{"total":112,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"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":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"id":"2306.07629","title":"SqueezeLLM: Dense-and-Sparse Quantization","created":"2023-06-13","cited_by_count":294,"area":null},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294,"area":null},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251,"area":null},{"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":"2209.13325","title":"Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models","created":"2022-09-27","cited_by_count":181,"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":"2109.04404","title":"All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality","created":"2021-09-09","cited_by_count":156,"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":"2310.00034","title":"PB-LLM: Partially Binarized Large Language Models","created":"2023-09-29","cited_by_count":83,"area":null},{"id":"2302.14017","title":"Full Stack Optimization of Transformer Inference: a Survey","created":"2023-02-27","cited_by_count":80,"area":null},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65,"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":"2205.11380","title":"Outliers Dimensions that Disrupt Transformers Are Driven by Frequency","created":"2022-05-23","cited_by_count":55,"area":null},{"id":"2411.07191","title":"The Super Weight in Large Language Models","created":"2024-11-11","cited_by_count":52,"area":null},{"id":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44,"area":null},{"id":"2406.06385","title":"Low-Rank Quantization-Aware Training for LLMs","created":"2024-06-10","cited_by_count":43,"area":null},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"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":"2302.00456","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","created":"2023-02-01","cited_by_count":33,"area":null},{"id":"2406.12016","title":"Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization","created":"2024-06-17","cited_by_count":33,"area":null},{"id":"2502.06415","title":"Systematic Outliers in Large Language Models","created":"2025-02-10","cited_by_count":33,"area":null},{"id":"2305.13417","title":"VISIT: Visualizing and Interpreting the Semantic Information Flow of Transformers","created":"2023-05-22","cited_by_count":32,"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":"2110.04504","title":"An Isotropy Analysis in the Multilingual BERT Embedding Space","created":"2021-10-09","cited_by_count":25,"area":null},{"id":"2202.12246","title":"Neural reality of argument structure constructions","created":"2022-02-24","cited_by_count":25,"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":"2601.22966","title":"A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training","created":"2026-01-30","cited_by_count":23,"area":null},{"id":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","cited_by_count":22,"area":null},{"id":"2405.14428","title":"Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2409.13652","title":"OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition","created":"2024-09-20","cited_by_count":20,"area":null},{"id":"2305.17446","title":"Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models","created":"2023-05-27","cited_by_count":19,"area":null},{"id":"2410.08113","title":"Robust AI-Generated Text Detection by Restricted Embeddings","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2306.00458","title":"Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity","created":"2023-06-01","cited_by_count":17,"area":null},{"id":"2303.11866","title":"Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning","created":"2023-03-21","cited_by_count":16,"area":"mllm"},{"id":"2502.00919","title":"Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings","created":"2025-02-02","cited_by_count":16,"area":null},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2310.17715","title":"Outlier Dimensions Encode Task-Specific Knowledge","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2502.15618","title":"Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing","created":"2025-02-21","cited_by_count":14,"area":null},{"id":"2503.08040","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","created":"2025-03-11","cited_by_count":14,"area":null},{"id":"2310.02065","title":"VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores","created":"2023-10-03","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":"2506.19697","title":"Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models","created":"2025-06-24","cited_by_count":13,"area":null},{"id":"2305.19358","title":"Stable Anisotropic Regularization","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2402.00024","title":"Can Large Language Models Understand Molecules?","created":"2024-01-05","cited_by_count":10,"area":null},{"id":"2405.19279","title":"Understanding and Minimising Outlier Features in Neural Network Training","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2404.02837","title":"Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models","created":"2024-04-03","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":"2509.26537","title":"The Loss Kernel: A Geometric Probe for Deep Learning Interpretability","created":"2025-09-30","cited_by_count":9,"area":null},{"id":"2209.00218","title":"Isotropic Representation Can Improve Dense Retrieval","created":"2022-09-01","cited_by_count":8,"area":null},{"id":"2405.18380","title":"Outlier-weighed Layerwise Sampling for LLM Fine-tuning","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2503.01874","title":"CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging","created":"2025-02-26","cited_by_count":8,"area":null},{"id":"2503.06518","title":"Towards Superior Quantization Accuracy: A Layer-sensitive Approach","created":"2025-03-09","cited_by_count":8,"area":"lr"},{"id":"2505.00598","title":"Fast and Low-Cost Genomic Foundation Models via Outlier