{"topic":{"slug":"efficient-ai","name":"Efficient Training & Inference","domain":"ai","description":"Quantization, distillation, sparsity, speculative decoding, KV-cache compression and IO-aware kernels that make frontier models cheaper to train and serve.","keywords":["quantization","speculative decoding","KV cache","FlashAttention","knowledge distillation","low-rank adaptation","efficient inference","pruning"],"paper_count":253,"latest_published":"2026-10-28","url":"https://space-kitty.com/topics/efficient-ai","api_url":"https://space-kitty.com/api/v1/topics/efficient-ai"},"dossier":null,"top_papers":[{"id":"doi:10.1145/3714983.3714987","kind":"article","title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","authors":["Ji Lin","Jiaming Tang","Haotian Tang","Shang Wen Yang","Guangxuan Xiao","Song Han"],"author_count":6,"year":2025,"published":"2025-01-20","venue":"GetMobile Mobile Computing and Communications","cited_by":274,"doi":"10.1145/3714983.3714987","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1145/3714983.3714987","archive_url":"https://space-kitty.com/papers/doi:10.1145/3714983.3714987"},{"id":"arxiv:2308.07633","kind":"article","title":"A Survey on Model Compression for Large Language Models","authors":["Xunyu Zhu","Jian Li","Yong Liu","Can Ma","Weiping Wang"],"author_count":5,"year":2024,"published":"2024-01-01","venue":"Transactions of the Association for Computational Linguistics","cited_by":272,"doi":"10.1162/tacl_a_00704","arxiv_id":"2308.07633","nct_id":null,"source_url":"https://doi.org/10.1162/tacl_a_00704","archive_url":"https://space-kitty.com/papers/arxiv:2308.07633"},{"id":"arxiv:2405.14371","kind":"article","title":"EdgeShard: Efficient LLM Inference via Collaborative Edge Computing","authors":["Mingjin Zhang","Xiaoming Shen","Jiannong Cao","Zeyang Cui","Shan Jiang"],"author_count":5,"year":2024,"published":"2024-12-31","venue":"IEEE Internet of Things Journal","cited_by":229,"doi":"10.1109/jiot.2024.3524255","arxiv_id":"2405.14371","nct_id":null,"source_url":"https://doi.org/10.1109/jiot.2024.3524255","archive_url":"https://space-kitty.com/papers/arxiv:2405.14371"},{"id":"arxiv:1412.6604","kind":"preprint","title":"Video (language) modeling: a baseline for generative models of natural videos","authors":["Marc’Aurelio Ranzato","Arthur D. Szlam","Joan Bruna","Michaël Mathieu","Ronan Collobert","Sumit Chopra"],"author_count":6,"year":2014,"published":"2014-12-20","venue":null,"cited_by":325,"doi":null,"arxiv_id":"1412.6604","nct_id":null,"source_url":"http://arxiv.org/abs/1412.6604","archive_url":"https://space-kitty.com/papers/arxiv:1412.6604"},{"id":"arxiv:2211.10438","kind":"preprint","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","authors":["Guangxuan Xiao","Ji Lin","Mickaël Seznec","Wu, Hao","Julien Demouth","Song Han"],"author_count":6,"year":2022,"published":"2022-11-18","venue":null,"cited_by":247,"doi":null,"arxiv_id":"2211.10438","nct_id":null,"source_url":"http://arxiv.org/abs/2211.10438","archive_url":"https://space-kitty.com/papers/arxiv:2211.10438"},{"id":"arxiv:2004.09602","kind":"preprint","title":"Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation","authors":["Hao Wu","Patrick Judd","Xiaojie Zhang","Mikhail Isaev","Paulius Micikevicius"],"author_count":5,"year":2020,"published":"2020-04-20","venue":null,"cited_by":240,"doi":null,"arxiv_id":"2004.09602","nct_id":null,"source_url":"http://arxiv.org/abs/2004.09602","archive_url":"https://space-kitty.com/papers/arxiv:2004.09602"},{"id":"arxiv:2210.17323","kind":"preprint","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","authors":["Elias Frantar","Saleh Ashkboos","Torsten Hoefler","Dan Alistarh"],"author_count":4,"year":2022,"published":"2022-10-31","venue":null,"cited_by":197,"doi":null,"arxiv_id":"2210.17323","nct_id":null,"source_url":"http://arxiv.org/abs/2210.17323","archive_url":"https://space-kitty.com/papers/arxiv:2210.17323"},{"id":"arxiv:2101.01321","kind":"preprint","title":"I-BERT: Integer-only BERT Quantization","authors":["Sehoon Kim","Amir Gholami","Zhewei Yao","Michael W. Mahoney","Kurt Keutzer"],"author_count":5,"year":2021,"published":"2021-01-05","venue":"ICML 2021 (Oral)","cited_by":186,"doi":null,"arxiv_id":"2101.01321","nct_id":null,"source_url":"http://arxiv.org/abs/2101.01321","archive_url":"https://space-kitty.com/papers/arxiv:2101.01321"},{"id":"doi:10.1016/j.mlwa.2024.100605","kind":"article","title":"A