Zhaozhuo Xu

1. KIVI : Plug-and-play 2bit KV Cache Quantization with Streaming Asymmetric Quantization
   2023/01/01 by Zirui Liu, Jiayi Yuan, Hongye Jin +6 · 1 voice · 42 citations
   Computer Science · #Error Correcting Code Techniques #Interconnection Networks and Systems #Quantum-Dot Cellular Automata #cs.CL #cs.LG #cs.PF
2. Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
   2023/05/26 by Zichang Liu, Aditya Desai, Liu, Zichang +13 · 43 citations
   Computer Science · #Topic Modeling #Advanced Neural Network Applications #Explainable Artificial Intelligence (XAI)
3. LLM Multi-Agent Systems: Challenges and Open Problems
   2024/02/05 by Shanshan Han, Han, Shanshan, Qifan Zhang +6 · 40 citations
   Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation #Multiagent Systems (cs.MA)
4. TensorOpera Router: A Multi-Model Router for Efficient LLM Inference
   2024/08/22 by Dimitris Stripelis, Zijian Hu, Stripelis, Dimitris +15 · 15 citations
   Computer Science · #Natural Language Processing Techniques #Algorithms and Data Compression #Network Packet Processing and Optimization
5. Proximity Graph Maintenance for Fast Online Nearest Neighbor Search
   2022/06/22 by Zhaozhuo Xu, Xu, Zhaozhuo, Weijie Zhao +7 · 3 citations
   Computer Science · #Advanced Image and Video Retrieval Techniques #Caching and Content Delivery #Data Management and Algorithms #FOS: Computer and information sciences #Information Retrieval (cs.IR)
6. KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches
   2024/07/01 by Jiayi Yuan, Hongyi Liu, Yuan, Jiayi +21 · 5 citations
   Computer Science · #Algorithms and Data Compression #Parallel Computing and Optimization Techniques #Advanced Data Storage Technologies
7. Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
   2024/06/05 by Wentao Guo, Guo, Wentao, Jikai Long +21 · 3 citations
   Engineering · Mathematics · #Electromagnetic Simulation and Numerical Methods #Particle accelerators and beam dynamics #Numerical methods for differential equations
8. Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt
   2023/05/17 by Zhaozhuo Xu, Zirui Liu, Xu, Zhaozhuo +13 · 2 citations
   Computer Science · #Topic Modeling #Natural Language Processing Techniques #Speech Recognition and Synthesis