{"total":77,"rows":[{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167,"area":null},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131,"area":null},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2410.01699","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding","created":"2024-10-02","cited_by_count":66,"area":"inference"},{"id":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45,"area":"mllm"},{"id":"2406.14909","title":"Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths","created":"2024-06-21","cited_by_count":44,"area":null},{"id":"2406.02924","title":"Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models","created":"2024-06-05","cited_by_count":40,"area":null},{"id":"2504.03360","title":"Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency","created":"2025-04-04","cited_by_count":34,"area":null},{"id":"2509.23202","title":"Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization","created":"2025-09-27","cited_by_count":32,"area":null},{"id":"2501.02600","title":"TAPAS: Thermal- and Power-Aware Scheduling for LLM Inference in Cloud Platforms","created":"2025-01-05","cited_by_count":29,"area":null},{"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":"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":"2407.12327","title":"Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale","created":"2024-07-17","cited_by_count":21,"area":null},{"id":"2406.16330","title":"Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging","created":"2024-06-24","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":"2502.07780","title":"DarwinLM: Evolutionary Structured Pruning of Large Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2502.15799","title":"Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models","created":"2025-02-18","cited_by_count":18,"area":"lr"},{"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":"2505.19433","title":"Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression","created":"2025-05-26","cited_by_count":16,"area":"agents"},{"id":"2507.05197","title":"Pre-Trained Policy Discriminators are General Reward Models","created":"2025-07-07","cited_by_count":15,"area":"alignment"},{"id":"2406.12311","title":"Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2409.11055","title":"Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2502.13178","title":"Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2406.12928","title":"Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and Toolbox","created":"2024-06-15","cited_by_count":11,"area":null},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","cited_by_count":11,"area":null},{"id":"2412.18169","title":"KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving","created":"2024-12-24","cited_by_count":11,"area":"inference"},{"id":"2502.08246","title":"Inference-time sparse attention with asymmetric indexing","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2502.15260","title":"LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design","created":"2025-02-21","cited_by_count":11,"area":"ssm"},{"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":"2601.22347","title":"Pushing the Limits of Block Rotations in Post-Training Quantization","created":"2026-01-29","cited_by_count":11,"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":"2409.16997","title":"INT-FlashAttention: Enabling Flash Attention for INT8 Quantization","created":"2024-09-25","cited_by_count":9,"area":null},{"id":"2503.24000","title":"Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving","created":"2025-03-31","cited_by_count":8,"area":"inference"},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2605.28873","title":"Pre-Registering the Detectable Effect: A Paired-MDE Budget for 4-bit Quantization Benchmarks, with a Pilot Audit","created":"2026-05-25","cited_by_count":8,"area":null},{"id":"2409.00084","title":"Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models","created":"2024-08-25","cited_by_count":7,"area":"lr"},{"id":"2502.10659","title":"Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGA","created":"2025-02-15","cited_by_count":7,"area":"inference"},{"id":"2409.17092","title":"Accumulator-Aware Post-Training Quantization for Large Language Models","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2507.07877","title":"Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models","created":"2025-07-10","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":"2511.20104","title":"The Devil in the Details: Emergent Misalignment, Format and Coherence in Open-Weights LLMs","created":"2025-11-25","cited_by_count":5,"area":null},{"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":"2606.03002","title":"Perplexity Can Miss SAE Feature Damage Under Quantization","created":"2026-06-02","cited_by_count":5,"area":"mechinterp"},{"id":"2406.10251","title":"The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs","created":"2024-06-10","cited_by_count":3,"area":"rag"},{"id":"2410.14766","title":"Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarks","created":"2024-10-18","cited_by_count":3,"area":null},{"id":"2501.06066","title":"Distilling Calibration via Conformalized Credal Inference","created":"2025-01-10","cited_by_count":3,"area":null},{"id":"2502.01804","title":"Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging","created":"2025-02-03","cited_by_count":3,"area":null},{"id":"2503.01820","title":"RSQ: Learning from Important Tokens Leads to Better Quantized LLMs","created":"2025-03-03","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":"2509.04534","title":"Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation","created":"2025-09-04","cited_by_count":3,"area":null},{"id":"2602.24059","title":"Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization","created":"2026-02-27","cited_by_count":3,"area":"mllm"},{"id":"2406.16611","title":"Evaluation of Language Models in the Medical Context Under Resource-Constrained Settings","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2512.07503","title":"SJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation","created":"2025-12-08","cited_by_count":2,"area":"inference"},{"id":"2609.05881","title":"Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2410.19318","title":"Two are better than one: Context window extension with multi-grained self-injection","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2502.00865","title":"Predicting potentially abusive clauses in Chilean terms of services with natural language processing","created":"2025-02-02","cited_by_count":1,"area":null},{"id":"2504.12334","title":"QM-ToT: A Medical Tree of Thoughts Reasoning Framework for Quantized Model","created":"2025-04-13","cited_by_count":1,"area":"lr"},{"id":"2510.06255","title":"Towards an Efficient, Customizable, and Accessible AI Tutor","created":"2025-10-04","cited_by_count":1,"area":"rag"},{"id":"2602.15563","title":"1-Bit Wonder: Improving QAT Performance in the Low-Bit Regime through K-Means Quantization","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2406.06773","title":"Evaluating Zero-Shot Long-Context LLM Compression","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2503.22698","title":"Fragile Mastery: Are Domain-Specific Trade-Offs Undermining On-Device Language Models?","created":"2025-03-16","cited_by_count":0,"area":null},{"id":"2506.00486","title":"It Takes a Good Model to Train a Good Model: Generalized Gaussian Priors for Optimized LLMs","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2602.13289","title":"Evaluating the Impact of Post-Training Quantization on Reliable VQA with Multimodal LLMs","created":"2026-02-08","cited_by_count":0,"area":"mllm"},{"id":"2602.15913","title":"Foundation Models for Medical Imaging: Status, Challenges, and Directions","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2605.26019","title":"Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Service","created":"2026-05-25","cited_by_count":0,"area":"rag"},{"id":"2606.10458","title":"Minimum Distortion Quantization with Specified Output Distribution","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.25532","title":"Agentic evolution of physically constrained foundation models","created":"2026-06-24","cited_by_count":0,"area":"agents"},{"id":"2606.29581","title":"The Joint Effect of Quantization and Sampling Temperature on LLM Safety Alignment: A Factorial Analysis","created":"2026-06-28","cited_by_count":0,"area":"alignment"},{"id":"2607.01244","title":"Retrieval-Augmented Generation to Support Railways Engineering Tasks: A Case Study","created":"2026-05-18","cited_by_count":0,"area":"rag"},{"id":"2607.02584","title":"RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.09999","title":"Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts","created":"2026-07-10","cited_by_count":0,"area":"lr"},{"id":"2607.18867","title":"HindsightBench: A Black-Box Behavioral Audit Protocol for Parametric Hindsight in Time-Indexed LLM Decision Tasks","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2608.08188","title":"Quantization Degradation in Large Language Models: A Signal-Noise Perspective","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.21621","title":"FrugalSOT - Frugal Search Over the Models","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.37902","title":"You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04403","title":"Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}