{"total":800,"rows":[{"id":"2306.14048","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","created":"2023-06-24","cited_by_count":832,"area":"inference"},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472,"area":null},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415,"area":null},{"id":"2401.15024","title":"SliceGPT: Compress Large Language Models by Deleting Rows and Columns","created":"2024-01-26","cited_by_count":385,"area":null},{"id":"2402.04396","title":"QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks","created":"2024-02-06","cited_by_count":378,"area":null},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269,"area":null},{"id":"2401.05459","title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","created":"2024-01-10","cited_by_count":260,"area":"agents"},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2402.14905","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","created":"2024-02-22","cited_by_count":223,"area":null},{"id":"2312.12456","title":"PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU","created":"2023-12-16","cited_by_count":217,"area":null},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"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":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"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":"2309.14717","title":"QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models","created":"2023-09-26","cited_by_count":155,"area":null},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152,"area":"inference"},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"id":"2312.16886","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","created":"2023-12-28","cited_by_count":122,"area":"mllm"},{"id":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117,"area":"lr"},{"id":"2601.08584","title":"Ministral 3","created":"2026-01-13","cited_by_count":114,"area":null},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2402.12374","title":"Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding","created":"2024-02-19","cited_by_count":103,"area":"inference"},{"id":"2402.09025","title":"SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks","created":"2024-02-14","cited_by_count":97,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2408.11049","title":"MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding","created":"2024-08-20","cited_by_count":91,"area":"inference"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2402.02834","title":"Shortened LLaMA: Depth Pruning for Large Language Models with Comparison of Retraining Methods","created":"2024-02-05","cited_by_count":82,"area":null},{"id":"2402.11295","title":"OneBit: Towards Extremely Low-bit Large Language Models","created":"2024-02-17","cited_by_count":79,"area":null},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"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":"2403.00835","title":"CLLMs: Consistency Large Language Models","created":"2024-02-28","cited_by_count":72,"area":"inference"},{"id":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72,"area":"alignment"},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2407.14057","title":"LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference","created":"2024-07-19","cited_by_count":70,"area":"inference"},{"id":"2308.14352","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","created":"2023-08-28","cited_by_count":69,"area":"moe"},{"id":"2407.08735","title":"Real-Time Anomaly Detection and Reactive Planning with Large Language Models","created":"2024-07-11","cited_by_count":68,"area":null},{"id":"2407.21018","title":"ThinK: Thinner Key Cache by Query-Driven Pruning","created":"2024-07-30","cited_by_count":68,"area":"lr"},{"id":"2310.08041","title":"QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models","created":"2023-10-12","cited_by_count":64,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2405.14917","title":"SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models","created":"2024-05-23","cited_by_count":63,"area":null},{"id":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"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":"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":"2405.14852","title":"PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression","created":"2024-05-23","cited_by_count":61,"area":null},{"id":"2503.20641","title":"Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging","created":"2025-03-26","cited_by_count":58,"area":"lr"},{"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":"2411.01016","title":"MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition","created":"2024-11-01","cited_by_count":57,"area":"moe"},{"id":"2405.19237","title":"ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning","created":"2024-05-29","cited_by_count":55,"area":"diffusion"},{"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":"2402.15751","title":"Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning","created":"2024-02-24","cited_by_count":54,"area":null},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","cited_by_count":53,"area":"alignment"},{"id":"2407.00945","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","created":"2024-07-01","cited_by_count":53,"area":"moe"},{"id":"2408.12798","title":"BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models","created":"2024-08-23","cited_by_count":50,"area":"safety"},{"id":"2408.13656","title":"Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic","created":"2024-08-24","cited_by_count":50,"area":null},{"id":"2409.17481","title":"MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models","created":"2024-09-26","cited_by_count":50,"area":null},{"id":"2408.09632","title":"MoDeGPT: