{"total":243,"rows":[{"id":"2407.11062","title":"EfficientQAT: Efficient Quantization-Aware Training for Large Language Models","created":"2024-07-10","cited_by_count":127,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2406.11903","title":"A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges","created":"2024-06-15","cited_by_count":90,"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":"2405.18886","title":"Compressing Large Language Models using Low Rank and Low Precision Decomposition","created":"2024-05-29","cited_by_count":59,"area":null},{"id":"2409.17066","title":"VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":57,"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":"2506.07900","title":"MiniCPM4: Ultra-Efficient LLMs on End Devices","created":"2025-06-09","cited_by_count":52,"area":null},{"id":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49,"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":"2504.12285","title":"BitNet b1.58 2B4T Technical Report","created":"2025-04-16","cited_by_count":38,"area":null},{"id":"2406.03287","title":"SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms","created":"2024-06-05","cited_by_count":31,"area":null},{"id":"2412.18653","title":"1.58-bit FLUX","created":"2024-12-24","cited_by_count":31,"area":null},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"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":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29,"area":null},{"id":"2405.21064","title":"Recurrent neural networks: vanishing and exploding gradients are not the end of the story","created":"2024-05-31","cited_by_count":25,"area":null},{"id":"2406.02528","title":"Scalable MatMul-free Language Modeling","created":"2024-06-04","cited_by_count":25,"area":null},{"id":"2407.10969","title":"Q-Sparse: All Large Language Models can be Fully Sparsely-Activated","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25,"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":"2412.09810","title":"The Complexity Dynamics of Grokking","created":"2024-12-13","cited_by_count":22,"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":"2502.11880","title":"Bitnet.cpp: Efficient Edge Inference for Ternary LLMs","created":"2025-02-17","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":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2411.17691","title":"Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens","created":"2024-11-26","cited_by_count":18,"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":"2504.18415","title":"BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs","created":"2025-04-25","cited_by_count":18,"area":null},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","cited_by_count":17,"area":null},{"id":"2411.04965","title":"BitNet a4.8: 4-bit Activations for 1-bit LLMs","created":"2024-11-07","cited_by_count":16,"area":null},{"id":"2410.05437","title":"ESPACE: Dimensionality Reduction of Activations for Model Compression","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2403.02694","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","created":"2024-03-05","cited_by_count":14,"area":null},{"id":"2410.13780","title":"Optimal Quantization for Matrix Multiplication","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2404.03021","title":"Blessing or curse? A survey on the Impact of Generative AI on Fake News","created":"2024-04-03","cited_by_count":12,"area":null},{"id":"2405.16528","title":"LoQT: Low-Rank Adapters for Quantized Pretraining","created":"2024-05-26","cited_by_count":12,"area":null},{"id":"2407.07093","title":"FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation","created":"2024-07-09","cited_by_count":12,"area":null},{"id":"2410.16144","title":"1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs","created":"2024-10-21","cited_by_count":12,"area":null},{"id":"2405.06419","title":"Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting","created":"2024-05-10","cited_by_count":11,"area":null},{"id":"2502.16440","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","created":"2025-02-23","cited_by_count":11,"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":"2405.10299","title":"HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models","created":"2024-05-16","cited_by_count":10,"area":null},{"id":"2406.09477","title":"Q-S5: Towards Quantized State Space Models","created":"2024-06-13","cited_by_count":10,"area":null},{"id":"2411.13757","title":"GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs","created":"2024-11-21","cited_by_count":10,"area":null},{"id":"2504.16266","title":"TeLLMe: An Energy-Efficient Ternary LLM Accelerator for Prefilling and Decoding on Edge FPGAs","created":"2025-04-22","cited_by_count":10,"area":null},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2407.00928","title":"FoldGPT: Simple and Effective Large Language Model Compression Scheme","created":"2024-07-01","cited_by_count":9,"area":null},{"id":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2411.03513","title":"Change Is the Only Constant: Dynamic LLM Slicing based on Layer Redundancy","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2412.15304","title":"TinyLLM: A Framework for Training and Deploying Language Models at the Edge Computers","created":"2024-12-19","cited_by_count":9,"area":null},{"id":"2501.10658","title":"LUT-DLA: Lookup Table as Efficient Extreme Low-Bit Deep Learning Accelerator","created":"2025-01-18","cited_by_count":9,"area":null},{"id":"2505.00850","title":"ICQuant: Index Coding enables Low-bit LLM Quantization","created":"2025-05-01","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":"2509.16989","title":"PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models","created":"2025-09-21","cited_by_count":9,"area":null},{"id":"2406.18051","title":"ViT-1.58b: