{"total":167,"rows":[{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"area":null},{"id":"2412.00447","title":"ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models","created":"2024-11-30","cited_by_count":89,"area":"mllm"},{"id":"2406.12275","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","created":"2024-06-18","cited_by_count":79,"area":"mllm"},{"id":"2502.21079","title":"Training-free and Adaptive Sparse Attention for Efficient Long Video Generation","created":"2025-02-28","cited_by_count":69,"area":"diffusion"},{"id":"2504.02692","title":"GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration","created":"2025-04-03","cited_by_count":60,"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":"2505.05422","title":"TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation","created":"2025-05-08","cited_by_count":51,"area":null},{"id":"2501.16383","title":"RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations","created":"2025-01-25","cited_by_count":46,"area":"inference"},{"id":"2412.14363","title":"ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals","created":"2024-12-18","cited_by_count":36,"area":null},{"id":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2602.20309","title":"QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models","created":"2026-02-23","cited_by_count":30,"area":"vla"},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2407.06794","title":"Towards Accurate Post-Training Quantization of Vision Transformers via Error Reduction","created":"2024-07-09","cited_by_count":23,"area":null},{"id":"2502.09720","title":"NestQuant: Nested Lattice Quantization for Matrix Products and LLMs","created":"2025-02-13","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":"2511.04214","title":"Block Rotation is All You Need for MXFP4 Quantization","created":"2025-11-06","cited_by_count":20,"area":null},{"id":"2408.03291","title":"DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers","created":"2024-08-06","cited_by_count":19,"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":"2503.06564","title":"TR-DQ: Time-Rotation Diffusion Quantization","created":"2025-03-09","cited_by_count":19,"area":"diffusion"},{"id":"2410.06535","title":"Happy: A Debiased Learning Framework for Continual Generalized Category Discovery","created":"2024-10-09","cited_by_count":18,"area":null},{"id":"2506.16054","title":"PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models","created":"2025-06-19","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":"2511.10645","title":"ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference","created":"2025-11-13","cited_by_count":17,"area":"lr"},{"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":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2510.16292","title":"QSVD: Efficient Low-rank Approximation for Unified Query-Key-Value Weight Compression in Low-Precision Vision-Language Models","created":"2025-10-18","cited_by_count":16,"area":"mllm"},{"id":"2503.18599","title":"Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization","created":"2025-03-24","cited_by_count":14,"area":"inference"},{"id":"2406.13474","title":"BoA: Attention-aware Post-training Quantization without Backpropagation","created":"2024-06-19","cited_by_count":12,"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":"2503.01483","title":"KurTail : Kurtosis-based LLM Quantization","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2508.03485","title":"LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation","created":"2025-08-05","cited_by_count":12,"area":"diffusion"},{"id":"2603.07904","title":"DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models","created":"2026-03-09","cited_by_count":12,"area":"vla"},{"id":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","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":"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":"2601.22347","title":"Pushing the Limits of Block Rotations in Post-Training Quantization","created":"2026-01-29","cited_by_count":11,"area":null},{"id":"2603.11487","title":"Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks","created":"2026-03-12","cited_by_count":11,"area":null},{"id":"2505.21366","title":"PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2506.13329","title":"EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization","created":"2025-06-16","cited_by_count":10,"area":"moe"},{"id":"2508.03616","title":"Hidden Dynamics of Massive Activations in Transformer Training","created":"2025-08-05","cited_by_count":10,"area":null},{"id":"2509.09679","title":"ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms","created":"2025-09-11","cited_by_count":10,"area":null},{"id":"2510.10432","title":"Hierarchical LoRA MoE for Efficient CTR Model Scaling","created":"2025-10-12","cited_by_count":10,"area":"moe"},{"id":"2510.13855","title":"Harnessing Consistency for Robust Test-Time LLM Ensemble","created":"2025-10-12","cited_by_count":10,"area":null},{"id":"2511.11663","title":"SpecQuant: Spectral Decomposition and Adaptive Truncation for Ultra-Low-Bit LLMs Quantization","created":"2025-11-11","cited_by_count":10,"area":null},{"id":"2601.09555","title":"Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats","created":"2026-01-14","cited_by_count":10,"area":null},{"id":"2603.24840","title":"Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR","created":"2026-03-25","cited_by_count":10,"area":"lr"},{"id":"2503.13565","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts","created":"2025-03-17","cited_by_count":9,"area":"inference"},{"id":"2411.09852","title":"InterFormer: Effective Heterogeneous Interaction Learning for Click-Through Rate