Modular Decomposition for Large Language Model Compression","created":"2024-08-19","cited_by_count":48,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2402.13516","title":"ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models","created":"2024-02-21","cited_by_count":45,"area":"inference"},{"id":"2402.16880","title":"BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation","created":"2024-02-18","cited_by_count":45,"area":null},{"id":"2311.07052","title":"Towards the Law of Capacity Gap in Distilling Language Models","created":"2023-11-13","cited_by_count":44,"area":"distill"},{"id":"2412.18110","title":"SlimGPT: Layer-wise Structured Pruning for Large Language Models","created":"2024-12-24","cited_by_count":44,"area":null},{"id":"2511.13653","title":"Weight-sparse transformers have interpretable circuits","created":"2025-11-17","cited_by_count":44,"area":"mechinterp"},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43,"area":null},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2402.05445","title":"Accurate LoRA-Finetuning Quantization of LLMs via Information Retention","created":"2024-02-08","cited_by_count":41,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2410.06270","title":"Mixture Compressor for Mixture-of-Experts LLMs Gains More","created":"2024-10-08","cited_by_count":41,"area":"moe"},{"id":"2406.02924","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","created":"2024-06-05","cited_by_count":40,"area":null},{"id":"2412.04315","title":"Densing Law of LLMs","created":"2024-12-05","cited_by_count":40,"area":null},{"id":"2411.10666","title":"SAM Decoding: Speculative Decoding via Suffix Automaton","created":"2024-11-16","cited_by_count":39,"area":"inference"},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2310.18356","title":"LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery","created":"2023-10-24","cited_by_count":38,"area":null},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2312.17244","title":"The LLM Surgeon","created":"2023-12-28","cited_by_count":38,"area":null},{"id":"2402.11131","title":"Speculative Streaming: Fast LLM Inference without Auxiliary Models","created":"2024-02-16","cited_by_count":38,"area":"inference"},{"id":"2410.04466","title":"Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective","created":"2024-10-06","cited_by_count":38,"area":"inference"},{"id":"2410.10912","title":"AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models","created":"2024-10-14","cited_by_count":36,"area":null},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"area":null},{"id":"2402.15607","title":"How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?","created":"2024-02-23","cited_by_count":35,"area":null},{"id":"2407.15861","title":"Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey","created":"2024-07-10","cited_by_count":35,"area":"diffusion"},{"id":"2410.03765","title":"Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression","created":"2024-10-02","cited_by_count":35,"area":null},{"id":"2502.06415","title":"Systematic Outliers in Large Language Models","created":"2025-02-10","cited_by_count":33,"area":null},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31,"area":null},{"id":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2408.05499","title":"LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale","created":"2024-08-10","cited_by_count":31,"area":"inference"},{"id":"2410.02338","title":"How Much Can RAG Help the Reasoning of LLM?","created":"2024-10-03","cited_by_count":31,"area":"lr"},{"id":"2410.03129","title":"ARB-LLM: Alternating Refined Binarizations for Large Language Models","created":"2024-10-04","cited_by_count":31,"area":null},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31,"area":null},{"id":"2311.04902","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","created":"2023-11-08","cited_by_count":30,"area":null},{"id":"2402.04497","title":"The Fine-Grained Complexity of Gradient Computation for Training Large Language Models","created":"2024-02-07","cited_by_count":30,"area":null},{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2409.06211","title":"STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning","created":"2024-09-10","cited_by_count":30,"area":"moe"},{"id":"2502.02421","title":"Activation-Informed Merging of Large Language Models","created":"2025-02-04","cited_by_count":30,"area":null},{"id":"2401.12200","title":"APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference","created":"2024-01-22","cited_by_count":29,"area":null},{"id":"2405.18218","title":"FinerCut: Finer-grained Interpretable Layer Pruning for Large Language Models","created":"2024-05-28","cited_by_count":27,"area":null},{"id":"2309.14021","title":"LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression","created":"2023-09-25","cited_by_count":26,"area":null},{"id":"2401.10862","title":"Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning","created":"2024-01-19","cited_by_count":26,"area":"safety"},{"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":"2502.03805","title":"CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective","created":"2025-02-06","cited_by_count":26,"area":"inference"}],"next_cursor":"100"}