-06-17","cited_by_count":3,"area":null},{"id":"2405.01943","title":"Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2505.07289","title":"Semantic Retention and Extreme Compression in LLMs: Can We Have Both?","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2510.24256","title":"From Memorization to Reasoning in the Spectrum of Loss Curvature","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2601.09694","title":"LLMs can Compress LLMs: Adaptive Pruning by Agents","created":"2026-01-14","cited_by_count":2,"area":"agents"},{"id":"2606.17609","title":"The Benchmark Illusion: Pruned LLMs Can Pass Multiple Choice but Fail to Answer","created":"2026-06-16","cited_by_count":2,"area":null},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2504.08838","title":"SD$^2$: Self-Distilled Sparse Drafters","created":"2025-04-10","cited_by_count":1,"area":"inference"},{"id":"2507.01900","title":"High-Layer Attention Pruning with Rescaling","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2607.04640","title":"Wrong Before Right: Late Rescue and Interface Failure in Aligned Language Models","created":"2026-07-06","cited_by_count":1,"area":"alignment"},{"id":"2410.08791","title":"Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2501.07641","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2503.02508","title":"Q&C: When Quantization Meets Cache in Efficient Image Generation","created":"2025-03-04","cited_by_count":0,"area":"diffusion"},{"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":"2509.15206","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2605.08174","title":"CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.03328","title":"Rethinking Calibration for High-Sparsity LLM Pruning: From Single Sources to Capability Coverage","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.10855","title":"Reliability Scaling Laws for Quantized Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2609.04575","title":"Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models","created":"2026-09-04","cited_by_count":0,"area":"moe"},{"id":"2609.18005","title":"A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality","created":"2026-09-16","cited_by_count":0,"area":"inference"},{"id":"2609.23125","title":"Perplexity Cost Understates What Activation Quantisation Breaks","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.26241","title":"Damage Predicts Recovery: When Calibration Data Matters in Compressing Financial LLMs","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.02462","title":"Capability Scaling-Down Laws for LLM Compression","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04403","title":"Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}