Robust Implementation of Retrieval-Augmented Generation on Edge-based Computing-in-Memory Architecturesby Ruiyang Qin, Zheyu Yan, Dewen Zeng,…
vAttention: Dynamic Memory Management for Serving LLMs without PagedAttentionby Ramya Prabhu, Ajay Nayak, Jayashree Mohan,…
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Servingby Yujun Lin, Haotian Tang, Shang…
Language-Image Models with 3D Understandingby Jang Hyun Cho, Boris Ivanovic, Yulong Cao, Edward Schmerling, Yue…
Federated Reinforcement Learning with Constraint Heterogeneityby Hao Jin, Liangyu Zhang, Zhihua ZhangFirst submitted to arxiv…
TED: Accelerate Model Training by Internal Generalizationby Jinying Xiao, Ping Li, Jie NieFirst submitted to…
Sub-goal Distillation: A Method to Improve Small Language Agentsby Maryam Hashemzadeh, Elias Stengel-Eskin, Sarath Chandar,…
Mitigating LLM Hallucinations via Conformal Abstentionby Yasin Abbasi Yadkori, Ilja Kuzborskij, David Stutz, András György,…
The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representationby…
CACTUS: Chemistry Agent Connecting Tool-Usage to Scienceby Andrew D. McNaughton, Gautham Ramalaxmi, Agustin Kruel, Carter…