Prediction","created":"2024-11-15","cited_by_count":8,"area":null},{"id":"2509.01229","title":"LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving","created":"2025-09-01","cited_by_count":8,"area":"inference"},{"id":"2509.20214","title":"Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment","created":"2025-09-24","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":"2603.17809","title":"Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients","created":"2026-03-18","cited_by_count":8,"area":"mllm"},{"id":"2604.17789","title":"DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization","created":"2026-04-20","cited_by_count":8,"area":"inference"},{"id":"2410.04808","title":"LPZero: Language Model Zero-cost Proxy Search from Zero","created":"2024-10-07","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":"2504.05316","title":"Scale Up Composed Image Retrieval Learning via Modification Text Generation","created":"2025-02-21","cited_by_count":7,"area":null},{"id":"2505.14742","title":"Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2506.09932","title":"HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations","created":"2025-06-11","cited_by_count":7,"area":"diffusion"},{"id":"2508.15008","title":"Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2512.03673","title":"ConvRot: Rotation-Based Plug-and-Play 4-bit Quantization for Diffusion Transformers","created":"2025-12-03","cited_by_count":7,"area":"diffusion"},{"id":"2503.15465","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","created":"2025-03-19","cited_by_count":6,"area":"diffusion"},{"id":"2506.02006","title":"MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing","created":"2025-05-24","cited_by_count":6,"area":"inference"},{"id":"2507.01299","title":"La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation","created":"2025-07-02","cited_by_count":6,"area":null},{"id":"2509.22944","title":"SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights","created":"2025-09-26","cited_by_count":6,"area":null},{"id":"2603.16590","title":"BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization","created":"2026-03-17","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":"2607.02461","title":"OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers","created":"2026-07-02","cited_by_count":6,"area":"diffusion"},{"id":"2501.16385","title":"FBQuant: FeedBack Quantization for Large Language Models","created":"2025-01-25","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":"2506.15689","title":"BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2510.13500","title":"MedREK: Retrieval-Based Editing for Medical LLMs with Key-Aware Prompts","created":"2025-10-15","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":"2510.23926","title":"Improving the Straight-Through Estimator with Zeroth-Order Information","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2602.09883","title":"AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization","created":"2026-02-10","cited_by_count":5,"area":"diffusion"},{"id":"2603.04800","title":"MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models","created":"2026-03-05","cited_by_count":5,"area":"mllm"},{"id":"2603.25284","title":"SliderQuant: Accurate Post-Training Quantization for LLMs","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2412.18135","title":"LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment","created":"2024-12-24","cited_by_count":4,"area":null},{"id":"2501.19107","title":"Brain network science modelling of sparse neural networks enables Transformers and LLMs to perform as fully connected","created":"2025-01-31","cited_by_count":4,"area":null},{"id":"2502.15779","title":"Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizer","created":"2025-02-17","cited_by_count":4,"area":"inference"},{"id":"2503.19353","title":"QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2506.01352","title":"TAH-QUANT: Effective Activation Quantization in Pipeline Parallelism over Slow Network","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2506.05413","title":"SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2506.12040","title":"BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook","created":"2025-05-24","cited_by_count":4,"area":null},{"id":"2508.03668","title":"CTR-Sink: Attention Sink for Language Models in Click-Through Rate Prediction","created":"2025-08-05","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":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2603.22370","title":"FAAR: Format-Aware Adaptive Rounding for NVFP4","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2505.03810","title":"Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2509.24416","title":"CLQ: Cross-Layer Guided Orthogonal-based Quantization for Diffusion Transformers","created":"2025-09-29","cited_by_count":3,"area":"diffusion"},{"id":"2511.07842","title":"Safety-Preserving PTQ via Contrastive Alignment Loss","created":"2025-11-11","cited_by_count":3,"area":"safety"},{"id":"2511.17637","title":"PocketLLM: Ultimate Compression of Large Language Models via Meta Networks","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2601.19675","title":"LoPRo: Enhancing Low-Rank Quantization via Permuted Block-Wise Rotation","created":"2026-01-27","cited_by_count":3,"area":null},{"id":"2602.02110","title":"An Empirical Study of World Model Quantization","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2602.04929","title":"TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2603.18426","title":"Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.02570","title":"WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models","created":"2026-04-02","cited_by_count":3,"area":"mllm"},{"id":"2609.02108","title":"Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models","created":"2026-09-02","cited_by_count":3,"area":"diffusion"}],"next_cursor":"100"}