Mobile Vision Transformers in the 1-bit Era","created":"2024-06-26","cited_by_count":8,"area":null},{"id":"2407.09527","title":"BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks","created":"2024-06-24","cited_by_count":8,"area":null},{"id":"2501.02423","title":"Scaling Laws for Floating Point Quantization Training","created":"2025-01-05","cited_by_count":8,"area":null},{"id":"2502.13179","title":"PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2503.18002","title":"Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2407.18908","title":"Wolf: Dense Video Captioning with a World Summarization Framework","created":"2024-07-26","cited_by_count":7,"area":null},{"id":"2411.07501","title":"LAuReL: Learned Augmented Residual Layer","created":"2024-11-12","cited_by_count":7,"area":null},{"id":"2504.07389","title":"Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression","created":"2025-04-10","cited_by_count":7,"area":null},{"id":"2601.21963","title":"Industrialized Deception: The Collateral Effects of LLM-Generated Misinformation on Digital Ecosystems","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2409.17092","title":"Accumulator-Aware Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2412.04787","title":"Direct Quantized Training of Language Models with Stochastic Rounding","created":"2024-12-06","cited_by_count":6,"area":null},{"id":"2502.16473","title":"TerEffic: Highly Efficient Ternary LLM Inference on FPGA","created":"2025-02-23","cited_by_count":6,"area":null},{"id":"2606.26650","title":"CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs","created":"2026-06-25","cited_by_count":6,"area":null},{"id":"2405.14446","title":"Worldwide Federated Training of Language Models","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2406.13170","title":"Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference","created":"2024-06-19","cited_by_count":5,"area":null},{"id":"2502.21001","title":"Towards Lossless Implicit Neural Representation via Bit Plane Decomposition","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2504.15208","title":"Compute-Optimal LLMs Provably Generalize Better With Scale","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2508.05571","title":"iFairy: the First 2-bit Complex LLM with All Parameters in $\\{\\pm1, \\pm i\\}$","created":"2025-08-07","cited_by_count":5,"area":null},{"id":"2510.23926","title":"Improving the Straight-Through Estimator with Zeroth-Order Information","created":"2025-10-27","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":"2405.02543","title":"Exploring Extreme Quantization in Spiking Language Models","created":"2024-05-04","cited_by_count":4,"area":null},{"id":"2405.13817","title":"Thermodynamic Natural Gradient Descent","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2405.18400","title":"Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2405.19065","title":"xTern: Energy-Efficient Ternary Neural Network Inference on RISC-V-Based Edge Systems","created":"2024-05-29","cited_by_count":4,"area":null},{"id":"2406.07247","title":"Dynamical Mean-Field Theory of Self-Attention Neural Networks","created":"2024-06-11","cited_by_count":4,"area":null},{"id":"2407.08597","title":"Learning Program Behavioral Models from Synthesized Input-Output Pairs","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2409.00297","title":"On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic","created":"2024-08-30","cited_by_count":4,"area":null},{"id":"2410.16926","title":"Pyramid Vector Quantization for LLMs","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2410.19103","title":"TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2411.01663","title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","created":"2024-11-03","cited_by_count":4,"area":null},{"id":"2502.11895","title":"Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2508.16703","title":"ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2510.03267","title":"PT$^2$-LLM: Post-Training Ternarization for Large Language Models","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2511.13676","title":"T-SAR: A Full-Stack Co-design for CPU-Only Ternary LLM Inference via In-Place SIMD ALU Reorganization","created":"2025-11-17","cited_by_count":4,"area":null},{"id":"2407.09503","title":"PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos","created":"2024-06-14","cited_by_count":3,"area":null},{"id":"2407.12036","title":"Exploring Advanced Large Language Models with LLMsuite","created":"2024-07-01","cited_by_count":3,"area":null},{"id":"2407.12819","title":"I've Got 99 Problems But FLOPS Ain't One","created":"2024-07-01","cited_by_count":3,"area":null},{"id":"2408.03414","title":"Logistic Regression makes small LLMs strong and explainable \"tens-of-shot\" classifiers","created":"2024-08-06","cited_by_count":3,"area":null},{"id":"2408.10230","title":"A General-Purpose Device for Interaction with LLMs","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2410.05911","title":"Accelerating Error Correction Code Transformers","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2410.14570","title":"Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2411.06360","title":"An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks","created":"2024-11-10","cited_by_count":3,"area":null},{"id":"2411.17309","title":"PIM-AI: A Novel Architecture for High-Efficiency LLM Inference","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2412.08291","title":"Code LLMs: A Taxonomy-based Survey","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2501.11847","title":"A Survey on Memory-Efficient Transformer-Based Model Training in AI for Science","created":"2025-01-21","cited_by_count":3,"area":null}],"next_cursor":"100"}