{"total":95,"rows":[{"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":"2502.17578","title":"How Do Large Language Monkeys Get Their Power (Laws)?","created":"2025-02-24","cited_by_count":43,"area":"safety"},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2502.05172","title":"Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient","created":"2025-02-07","cited_by_count":31,"area":"moe"},{"id":"2412.02573","title":"Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":23,"area":"mllm"},{"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":"2411.17691","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":"2510.25602","title":"INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats","created":"2025-10-29","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":"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":"2501.18107","title":"Scaling Inference-Efficient Language Models","created":"2025-01-30","cited_by_count":16,"area":null},{"id":"2503.22879","title":"Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models","created":"2025-03-28","cited_by_count":16,"area":"ssm"},{"id":"2510.06213","title":"Training Dynamics Impact Post-Training Quantization Robustness","created":"2025-10-07","cited_by_count":15,"area":null},{"id":"2502.00498","title":"MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing","created":"2025-02-01","cited_by_count":13,"area":"lr"},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2509.24244","title":"Model Merging Scaling Laws in Large Language Models","created":"2025-09-29","cited_by_count":12,"area":null},{"id":"2605.01640","title":"Prescriptive Scaling Laws for Data Constrained Training","created":"2026-05-02","cited_by_count":12,"area":null},{"id":"2502.16440","title":"Compression Scaling Laws:Unifying Sparsity and Quantization","created":"2025-02-23","cited_by_count":11,"area":null},{"id":"2506.08415","title":"Improved Scaling Laws in Linear Regression via Data Reuse","created":"2025-06-10","cited_by_count":11,"area":null},{"id":"2509.23324","title":"Scaling LLM Test-Time Compute with Mobile NPU on Smartphones","created":"2025-09-27","cited_by_count":11,"area":"lr"},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"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":"2509.25087","title":"Scaling with Collapse: Efficient and Predictable Training of LLM Families","created":"2025-09-29","cited_by_count":9,"area":null},{"id":"2501.02423","title":"Scaling Laws for Floating Point Quantization Training","created":"2025-01-05","cited_by_count":8,"area":null},{"id":"2501.12391","title":"Physics of Skill Learning","created":"2025-01-21","cited_by_count":8,"area":null},{"id":"2602.06797","title":"Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay","created":"2026-02-06","cited_by_count":8,"area":null},{"id":"2509.00454","title":"Universal Properties of Activation Sparsity in Modern Large Language Models","created":"2025-08-30","cited_by_count":7,"area":null},{"id":"2505.21732","title":"LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2506.10972","title":"Predictable Scale: Part II, Farseer: A Refined Scaling Law in Large Language Models","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2510.11004","title":"Automating Structural Engineering Workflows with Large Language Model Agents","created":"2025-10-13","cited_by_count":6,"area":"agents"},{"id":"2601.23261","title":"TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training","created":"2026-01-30","cited_by_count":6,"area":null},{"id":"2602.07712","title":"Towards Robust Scaling Laws for Optimizers","created":"2026-02-07","cited_by_count":6,"area":null},{"id":"2602.21545","title":"MUON+: Towards More Effective Muon via One Additional Normalization Step for LLM Pre-training","created":"2026-02-25","cited_by_count":6,"area":null},{"id":"2502.12051","title":"How to Upscale Neural Networks with Scaling Law? A Survey and Practical Guidelines","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.18724","title":"LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2506.01863","title":"Unified Scaling Laws for Compressed Representations","created":"2025-06-02","cited_by_count":5,"area":null},{"id":"2510.12077","title":"Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory","created":"2025-10-14","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":"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":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2509.22935","title":"Compute-Optimal Quantization-Aware Training","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2510.10964","title":"Not All Bits Are Equal: Scale-Dependent Memory Optimization Strategies for Reasoning Models","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2510.18245","title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2510.18784","title":"CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2501.02156","title":"The Race to Efficiency: A New Perspective on AI Scaling Laws","created":"2025-01-04","cited_by_count":3,"area":null},{"id":"2510.02228","title":"xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2511.07892","title":"A Generalized Spectral Framework to Expain Neural Scaling and Compression Dynamics","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2602.20433","title":"Disentangling Geometry, Performance, and Training in Language Models","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2605.17471","title":"WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2504.04342","title":"Pruning