survey on knowledge distillation: Recent advancements","authors":["Amir Moslemi","Anna Briskina","Zubeka Dang","Jason H. Li"],"author_count":4,"year":2024,"published":"2024-11-10","venue":"Machine Learning with Applications","cited_by":112,"doi":"10.1016/j.mlwa.2024.100605","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.mlwa.2024.100605","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.mlwa.2024.100605"},{"id":"arxiv:2301.00774","kind":"preprint","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","authors":["Elias Frantar","Dan Alistarh"],"author_count":2,"year":2023,"published":"2023-01-02","venue":null,"cited_by":131,"doi":null,"arxiv_id":"2301.00774","nct_id":null,"source_url":"http://arxiv.org/abs/2301.00774","archive_url":"https://space-kitty.com/papers/arxiv:2301.00774"},{"id":"arxiv:2104.10640","kind":"article","title":"The NLP Cookbook: Modern Recipes for Transformer Based Deep Learning Architectures","authors":["Sushant Kumar Singh","Ausif Mahmood"],"author_count":2,"year":2021,"published":"2021-01-01","venue":"IEEE Access","cited_by":158,"doi":"10.1109/access.2021.3077350","arxiv_id":"2104.10640","nct_id":null,"source_url":"https://doi.org/10.1109/access.2021.3077350","archive_url":"https://space-kitty.com/papers/arxiv:2104.10640"},{"id":"arxiv:2303.01037","kind":"preprint","title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","authors":["Yu Zhang","Han, Wei","James Qin","Yongqiang Wang","Ankur Bapna","Zhehuai Chen"],"author_count":27,"year":2023,"published":"2023-03-02","venue":null,"cited_by":110,"doi":null,"arxiv_id":"2303.01037","nct_id":null,"source_url":"http://arxiv.org/abs/2303.01037","archive_url":"https://space-kitty.com/papers/arxiv:2303.01037"},{"id":"arxiv:2306.00978","kind":"preprint","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","authors":["Ji Lin","Jiaming Tang","Haotian Tang","Yang Shang","Wei-Ming Chen","Wei-Chen Wang"],"author_count":10,"year":2023,"published":"2023-06-01","venue":null,"cited_by":103,"doi":null,"arxiv_id":"2306.00978","nct_id":null,"source_url":"https://arxiv.org/abs/2306.00978","archive_url":"https://space-kitty.com/papers/arxiv:2306.00978"},{"id":"arxiv:2403.07815","kind":"preprint","title":"Chronos: Learning the Language of Time Series","authors":["Abdul Fatir Ansari","Lorenzo Stella","Ali Caner Türkmen","Xiyuan Zhang","Mercado, Pedro","Huibin Shen"],"author_count":18,"year":2024,"published":"2024-03-12","venue":null,"cited_by":85,"doi":null,"arxiv_id":"2403.07815","nct_id":null,"source_url":"http://arxiv.org/abs/2403.07815","archive_url":"https://space-kitty.com/papers/arxiv:2403.07815"},{"id":"doi:10.1109/access.2024.3409745","kind":"article","title":"Measuring and Improving the Energy Efficiency of Large Language Models Inference","authors":["Mauricio Fadel Argerich","Marta Patiño-Martı́nez"],"author_count":2,"year":2024,"published":"2024-01-01","venue":"IEEE Access","cited_by":84,"doi":"10.1109/access.2024.3409745","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1109/access.2024.3409745","archive_url":"https://space-kitty.com/papers/doi:10.1109/access.2024.3409745"}],"newest_papers":[{"id":"arxiv:2610.38095","kind":"preprint","title":"Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI","authors":["NVIDIA",":","Aastha Jhunjhunwala","Aayushi Ashokkumar Srivastava","Abhibha Gupta","Abhinav Garg"],"author_count":559,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38095","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38095","archive_url":"https://space-kitty.com/papers/arxiv:2610.38095"},{"id":"arxiv:2610.38277","kind":"preprint","title":"The Role of Quantization in Loss Spikes","authors":["Zaiqian Chen","Aditya Somasundaram","Sophie Li","Sean McLeish","John Kirchenbauer","Tom Goldstein"],"author_count":7,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38277","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38277","archive_url":"https://space-kitty.com/papers/arxiv:2610.38277"},{"id":"arxiv:2610.38331","kind":"preprint","title":"Multi-Token Prediction Done Right","authors":["Jayden Teoh"],"author_count":1,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38331","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38331","archive_url":"https://space-kitty.com/papers/arxiv:2610.38331"},{"id":"arxiv:2610.38355","kind":"preprint","title":"FlatCake: A Flat KVCache Storage Architecture for LLM Serving","authors":["Xin Huang","Teng Ma","Zhuoran Li","Yibo Zhao","Zhaoshi Li","Qianchao Zhu"],"author_count":10,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38355","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38355","archive_url":"https://space-kitty.com/papers/arxiv:2610.38355"},{"id":"arxiv:2610.38357","kind":"preprint","title":"CSO: Refining Robotic Policies via Skill Distribution Alignment and Skill-Grained Optimization","authors":["Zhiyuan Xiang","Xiang Deng","Wanjie Tao","Xu Chen","Zhao Jielun","Weili Guan"],"author_count":6,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38357","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38357","archive_url":"https://space-kitty.com/papers/arxiv:2610.38357"},{"id":"arxiv:2610.38378","kind":"preprint","title":"Towards Reliable, Scalable, and Value-Aligned Generative Recommendation for Large-Scale Advertising","authors":["Yatong Xiao","Yibo Sheng","Lixiang Wang","Mingjie Sun","Yunhao Sha","Pengfei Zhang"],"author_count":10,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38378","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38378","archive_url":"https://space-kitty.com/papers/arxiv:2610.38378"},{"id":"arxiv:2610.38558","kind":"preprint","title":"REVBRAIN: Real-time Probabilistic EEG Forecasting Using Residual Vector Quantization","authors":["Hanna Pankka","Jaakko Lehtinen","Timo Roine"],"author_count":3,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38558","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38558","archive_url":"https://space-kitty.com/papers/arxiv:2610.38558"},{"id":"arxiv:2610.38681","kind":"preprint","title":"Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models","authors":["Yecheng Wu","Song Han","Han Cai"],"author_count":3,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38681","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38681","archive_url":"https://space-kitty.com/papers/arxiv:2610.38681"},{"id":"arxiv:2610.36452","kind":"preprint","title":"Whole-Body Humanoid Control via Stochastic Motion Tokenization","authors":["Michael Drolet","Oleg Arenz","Jan Peters"],"author_count":3,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.36452","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36452","archive_url":"https://space-kitty.com/papers/arxiv:2610.36452"},{"id":"arxiv:2610.36520","kind":"preprint","title":"Folding Attention Biases into Keys Makes Compacted KV Caches Run on Standard Kernels","authors":["Utkarsh Kanwat"],"author_count":1,"year":2026,"published":"2026-10-27","venue":null,"cited_by":0,"doi":null,"arxiv_id":"2610.36520","nct_id":null,"source_url":"https://arxiv.org/abs/2610.36520","archive_url":"https://space-kitty.com/papers/arxiv:2610.36520"}],"related_topics":[{"slug":"llm-architectures","name":"LLM Architectures & Pretraining","api_url":"https://space-kitty.com/api/v1/topics/llm-architectures"},{"slug":"scaling-laws","name":"Scaling Laws & Compute-Optimal Training","api_url":"https://space-kitty.com/api/v1/topics/scaling-laws"},{"slug":"reasoning-models","name":"Reasoning Models & Test-Time Compute","api_url":"https://space-kitty.com/api/v1/topics/reasoning-models"},{"slug":"alignment-safety","name":"AI Alignment & Safety","api_url":"https://space-kitty.com/api/v1/topics/alignment-safety"},{"slug":"interpretability","name":"Mechanistic Interpretability","api_url":"https://space-kitty.com/api/v1/topics/interpretability"},{"slug":"ai-agents","name":"LLM Agents & Tool Use","api_url":"https://space-kitty.com/api/v1/topics/ai-agents"},{"slug":"generative-multimodal","name":"Generative & Multimodal Models","api_url":"https://space-kitty.com/api/v1/topics/generative-multimodal"},{"slug":"ai-for-science","name":"AI for Science","api_url":"https://space-kitty.com/api/v1/topics/ai-for-science"},{"slug":"robotics-embodied","name":"Robot Learning & Embodied AI","api_url":"https://space-kitty.com/api/v1/topics/robotics-embodied"}],"premium":{"dossier":null,"research_pack":{"url":"https://space-kitty.com/api/v1/topics/efficient-ai/pack","price_usd":"0.20"}},"more":"https://space-kitty.com/api/v1/topics/efficient-ai/papers?sort=top&limit=100"}