{"total":170,"rows":[{"id":"2404.16710","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","created":"2024-04-25","cited_by_count":307,"area":"inference"},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"area":null},{"id":"2411.02359","title":"DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution","created":"2024-11-04","cited_by_count":117,"area":"lr"},{"id":"2408.00741","title":"DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency","created":"2024-08-01","cited_by_count":112,"area":null},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2505.09598","title":"How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference","created":"2025-05-14","cited_by_count":76,"area":null},{"id":"2403.20306","title":"Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference","created":"2024-03-29","cited_by_count":61,"area":null},{"id":"2504.17674","title":"Energy Considerations of Large Language Model Inference and Efficiency Optimizations","created":"2025-04-24","cited_by_count":55,"area":null},{"id":"2402.05406","title":"Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes","created":"2024-02-08","cited_by_count":43,"area":null},{"id":"2508.18076","title":"Neither Valid nor Reliable? Investigating the Use of LLMs as Judges","created":"2025-08-25","cited_by_count":39,"area":null},{"id":"2508.15734","title":"Measuring the environmental impact of delivering AI at Google Scale","created":"2025-08-21","cited_by_count":32,"area":null},{"id":"2404.01322","title":"A Review of Multi-Modal Large Language and Vision Models","created":"2024-03-28","cited_by_count":30,"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":"2407.04014","title":"Offline Energy-Optimal LLM Serving: Workload-Based Energy Models for LLM Inference on Heterogeneous Systems","created":"2024-07-04","cited_by_count":28,"area":"inference"},{"id":"2404.15149","title":"Bias patterns in the application of LLMs for clinical decision support: A comprehensive study","created":"2024-04-23","cited_by_count":27,"area":null},{"id":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2407.16893","title":"The Price of Prompting: Profiling Energy Use in Large Language Models Inference","created":"2024-07-04","cited_by_count":23,"area":null},{"id":"2512.03024","title":"TokenPowerBench: Benchmarking the Power Consumption of LLM Inference","created":"2025-12-02","cited_by_count":22,"area":null},{"id":"2408.05235","title":"SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving","created":"2024-08-05","cited_by_count":19,"area":"inference"},{"id":"2412.04782","title":"A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges","created":"2024-12-06","cited_by_count":18,"area":null},{"id":"2407.00010","title":"Hybrid Heterogeneous Clusters Can Lower the Energy Consumption of LLM Inference Workloads","created":"2024-04-25","cited_by_count":17,"area":null},{"id":"2410.12032","title":"MLPerf Power: Benchmarking the Energy Efficiency of Machine Learning Systems from Microwatts to Megawatts for Sustainable AI","created":"2024-10-15","cited_by_count":16,"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":"2406.08413","title":"Memory Is All You Need: An Overview of Compute-in-Memory Architectures for Accelerating Large Language Model Inference","created":"2024-06-12","cited_by_count":15,"area":null},{"id":"2410.02425","title":"LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services","created":"2024-10-03","cited_by_count":14,"area":null},{"id":"2511.07885","title":"Intelligence per Watt: Measuring Intelligence Efficiency of Local AI","created":"2025-11-11","cited_by_count":14,"area":null},{"id":"2601.10955","title":"Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents","created":"2026-01-16","cited_by_count":14,"area":"agents"},{"id":"2508.07675","title":"Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptation","created":"2025-08-11","cited_by_count":13,"area":"inference"},{"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":"2406.12128","title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2410.11042","title":"Persistent Topological Features in Large Language Models","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2511.05597","title":"From Prompts to Power: Measuring the Energy Footprint of LLM Inference","created":"2025-11-05","cited_by_count":12,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2407.09722","title":"Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference","created":"2024-07-12","cited_by_count":11,"area":"inference"},{"id":"2502.05610","title":"Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2503.23513","title":"RARE: Retrieval-Augmented Reasoning Modeling","created":"2025-03-30","cited_by_count":11,"area":"lr"},{"id":"2505.21594","title":"Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits","created":"2025-05-27","cited_by_count":11,"area":"inference"},{"id":"2506.04179","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2403.06009","title":"Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2406.11118","title":"Incentivizing Quality Text Generation via Statistical Contracts","created":"2024-06-17","cited_by_count":10,"area":null},{"id":"2409.11416","title":"The Unseen AI Disruptions for Power Grids: LLM-Induced Transients","created":"2024-09-09","cited_by_count":10,"area":null},{"id":"2505.20276","title":"Does quantization affect models' performance on long-context tasks?","created":"2025-05-26","cited_by_count":10,"area":null},{"id":"2508.02668","title":"LOST: Low-rank and Sparse Pre-training for Large Language Models","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2408.13940","title":"Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning","created":"2024-08-25","cited_by_count":9,"area":"lr"},{"id":"2412.15304","title":"TinyLLM: A Framework for Training and Deploying Language Models at the Edge Computers","created":"2024-12-19","cited_by_count":9,"area":null},{"id":"2505.19947","title":"MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2501.06699","title":"Large Language Models, Knowledge Graphs and Search Engines: A Crossroads for Answering Users' Questions","created":"2025-01-12","cited_by_count":8,"area":null},{"id":"2502.13329","title":"Language Models Can Predict Their Own Behavior","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2506.03616","title":"Learning to Insert [PAUSE] Tokens for Better Reasoning","created":"2025-06-04","cited_by_count":8,"area":"lr"},{"id":"2601.19026","title":"Is Finer Better? The Limits of Microscaling Formats in Large Language Models","created":"2026-01-26","cited_by_count":8,"area":null},{"id":"2501.09765","title":"Enhancing the De-identification of Personally Identifiable Information in Educational Data","created":"2025-01-14","cited_by_count":7,"area":null},{"id":"2410.20777","title":"KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation","created":"2024-10-28","cited_by_count":6,"area":"distill"},{"id":"2505.00022","title":"Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation","created":"2025-04-24","cited_by_count":6,"area":"synth"},{"id":"2310.15961","title":"Mixture of Tokens: Continuous MoE through Cross-Example Aggregation","created":"2023-10-24","cited_by_count":5,"area":"moe"},{"id":"2404.03353","title":"Towards Pareto Optimal Throughput in Small Language Model Serving","created":"2024-04-04","cited_by_count":5,"area":null},{"id":"2405.15842","title":"Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2406.17261","title":"TRAWL: Tensor Reduced and Approximated Weights for Large Language Models","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2408.01050","title":"The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2506.04203","title":"Cascadia: An Efficient Cascade Serving System for Large Language Models","created":"2025-06-04","cited_by_count":5,"area":"inference"},{"id":"2601.00624","title":"Do Chatbot LLMs Talk Too Much? The YapBench Benchmark","created":"2026-01-02","cited_by_count":5,"area":null},{"id":"2310.12821","title":"GestureGPT: Toward Zero-Shot Free-Form Hand Gesture Understanding with Large Language Model Agents","created":"2023-10-19","cited_by_count":4,"area":"agents"},{"id":"2311.02253","title":"Comparative Knowledge Distillation","created":"2023-11-03","cited_by_count":4,"area":"distill"},{"id":"2408.03033","title":"L3iTC at the FinLLM Challenge Task: Quantization for Financial Text Classification & Summarization","created":"2024-08-06","cited_by_count":4,"area":null},{"id":"2411.10599","title":"Generating Energy-efficient code with LLMs","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2411.19211","title":"On the Ethical Considerations of Generative Agents","created":"2024-11-28","cited_by_count":4,"area":"agents"},{"id":"2510.05181","title":"Auditing Pay-Per-Token in Large Language Models","created":"2025-10-05","cited_by_count":4,"area":null},{"id":"2511.21695","title":"EvalCards: A Framework for Standardized