{"total":198,"rows":[{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418,"area":null},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298,"area":null},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121,"area":null},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800,"area":null},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575,"area":null},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2308.13137","title":"OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models","created":"2023-08-25","cited_by_count":424,"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":"2306.03078","title":"SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression","created":"2023-06-05","cited_by_count":367,"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":"2401.06118","title":"Extreme Compression of Large Language Models via Additive Quantization","created":"2024-01-11","cited_by_count":232,"area":null},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180,"area":null},{"id":"2303.15647","title":"Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning","created":"2023-03-28","cited_by_count":173,"area":null},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151,"area":null},{"id":"2301.03728","title":"Scaling Laws for Generative Mixed-Modal Language Models","created":"2023-01-10","cited_by_count":134,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2406.11235","title":"QTIP: Quantization with Trellises and Incoherence Processing","created":"2024-06-17","cited_by_count":91,"area":null},{"id":"2310.07707","title":"MatFormer: Nested Transformer for Elastic Inference","created":"2023-10-11","cited_by_count":85,"area":null},{"id":"2303.08302","title":"ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation","created":"2023-03-15","cited_by_count":79,"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":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2304.04487","title":"Inference with Reference: Lossless Acceleration of Large Language Models","created":"2023-04-10","cited_by_count":65,"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":"2304.09145","title":"Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling","created":"2023-04-18","cited_by_count":61,"area":null},{"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":"2311.09755","title":"On the Impact of Calibration Data in Post-training Quantization and Pruning","created":"2023-11-16","cited_by_count":58,"area":null},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2501.17116","title":"Optimizing Large Language Model Training Using FP4 Quantization","created":"2025-01-28","cited_by_count":56,"area":null},{"id":"2407.00088","title":"T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge","created":"2024-06-25","cited_by_count":55,"area":null},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2309.01507","title":"Memory Efficient Optimizers with 4-bit States","created":"2023-09-04","cited_by_count":54,"area":null},{"id":"2408.11743","title":"MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models","created":"2024-08-21","cited_by_count":52,"area":null},{"id":"2411.07191","title":"The Super Weight in Large Language Models","created":"2024-11-11","cited_by_count":52,"area":null},{"id":"2302.08007","title":"With Shared Microexponents, A Little Shifting Goes a Long Way","created":"2023-02-16","cited_by_count":50,"area":null},{"id":"2305.19268","title":"Intriguing Properties of Quantization at Scale","created":"2023-05-30","cited_by_count":49,"area":null},{"id":"2403.17312","title":"ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching","created":"2024-03-26","cited_by_count":48,"area":null},{"id":"2502.02631","title":"ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization","created":"2025-02-04","cited_by_count":46,"area":null},{"id":"2307.09782","title":"ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats","created":"2023-07-19","cited_by_count":44,"area":null},{"id":"2307.08072","title":"Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical Study","created":"2023-07-16","cited_by_count":43,"area":null},{"id":"2309.08520","title":"Scaling Laws for Sparsely-Connected Foundation Models","created":"2023-09-15","cited_by_count":43,"area":null},{"id":"2407.03211","title":"How Does Quantization Affect Multilingual LLMs?","created":"2024-07-03","cited_by_count":43,"area":null},{"id":"2309.07098","title":"Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding","created":"2023-09-13","cited_by_count":42,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2310.09259","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","created":"2023-10-13","cited_by_count":39,"area":null},{"id":"2512.02010","title":"Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling","created":"2025-12-01","cited_by_count":35,"area":null},{"id":"2411.02355","title":"\"Give Me BF16 or Give Me Death\"? Accuracy-Performance Trade-Offs in LLM Quantization","created":"2024-11-04","cited_by_count":34,"area":null},{"id":"2505.07004","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","created":"2025-05-11","cited_by_count":32,"area":null},{"id":"2303.17951","title":"FP8 versus INT8 for efficient deep learning inference","created":"2023-03-31","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":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2504.06225","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","created":"2025-04-08","cited_by_count":28,"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":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2502.18969","title":"(Mis)Fitting: A Survey of Scaling