{"total":155,"rows":[{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"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":"2409.09756","title":"MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformation","created":"2024-09-15","cited_by_count":56,"area":null},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2502.01563","title":"Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding","created":"2025-02-03","cited_by_count":47,"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":"2406.15486","title":"SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention","created":"2024-06-17","cited_by_count":39,"area":null},{"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":"2312.15159","title":"Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference","created":"2023-12-23","cited_by_count":33,"area":null},{"id":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32,"area":null},{"id":"2409.16694","title":"A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms","created":"2024-09-25","cited_by_count":31,"area":null},{"id":"2407.10960","title":"Fast Matrix Multiplications for Lookup Table-Quantized LLMs","created":"2024-07-15","cited_by_count":29,"area":null},{"id":"2411.05282","title":"MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization","created":"2024-11-08","cited_by_count":28,"area":null},{"id":"2603.05498","title":"The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks","created":"2026-03-05","cited_by_count":27,"area":null},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"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":"2508.14896","title":"Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs","created":"2025-08-20","cited_by_count":23,"area":null},{"id":"2502.05003","title":"QuEST: Stable Training of LLMs with 1-Bit Weights and Activations","created":"2025-02-07","cited_by_count":22,"area":null},{"id":"2411.09909","title":"AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference","created":"2024-11-15","cited_by_count":19,"area":null},{"id":"2411.16102","title":"BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2405.03103","title":"Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2411.11745","title":"BitMoD: Bit-serial Mixture-of-Datatype LLM Acceleration","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2411.17178","title":"LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization","created":"2024-11-26","cited_by_count":17,"area":null},{"id":"2511.04063","title":"DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2404.04815","title":"Allo: A Programming Model for Composable Accelerator Design","created":"2024-04-07","cited_by_count":16,"area":null},{"id":"2406.09904","title":"QQQ: Quality Quattuor-Bit Quantization for Large Language Models","created":"2024-06-14","cited_by_count":16,"area":null},{"id":"2412.14590","title":"MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design","created":"2024-12-19","cited_by_count":16,"area":null},{"id":"2502.18755","title":"M-ANT: Efficient Low-bit Group Quantization for LLMs via Mathematically Adaptive Numerical Type","created":"2025-02-26","cited_by_count":16,"area":null},{"id":"2601.07475","title":"ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs","created":"2026-01-12","cited_by_count":15,"area":null},{"id":"2406.16635","title":"ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models","created":"2024-06-24","cited_by_count":13,"area":null},{"id":"2407.08044","title":"RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2410.05265","title":"PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization","created":"2024-10-07","cited_by_count":12,"area":null},{"id":"2506.13045","title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2505.01043","title":"Low-Precision Training of Large Language Models: Methods, Challenges, and Opportunities","created":"2025-05-02","cited_by_count":11,"area":null},{"id":"2508.02343","title":"MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models","created":"2025-08-04","cited_by_count":11,"area":null},{"id":"2403.09059","title":"LAMP: A Language Model on the Map","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2504.14152","title":"FGMP: Fine-Grained Mixed-Precision Weight and Activation Quantization for Hardware-Accelerated LLM Inference","created":"2025-04-19","cited_by_count":9,"area":null},{"id":"2508.19432","title":"Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs","created":"2025-08-26","cited_by_count":9,"area":null},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","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":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2601.19213","title":"M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2409.01366","title":"CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification","created":"2024-09-02","cited_by_count":7,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2410.15116","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2411.09510","title":"Communication Compression for Tensor Parallel LLM Inference","created":"2024-11-14","cited_by_count":7,"area":null},{"id":"2501.04052","title":"RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping","created":"2025-01-06","cited_by_count":7,"area":null},{"id":"2502.05376","title":"LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2410.12168","title":"COMET: Towards Partical W4A4KV4 LLMs Serving","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2412.04180","title":"SKIM: Any-bit Quantization Pushing The Limits of Post-Training Quantization","created":"2024-12-05","cited_by_count":6,"area":null},{"id":"2502.08141","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","created":"2025-02-12","cited_by_count":6,"area":null},{"id":"2510.08544","title":"SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2512.03383","title":"UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2404.09356","title":"LLeMpower: Understanding Disparities in the Control and Access of Large Language Models","created":"2024-04-14","cited_by_count":5,"area":null},{"id":"2409.20361","title":"Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2502.01070","title":"An Inquiry into Datacenter TCO for LLM Inference with FP8","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2505.00347","title":"Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics","created":"2025-05-01","cited_by_count":5,"area":null},{"id":"2505.03802","title":"Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2603.25284","title":"SliderQuant: Accurate Post-Training Quantization for LLMs","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2405.18258","title":"Text-only Synthesis for Image Captioning","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2501.13331","title":"Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring","created":"2025-01-23","cited_by_count":4,"area":null},{"id":"2503.03777","title":"FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2503.04704","title":"Universality of Layer-Level Entropy-Weighted Quantization Beyond Model Architecture and Size","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2505.23520","title":"AnchorAttention: Difference-Aware Sparse Attention with Stripe Granularity","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2609.00097","title":"Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding","created":"2026-08-31","cited_by_count":4,"area":null},{"id":"2410.19262","title":"Autonomous Building Cyber-Physical Systems Using Decentralized Autonomous Organizations, Digital Twins, and Large Language Model","created":"2024-10-25","cited_by_count":3,"area":null},{"id":"2506.22776","title":"Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2507.16872","title":"CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage","created":"2025-07-22","cited_by_count":3,"area":null},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2511.04002","title":"Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing","created":"2025-11-06","cited_by_count":3,"area":null},{"id":"2511.06838","title":"P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2606.01556","title":"TwinQuant: Learnable Subspace Decomposition for 4-Bit LLM Quantization","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2606.15652","title":"MosaicQuant: Inlier-Outlier Disaggregation for Unified 4-Bit LLM Quantization","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2403.13112","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2412.07902","title":"Low-Rank Correction for Quantized LLMs","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2505.19349","title":"DECA: A Near-Core LLM Decompression Accelerator Grounded on a 3D Roofline Model","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2505.23615","title":"Learning Interpretable Differentiable Logic Networks for Tabular Regression","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.01967","title":"Turning LLM Activations Quantization-Friendly","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2506.20251","title":"Q-resafe: Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models","created":"2025-06-25","cited_by_count":2,"area":null},{"id":"2509.26534","title":"Rearchitecting Datacenter Lifecycle for AI: A TCO-Driven Framework","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.14823","title":"FraQAT: Quantization Aware Training with Fractional bits","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2510.19498","title":"Energy-Efficient and Dequantization-Free Q-LLMs: A Spiking Neural Network Approach to Salient Value Mitigation","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.02546","title":"D$^2$Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.17681","title":"LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2603.08747","title":"Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.18137","title":"AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2606.01850","title":"Does Compression Preserve Uncertainty? A Unified Benchmark for Quantized and Sparse LLMs via Conformal Prediction","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2609.06161","title":"All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2409.14206","title":"AI Assistants for Spaceflight Procedures: Combining Generative Pre-Trained Transformer and Retrieval-Augmented Generation on Knowledge Graphs With Augmented Reality Cues","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2503.17783","title":"Energy-Aware LLMs: A step towards sustainable AI for downstream applications","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2504.05352","title":"Achieving binary weight and activation for LLMs using Post-Training Quantization","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2508.19087","title":"APT-LLM: Exploiting Arbitrary-Precision Tensor Core Computing for LLM Acceleration","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.02822","title":"FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2510.16028","title":"TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks","created":"2025-10-15","cited_by_count":1,"area":null}],"next_cursor":"100"}