{"total":52,"rows":[{"id":"2408.14690","title":"Training-Free Activation Sparsity in Large Language Models","created":"2024-08-26","cited_by_count":55,"area":"inference"},{"id":"2509.24663","title":"InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation","created":"2025-09-29","cited_by_count":32,"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":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2507.00390","title":"MoNE: Replacing Redundant Experts with Lightweight Novices for Structured Pruning of MoE","created":"2025-07-01","cited_by_count":13,"area":"moe"},{"id":"2509.20241","title":"Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling","created":"2025-09-24","cited_by_count":13,"area":null},{"id":"2505.11415","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2025-05-16","cited_by_count":11,"area":"moe"},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10,"area":"inference"},{"id":"2503.18773","title":"BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache","created":"2025-03-24","cited_by_count":8,"area":"inference"},{"id":"2508.03351","title":"SalQ-VLM: Fine-Grained Saliency-Guided Quantization for Vision-Language Models","created":"2025-08-05","cited_by_count":8,"area":"mllm"},{"id":"2410.07002","title":"CursorCore: Assist Programming through Aligning Anything","created":"2024-10-09","cited_by_count":7,"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":"2605.02404","title":"Statistically-Lossless Quantization of Large Language Models","created":"2026-05-04","cited_by_count":6,"area":"inference"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2511.10054","title":"BuddyMoE: Exploiting Expert Redundancy to Accelerate Memory-Constrained Mixture-of-Experts Inference","created":"2025-11-13","cited_by_count":5,"area":"moe"},{"id":"2501.18015","title":"A Proximal Operator for Inducing 2:4-Sparsity","created":"2025-01-29","cited_by_count":4,"area":null},{"id":"2511.06174","title":"LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs","created":"2025-11-09","cited_by_count":4,"area":"inference"},{"id":"2501.06417","title":"DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory","created":"2025-01-11","cited_by_count":3,"area":null},{"id":"2601.15710","title":"FlexLLM: Composable HLS Library for Flexible Hybrid LLM Accelerator Design","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2601.16536","title":"W4A16 Mixed-Precision Matrix Multiplication on Decoupled Architecture: Kernel Design and Memory Bottleneck Analysis for Ascend NPUs","created":"2026-01-23","cited_by_count":3,"area":null},{"id":"2602.03537","title":"MatGPTQ: Efficient and Accurate Inference over Nested Quantized Models","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2504.16214","title":"Hexcute: A Compiler Framework for Automating Layout Synthesis in GPU Programs","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2509.04897","title":"PLaMo 2 Technical Report","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2501.13111","title":"iServe: An Intent-based Serving System for LLMs","created":"2025-01-08","cited_by_count":1,"area":"inference"},{"id":"2602.17693","title":"A Case Study of Selected PTQ Baselines for Reasoning LLMs on Ascend NPU","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2602.18568","title":"RPU -- A Reasoning Processing Unit","created":"2026-02-20","cited_by_count":1,"area":"lr"},{"id":"2603.19296","title":"TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.13806","title":"Robust Ultra Low-Bit Post-Training Quantization via Stable Diagonal Curvature Estimate","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.13915","title":"Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference","created":"2026-05-13","cited_by_count":1,"area":"inference"},{"id":"2605.16423","title":"Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2606.23419","title":"GRINQH: Graded Input-based Quantization Hierarchy for Efficient LLM Generation","created":"2026-06-22","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":"2609.30820","title":"Quantizing Looped Transformers: Feedback Exposure and Calibration Blindness","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2412.07067","title":"MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems","created":"2024-12-10","cited_by_count":0,"area":"moe"},{"id":"2509.15206","title":"Fair-GPTQ: Bias-Aware Quantization for Large Language Models","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2511.03586","title":"PerfDojo: Automated ML Library Generation for Heterogeneous Architectures","created":"2025-11-05","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":"2605.15626","title":"IO-SVD: Input-Output Whitened SVD for Adaptive-Rank LLM Compression","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2606.00079","title":"BitsMoE: Efficient Spectral Energy-Guided Bit Allocation for MoE LLM Quantization","created":"2026-05-22","cited_by_count":0,"area":"moe"},{"id":"2606.04063","title":"LLM Compression with Jointly Optimizing Architectural and Quantization choices","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.09682","title":"AutoMegaKernel: A Statically-Checked Agent Harness for Self-Retargeting Megakernel Synthesis","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.11244","title":"SPEAR: A System for Post-Quantization Error-Adaptive Recovery Enabling Efficient Low-Bit LLM Serving","created":"2026-06-04","cited_by_count":0,"area":"inference"},{"id":"2607.26316","title":"Route-Block Membership Selects Packed-AWQ Arithmetic: A Controlled Single-Fixture Mechanism Study","created":"2026-07-28","cited_by_count":0,"area":"moe"},{"id":"2608.06763","title":"CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.12932","title":"FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving","created":"2026-08-13","cited_by_count":0,"area":"vla"},{"id":"2608.15383","title":"Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference","created":"2026-08-15","cited_by_count":0,"area":"moe"},{"id":"2608.24070","title":"Compression Trinity: Exploring Sparsity, Quantization, and Low-Rank Approximations for LLM Compression","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.07901","title":"Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight Compression","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.11687","title":"Structured Transforms for Low-Overhead Quantization of Language Models","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.26333","title":"Disaggregated Quantization: Specializing LLM Prefill and Decode","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.35465","title":"Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.02241","title":"Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts","created":"2026-09-29","cited_by_count":0,"area":"moe"}],"next_cursor":null}