Laws","created":"2025-02-26","cited_by_count":26,"area":null},{"id":"2301.12017","title":"Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases","created":"2023-01-27","cited_by_count":23,"area":null},{"id":"2402.17946","title":"SparseLLM: Towards Global Pruning for Pre-trained Language Models","created":"2024-02-28","cited_by_count":23,"area":null},{"id":"2403.06408","title":"What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation","created":"2024-03-11","cited_by_count":23,"area":null},{"id":"2404.03605","title":"Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization","created":"2024-04-04","cited_by_count":23,"area":null},{"id":"2309.10917","title":"End-to-End Speech Recognition Contextualization with Large Language Models","created":"2023-09-19","cited_by_count":22,"area":null},{"id":"2407.10032","title":"LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid","created":"2024-07-14","cited_by_count":22,"area":null},{"id":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2411.17525","title":"Pushing the Limits of Large Language Model Quantization via the Linearity Theorem","created":"2024-11-26","cited_by_count":21,"area":null},{"id":"2309.17224","title":"Training and inference of large language models using 8-bit floating point","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2410.14649","title":"EvoPress: Accurate Dynamic Model Compression via Evolutionary Search","created":"2024-10-18","cited_by_count":20,"area":null},{"id":"2305.12356","title":"Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models","created":"2023-05-21","cited_by_count":19,"area":null},{"id":"2405.03146","title":"Quantifying the Capabilities of LLMs across Scale and Precision","created":"2024-05-06","cited_by_count":19,"area":null},{"id":"2408.06003","title":"LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference","created":"2024-08-12","cited_by_count":18,"area":null},{"id":"2403.20041","title":"Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs","created":"2024-03-29","cited_by_count":17,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2406.17415","title":"Layer-Wise Quantization: A Pragmatic and Effective Method for Quantizing LLMs Beyond Integer Bit-Levels","created":"2024-06-25","cited_by_count":16,"area":null},{"id":"2510.05197","title":"Efficient Prediction of Pass@k Scaling in Large Language Models","created":"2025-10-06","cited_by_count":16,"area":null},{"id":"2402.04902","title":"L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models","created":"2024-02-07","cited_by_count":15,"area":null},{"id":"2406.04379","title":"VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2309.07601","title":"Weakly Supervised Veracity Classification with LLM-Predicted Credibility Signals","created":"2023-09-14","cited_by_count":14,"area":null},{"id":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2408.06731","title":"Large language models can consistently generate high-quality content for election disinformation operations","created":"2024-08-13","cited_by_count":14,"area":null},{"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":"2410.20650","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2302.02390","title":"Quantized Distributed Training of Large Models with Convergence Guarantees","created":"2023-02-05","cited_by_count":13,"area":null},{"id":"2302.04907","title":"Binarized Neural Machine Translation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2405.07135","title":"Post Training Quantization of Large Language Models with Microscaling Formats","created":"2024-05-12","cited_by_count":12,"area":null},{"id":"2405.20835","title":"Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs","created":"2024-05-31","cited_by_count":12,"area":null},{"id":"2412.06484","title":"Small Languages, Big Models: A Study of Continual Training on Languages of Norway","created":"2024-12-09","cited_by_count":12,"area":null},{"id":"2412.18260","title":"Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study","created":"2024-12-24","cited_by_count":12,"area":null},{"id":"2401.02938","title":"Fast and Effective Weight Update for Pruned Large Language Models","created":"2024-01-01","cited_by_count":11,"area":null},{"id":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2302.10360","title":"Optical Transformers","created":"2023-02-20","cited_by_count":10,"area":null},{"id":"2401.03741","title":"Enhanced Automated Code Vulnerability Repair using Large Language Models","created":"2024-01-08","cited_by_count":10,"area":null},{"id":"2405.03637","title":"Collage: Light-Weight Low-Precision Strategy for LLM Training","created":"2024-05-06","cited_by_count":10,"area":null},{"id":"2407.11722","title":"Exploring Quantization for Efficient Pre-Training of Transformer Language Models","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2401.06920","title":"Comparing GPT-4 and Open-Source Language Models in Misinformation Mitigation","created":"2024-01-12","cited_by_count":9,"area":null},{"id":"2405.16820","title":"Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2410.02062","title":"TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2506.12044","title":"Why Do Some Inputs Break Low-Bit LLM Quantization?","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2310.19531","title":"MiLe Loss: a New Entropy-Weighed Loss for Mitigating the Bias of Learning Difficulties in Large Language Models","created":"2023-10-30","cited_by_count":8,"area":null},{"id":"2410.05315","title":"PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms","created":"2024-10-05","cited_by_count":8,"area":null},{"id":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8,"area":null}],"next_cursor":"100"}