activity
20232025
most citedZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation

17 citations · 51 across the 15 of their papers we have counts for

collaborators

15 papers

cs.LG2025

Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences

Stas Bekman, Samyam Rajbhandari, Michael Wyatt +5

Long sequences are critical for applications like RAG, long document summarization, multi-modality, etc., and modern LLMs, like Llama 4 Scout, support max sequence length of up to…

cs.CL2025

MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility

Yexiao He, Ang Li, Boyi Liu +2

Healthcare decision-making represents one of the most challenging domains for Artificial Intelligence (AI), requiring the integration of diverse knowledge sources, complex reasonin…

cs.CL2025

ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering

Ruofan Wu, Youngwon Lee, Fan Shu +5

Retrieval-Augmented Generation (RAG) systems are increasingly diverse, yet many suffer from monolithic designs that tightly couple core functions like query reformulation, retrieva…

cs.CL2024

CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation

Youngwon Lee, Seung-won Hwang, Daniel Campos +3

With the adoption of retrieval-augmented generation (RAG), large language models (LLMs) are expected to ground their generation to the retrieved contexts. Yet, this is hindered by…

cs.CL2024

Inference Scaling for Bridging Retrieval and Augmented Generation

Youngwon Lee, Seung-won Hwang, Daniel Campos +3

Retrieval-augmented generation (RAG) has emerged as a popular approach to steering the output of a large language model (LLM) by incorporating retrieved contexts as inputs. However…

cs.LG2024

AI and Memory Wall

Amir Gholami, Zhewei Yao, Sehoon Kim +3

The availability of unprecedented unsupervised training data, along with neural scaling laws, has resulted in an unprecedented surge in model size and compute requirements for serv…