Evaluation Reporting","created":"2025-11-05","cited_by_count":4,"area":null},{"id":"2601.22362","title":"Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2402.06357","title":"The SkipSponge Attack: Sponge Weight Poisoning of Deep Neural Networks","created":"2024-02-09","cited_by_count":3,"area":null},{"id":"2404.03714","title":"SpikeExplorer: hardware-oriented Design Space Exploration for Spiking Neural Networks on FPGA","created":"2024-04-04","cited_by_count":3,"area":null},{"id":"2406.07794","title":"Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2409.03945","title":"TropNNC: Structured Neural Network Compression Using Tropical Geometry","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2410.08442","title":"JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2410.13147","title":"AgentDrug: Utilizing Large Language Models in An Agentic Workflow for Zero-Shot Molecular Editing","created":"2024-10-17","cited_by_count":3,"area":"agents"},{"id":"2410.14740","title":"Harnessing Your DRAM and SSD for Sustainable and Accessible LLM Inference with Mixed-Precision and Multi-level Caching","created":"2024-10-17","cited_by_count":3,"area":null},{"id":"2411.14458","title":"Improving training time and GPU utilization in geo-distributed language model training","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2411.17309","title":"PIM-AI: A Novel Architecture for High-Efficiency LLM Inference","created":"2024-11-26","cited_by_count":3,"area":null},{"id":"2503.10666","title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2504.13217","title":"Sustainability via LLM Right-sizing","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2509.23666","title":"Beyond Greedy Exits: Improved Early Exit Decisions for Risk Control and Reliability","created":"2025-09-28","cited_by_count":3,"area":"inference"},{"id":"2511.04481","title":"Promoting Sustainable Web Agents: Benchmarking and Estimating Energy Consumption through Empirical and Theoretical Analysis","created":"2025-11-06","cited_by_count":3,"area":"agents"},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2601.20617","title":"Agent Benchmarks Fail Public Sector Requirements","created":"2026-01-28","cited_by_count":3,"area":"agents"},{"id":"2603.15699","title":"This Is Taking Too Long -- Investigating Time as a Proxy for Energy Consumption of LLMs","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2604.24470","title":"Zero-shot Large Language Models for Automatic Readability Assessment","created":"2026-04-27","cited_by_count":3,"area":null},{"id":"2606.15954","title":"Green SARC: Predictive Cost and Carbon Governance for Agentic AI Systems","created":"2026-06-14","cited_by_count":3,"area":"agents"},{"id":"2606.19376","title":"Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2607.26571","title":"From Tokens to Watt-hours: Analytical Energy Estimation for LLM Inference on Modern GPUs","created":"2026-07-29","cited_by_count":3,"area":null},{"id":"2404.08727","title":"Can LLMs substitute SQL? Comparing Resource Utilization of Querying LLMs versus Traditional Relational Databases","created":"2024-04-12","cited_by_count":2,"area":null},{"id":"2405.00738","title":"HLSTransform: Energy-Efficient Llama 2 Inference on FPGAs Via High Level Synthesis","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2412.14708","title":"Creation of AI-driven Smart Spaces for Enhanced Indoor Environments -- A Survey","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2501.17980","title":"Limits to AI Growth: The Ecological and Social Consequences of Scaling","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2502.19747","title":"HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2503.03008","title":"MoSE: Hierarchical Self-Distillation Enhances Early Layer Embeddings","created":"2025-03-04","cited_by_count":2,"area":"distill"},{"id":"2503.23934","title":"Green MLOps to Green GenOps: An Empirical Study of Energy Consumption in Discriminative and Generative AI Operations","created":"2025-03-31","cited_by_count":2,"area":null},{"id":"2506.17940","title":"An entropy-optimal path to humble AI","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2506.20009","title":"Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks","created":"2025-06-24","cited_by_count":2,"area":"rag"},{"id":"2507.14633","title":"Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches","created":"2025-07-19","cited_by_count":2,"area":"agents"}],"next_cursor":"100"}