Laws for Large Language Models","created":"2025-04-06","cited_by_count":2,"area":"moe"},{"id":"2505.22811","title":"Highly Efficient and Effective LLMs with Multi-Boolean Architectures","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","cited_by_count":2,"area":"lr"},{"id":"2507.23035","title":"OASIS: Outlier-Aware LUT-Based GEMM with Dual-Side Quantization for LLM Inference Acceleration","created":"2025-07-30","cited_by_count":2,"area":"inference"},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2509.25380","title":"Predicting Training Re-evaluation Curves Enables Effective Data Curriculums for LLMs","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.02721","title":"Hyperparameter Loss Surfaces Are Simple Near their Optima","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2604.14629","title":"Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models","created":"2026-04-16","cited_by_count":2,"area":"mllm"},{"id":"2606.10520","title":"UniSVQ: 2-bit Unified Scalar-Vector Quantization","created":"2026-06-09","cited_by_count":2,"area":"inference"},{"id":"2411.12357","title":"A Layered Architecture for Developing and Enhancing Capabilities in Large Language Model-based Software Systems","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2505.07783","title":"Relative Overfitting and Accept-Reject Framework","created":"2025-05-12","cited_by_count":1,"area":null},{"id":"2508.06753","title":"Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2509.25996","title":"CAST: Continuous and Differentiable Semi-Structured Sparsity-Aware Training for Large Language Models","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2602.15563","title":"1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.01599","title":"Boosting Entropy with Bell Box Quantization","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2605.23591","title":"Asymmetric Scaling Laws from Sparse Features","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.27435","title":"When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.10154","title":"Quality Is Not a Safety Proxy Under Quantization","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2607.02893","title":"Variable Bit-width Quantization: Learning Per-Group Precision for \"Bigger-but-Smaller\" Language Models","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2608.06564","title":"Which Decisions Low-Bit Quantization Breaks, and How to Predict Them","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2608.13966","title":"QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2507.03300","title":"LRM-1B: Towards Large Routing Model","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2507.06079","title":"QS4D: Quantization-aware training for efficient hardware deployment of structured state-space sequential models","created":"2025-07-08","cited_by_count":0,"area":"ssm"},{"id":"2508.06617","title":"Generalizing Scaling Laws for Dense and Sparse Large Language Models","created":"2025-08-08","cited_by_count":0,"area":"moe"},{"id":"2510.08999","title":"SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.23198","title":"PTPP-Aware Adaptation Scaling Laws: Predicting Domain-Adaptation Performance at Unseen Pre-Training Budgets","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2512.02409","title":"Data Curation Through the Lens of Spectral Dynamics: Static Limits, Dynamic Acceleration, and Practical Oracles","created":"2025-12-02","cited_by_count":0,"area":"alignment"},{"id":"2512.10427","title":"Renormalizable Spectral-Shell Dynamics as the Origin of Neural Scaling Laws","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.18209","title":"When Does Learning Renormalize? Sufficient Conditions for Power Law Spectral Dynamics","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2601.10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.22339","title":"Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits","created":"2026-03-21","cited_by_count":0,"area":null},{"id":"2603.28507","title":"Continued AI Scaling Requires Repeated Efficiency Doublings","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.18085","title":"Predicting LLM Compression Degradation from Spectral Statistics","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.20079","title":"On the Quantization Robustness of Diffusion Language Models in Coding Benchmarks","created":"2026-04-22","cited_by_count":0,"area":"diffusion"},{"id":"2605.09189","title":"Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.14929","title":"A Hardware-Aware, Per-Layer Methodology for Post-Training Quantization of Large Language Models","created":"2026-05-14","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":"2609.08637","title":"Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.21666","title":"Samsone: A Family of Open Small Audio Language Models for On-Device Inference","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.32659","title":"Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32902","title":"Linger and Lose: Knowledge Collapse in Low-Bit Language Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.39813","title":"Backward-State Policy Is Part of the Learning Algorithm","created":"2026-09-30","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":"2610.05329","title":"Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.17637","title":"Mixed Precision Scaling Laws for Quantized Pretraining","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}