Removal","created":"2025-05-01","cited_by_count":8,"area":null},{"id":"2508.17744","title":"Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks","created":"2025-08-25","cited_by_count":8,"area":null},{"id":"2408.08073","title":"Extracting Sentence Embeddings from Pretrained Transformer Models","created":"2024-08-15","cited_by_count":7,"area":null},{"id":"2505.17101","title":"A quantitative analysis of semantic information in deep representations of text and images","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2510.10238","title":"The Achilles' Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2601.04765","title":"Differential syntactic and semantic encoding in LLMs","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2406.01468","title":"Understanding Token Probability Encoding in Output Embeddings","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2505.24360","title":"Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning","created":"2025-05-30","cited_by_count":6,"area":"diffusion"},{"id":"2306.00014","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","created":"2023-05-30","cited_by_count":5,"area":null},{"id":"2406.15035","title":"Improving Interpretability and Robustness for the Detection of AI-Generated Images","created":"2024-06-21","cited_by_count":5,"area":null},{"id":"2411.15113","title":"Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion","created":"2024-11-22","cited_by_count":5,"area":"diffusion"},{"id":"2205.10696","title":"Life after BERT: What do Other Muppets Understand about Language?","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2403.20284","title":"LayerNorm: A key component in parameter-efficient fine-tuning","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2406.18832","title":"OutlierTune: Efficient Channel-Wise Quantization for Large Language Models","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2503.07654","title":"MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2406.11022","title":"Outlier Reduction with Gated Attention for Improved Post-training Quantization in Large Sequence-to-sequence Speech Foundation Models","created":"2024-06-16","cited_by_count":3,"area":"distill"},{"id":"2408.04162","title":"Semantics or spelling? Probing contextual word embeddings with orthographic noise","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2410.09637","title":"ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2501.04784","title":"Leveraging Registers in Vision Transformers for Robust Adaptation","created":"2025-01-08","cited_by_count":3,"area":null},{"id":"2503.21718","title":"Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2509.22536","title":"A Comprehensive FP8 Training Recipe for Reasoning-Enhanced Language Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2302.00378","title":"An Empirical Study on the Transferability of Transformer Modules in Parameter-Efficient Fine-Tuning","created":"2023-02-01","cited_by_count":2,"area":null},{"id":"2403.06497","title":"QuantTune: Optimizing Model Quantization with Adaptive Outlier-Driven Fine Tuning","created":"2024-03-11","cited_by_count":2,"area":null},{"id":"2502.10735","title":"Beyond One-Size-Fits-All Pruning via Evolutionary Metric Search for Large Language Models","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2509.20124","title":"Probability Signature: Bridging Data Semantics and Embedding Structure in Language Models","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.04547","title":"Activation Quantization of Vision Encoders Needs Prefixing Registers","created":"2025-10-06","cited_by_count":2,"area":"mllm"},{"id":"2607.18745","title":"Contraction-Gauge Preconditioning for Quantized Matrix Multiplication","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2204.08688","title":"DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks","created":"2022-04-19","cited_by_count":1,"area":null},{"id":"2407.12886","title":"Whitening Not Recommended for Classification Tasks in LLMs","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2410.07505","title":"CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2502.11932","title":"On Representational Dissociation of Language and Arithmetic in Large Language Models","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2505.08620","title":"Resource-Efficient Language Models: Quantization for Fast and Accessible Inference","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2505.16743","title":"TRIM: Achieving Extreme Sparsity with Targeted Row-wise Iterative Metric-driven Pruning","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2602.02891","title":"TraceNAS: Zero-shot LLM Pruning via Gradient Trace Correlation","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.10444","title":"The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2606.20743","title":"Massive Activations Are Architecturally Robust: A Controlled Scratch/Commitment Residual Stream Test","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.22007","title":"The Communication Map of a Transformer","created":"2026-08-22","cited_by_count":1,"area":"mechinterp"},{"id":"2109.13304","title":"On Isotropy Calibration of Transformers","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2205.12452","title":"Sparse*BERT: Sparse Models Generalize To New tasks and Domains","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2302.02291","title":"A Semantic Approach to Negation Detection and Word Disambiguation with Natural Language Processing","created":"2023-02-05","cited_by_count":0,"area":null},{"id":"2512.22307","title":"LLA: Enhancing Security and Privacy for Generative Models with Logic-Locked Accelerators","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2603.00029","title":"Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2605.01609","title":"Concepts Whisper: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations","created":"2026-05-02","cited_by_count":0,"area":"mechinterp"},{"id":"2606.03712","title":"When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models","created":"2026-06-02","cited_by_count":0,"area":null}],"next_cursor":"100"}