{"total":73,"rows":[{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2506.08889","title":"SeerAttention-R: Sparse Attention Adaptation for Long Reasoning","created":"2025-06-10","cited_by_count":30,"area":"lr"},{"id":"2504.11651","title":"70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)","created":"2025-04-15","cited_by_count":24,"area":"diffusion"},{"id":"2505.17941","title":"VeriThinker: Learning to Verify Makes Reasoning Model Efficient","created":"2025-05-23","cited_by_count":24,"area":"lr"},{"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":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2505.14302","title":"Scaling Law for Quantization-Aware Training","created":"2025-05-20","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":"2510.17238","title":"StreamingThinker: Large Language Models Can Think While Reading","created":"2025-10-20","cited_by_count":15,"area":"lr"},{"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":"2511.18643","title":"Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost","created":"2025-11-23","cited_by_count":10,"area":"inference"},{"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":"2601.14888","title":"What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study","created":"2026-01-21","cited_by_count":10,"area":"lr"},{"id":"2602.03560","title":"HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing","created":"2026-02-03","cited_by_count":10,"area":"moe"},{"id":"2606.00206","title":"Quantized Reasoning Models Think They Need to Think Longer, but They Do Not","created":"2026-05-29","cited_by_count":10,"area":"lr"},{"id":"2512.19206","title":"MixKVQ: Query-Aware Mixed-Precision KV Cache Quantization for Long-Context Reasoning","created":"2025-12-22","cited_by_count":8,"area":"lr"},{"id":"2601.14277","title":"Which Quantization Should I Use? A Unified Evaluation of llama.cpp Quantization on Llama-3.1-8B-Instruct","created":"2026-01-11","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":"2603.17435","title":"ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression","created":"2026-03-18","cited_by_count":8,"area":"inference"},{"id":"2505.11574","title":"Quantization Meets Reasoning: Exploring and Mitigating Degradation of Low-Bit LLMs in Mathematical Reasoning","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"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":"2510.16805","title":"Mixed-Precision Quantization for Language Models: Techniques and Prospects","created":"2025-10-19","cited_by_count":5,"area":null},{"id":"2512.07993","title":"SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2602.02581","title":"QuantLRM: Quantization of Large Reasoning Models via Fine-Tuning Signals","created":"2026-01-31","cited_by_count":5,"area":"lr"},{"id":"2604.19884","title":"From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization","created":"2026-04-21","cited_by_count":5,"area":null},{"id":"2505.24680","title":"A Simple Linear Patch Revives Layer-Pruned Large Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2509.22034","title":"The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging","created":"2025-09-26","cited_by_count":4,"area":"lr"},{"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":"2601.21198","title":"ZipMoE: Efficient On-Device MoE Serving via Lossless Compression and Cache-Affinity Scheduling","created":"2026-01-29","cited_by_count":4,"area":"moe"},{"id":"2603.01776","title":"FreeAct: Freeing Activations for LLM Quantization","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2605.11222","title":"ADMM-Q: An Improved Hessian-based Weight Quantizer for Post-Training Quantization of Large Language Models","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.12464","title":"Search Your Block Floating Point Scales!","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2606.26488","title":"What Survives When You Compress a Recursive Reasoner for the Edge?","created":"2026-06-25","cited_by_count":3,"area":"lr"},{"id":"2607.07964","title":"KronQ: LLM Quantization via Kronecker-Factored Hessian","created":"2026-07-08","cited_by_count":3,"area":null},{"id":"2505.02390","title":"Quantitative Analysis of Performance Drop in DeepSeek Model Quantization","created":"2025-05-05","cited_by_count":2,"area":null},{"id":"2510.03223","title":"Attention-Aligned Reasoning for Large Language Models","created":"2025-10-03","cited_by_count":2,"area":"lr"},{"id":"2511.18864","title":"Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models","created":"2025-11-24","cited_by_count":2,"area":"lr"},{"id":"2601.22787","title":"Float8@2bits: Entropy Coding Enables Data-Free Model Compression","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.02711","title":"Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interaction","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.13595","title":"The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2605.29327","title":"Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware Initialization","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2607.16237","title":"Quantizing Recursive Reasoning Models","created":"2026-06-25","cited_by_count":2,"area":"lr"},{"id":"2511.10201","title":"EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2512.23367","title":"Post-Training Quantization of OpenPangu Models for Efficient Deployment on Atlas A2","created":"2025-12-29","cited_by_count":1,"area":null},{"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":"2604.22577","title":"QuantClaw: Precision Where It Matters for OpenClaw","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.08755","title":"LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2606.02011","title":"Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.25519","title":"Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models","created":"2026-06-24","cited_by_count":1,"area":"lr"},{"id":"2607.00908","title":"Beyond Activation Alignment:The Alignment-Diversity Tradeoff in Task-Aware LLM Quantization","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.20129","title":"CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"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":"2609.11716","title":"Why Does Post-Training Quantization Work?","created":"2026-09-10","cited_by_count":1,"area":null},{"id":"2609.39223","title":"QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMs","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2509.00914","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2602.09130","title":"UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2604.12160","title":"PubSwap: Public-Data Off-Policy Coordination for Federated RLVR","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.26558","title":"Cassandra: Enabling Reasoning LLMs at Edge via Self-Speculative Decoding","created":"2026-05-26","cited_by_count":0,"area":"inference"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2607.11317","title":"Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2608.08447","title":"Hidden Language Consistency Phenomena in Reasoning LLMs","created":"2026-08-09","cited_by_count":0,"area":"lr"},{"id":"2608.30996","title":"Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"rag"},{"id":"2609.00450","title":"HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference","created":"2026-08-31","cited_by_count":0,"area":"inference"},{"id":"2609.31009","title":"G$^2$PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32042","title":"Quantization Thresholds Replicate, Failure Modes Do Not: A Three-Model Study of Agentic Tool Use in Polish from 8-bit to 2-bit","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.36760","title":"QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38169","title":"STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"id":"2609.39277","title":"A Tilted Bowl Is Not a Slippery Slope: Compressing Looped Models","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":"2610.15259","title":"RECAP: Calibrating Low-Bit Reasoning Models on the History They Read","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.19605","title":"PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference","created":"2026-10-14","cited_by_count":0,"area":"inference"}],"next_cursor":null}