{"total":55,"rows":[{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919,"area":null},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121,"area":null},{"id":"2206.01861","title":"ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers","created":"2022-06-04","cited_by_count":526,"area":null},{"id":"2307.13304","title":"QuIP: 2-Bit Quantization of Large Language Models With Guarantees","created":"2023-07-25","cited_by_count":414,"area":null},{"id":"2203.07540","title":"ScienceWorld: Is your Agent Smarter than a 5th Grader?","created":"2022-03-14","cited_by_count":327,"area":"lr"},{"id":"2312.16886","title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","created":"2023-12-28","cited_by_count":122,"area":"mllm"},{"id":"2501.13987","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","created":"2025-01-23","cited_by_count":97,"area":null},{"id":"2102.03315","title":"Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge","created":"2021-02-05","cited_by_count":80,"area":null},{"id":"2403.15447","title":"Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression","created":"2024-03-18","cited_by_count":57,"area":null},{"id":"2504.09629","title":"Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization","created":"2025-04-13","cited_by_count":41,"area":null},{"id":"2310.09259","title":"QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models","created":"2023-10-13","cited_by_count":39,"area":null},{"id":"2311.08545","title":"Efficient Continual Pre-training for Building Domain Specific Large Language Models","created":"2023-11-14","cited_by_count":34,"area":null},{"id":"2406.05981","title":"ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2501.13484","title":"MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods","created":"2025-01-23","cited_by_count":29,"area":"ssm"},{"id":"2402.00858","title":"Can Large Language Models Understand Context?","created":"2024-02-01","cited_by_count":26,"area":null},{"id":"2405.17849","title":"I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models","created":"2024-05-28","cited_by_count":23,"area":null},{"id":"2506.17088","title":"Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation","created":"2025-06-20","cited_by_count":21,"area":"lr"},{"id":"2410.15567","title":"Pruning Foundation Models for High Accuracy without Retraining","created":"2024-10-21","cited_by_count":20,"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":"2403.02775","title":"EasyQuant: An Efficient Data-free Quantization Algorithm for LLMs","created":"2024-03-05","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":"2310.09499","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","created":"2023-10-14","cited_by_count":16,"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":"2312.08583","title":"ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2211.11586","title":"Random-LTD: Random and Layerwise Token Dropping Brings Efficient Training for Large-scale Transformers","created":"2022-11-17","cited_by_count":11,"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":"2602.11184","title":"KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models","created":"2026-01-30","cited_by_count":8,"area":"moe"},{"id":"2505.23807","title":"DLP: Dynamic Layerwise Pruning in Large Language Models","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2604.08896","title":"GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing","created":"2026-04-10","cited_by_count":6,"area":"mllm"},{"id":"2503.21135","title":"DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation","created":"2025-03-27","cited_by_count":4,"area":"moe"},{"id":"2505.03803","title":"RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization","created":"2025-05-02","cited_by_count":4,"area":null},{"id":"2203.02753","title":"Feeding What You Need by Understanding What You Learned","created":"2022-03-05","cited_by_count":3,"area":null},{"id":"2507.17417","title":"A Comprehensive Evaluation on Quantization Techniques for Large Language Models","created":"2025-07-23","cited_by_count":3,"area":null},{"id":"2509.22299","title":"HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space","created":"2025-09-26","cited_by_count":3,"area":"moe"},{"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":"2506.04255","title":"HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization","created":"2025-06-01","cited_by_count":2,"area":"agents"},{"id":"2506.05664","title":"BAQ: Efficient Bit Allocation Quantization for Large Language Models","created":"2025-06-06","cited_by_count":2,"area":null},{"id":"2510.01240","title":"RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2601.05684","title":"FLRQ: Faster LLM Quantization with Flexible Low-Rank Matrix Sketching","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2605.10793","title":"ConQuR: Corner Aligned Activation Quantization via Optimized Rotations for LLMs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2109.05168","title":"Semantic Categorization of Social Knowledge for Commonsense Question Answering","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2305.15130","title":"On Degrees of Freedom in Defining and Testing Natural Language Understanding","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2601.17680","title":"$\\infty$-MoE: Generalizing Mixture of Experts to Infinite Experts","created":"2026-01-25","cited_by_count":1,"area":"moe"},{"id":"2604.19520","title":"SimDiff: Depth Pruning via Similarity and Difference","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2605.09281","title":"TileQ: Efficient Low-Rank Quantization of Mixture-of-Experts with 2D Tiling","created":"2026-05-10","cited_by_count":1,"area":"moe"},{"id":"2409.02481","title":"PQ-GCN: Enhancing Text Graph Question Classification with Phrase Features","created":"2024-09-04","cited_by_count":0,"area":null},{"id":"2501.16376","title":"SwiftPrune: Hessian-Free Weight Pruning for Large Language Models","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2604.06154","title":"Exclusive Unlearning","created":"2026-04-07","cited_by_count":0,"area":"safety"},{"id":"2605.18800","title":"Theory-optimal Quantization Based on Flatness","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.26175","title":"InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.20434","title":"Break Through the Compression Bottleneck: From Theory to Practice","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.24268","title":"Accuracy Hides How Language Models Fail: Measuring Failure States Under Matched Output Budgets","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.35579","title":"Output-aware Residual Stream Pruning for Large Language Models","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.20303","title":"SpectrumQuant: Spectrum Alignment for LLM Quantization","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}