56 citations · 137 across the 31 of their papers we have counts for
33 papers
DIALER: A Case for Improving Rare-Class Accuracy in Retraining-Free Edge Video Analytics
Dongyoon Ryu, Sungho Jeon, Xinyue Ma +4
Edge video analytics with lightweight models is prone to accuracy degradation due to persistent distributional shifts in live video streams. While continuous learning (CL) addresse…
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
Haozhe Zhao, Shuzheng Si, Zhenhailong Wang +6
Scientific figures are among the most effective means of communicating complex research ideas, yet producing publication-quality illustrations remains one of the most labor-intensi…
Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning
Banghao Chi, Yining Xie, Mingyuan Wu +9
Spreadsheet systems (e.g., Microsoft Excel, Google Sheets) play a central role in modern data-centric workflows. As AI agents grow increasingly capable of automating complex tasks,…
Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On
Yixiang Yao, Yuhang Yao, Xinyi Fan +5
The rapid advancement of Large Language Models has given rise to autonomous LLM-based agents capable of complex reasoning and execution. As these agents transition from isolated op…
From Context to Skills: Can Language Models Learn from Context Skillfully?
Shuzheng Si, Haozhe Zhao, Yu Lei +10
Many real-world tasks require language models (LMs) to reason over complex contexts that exceed their parametric knowledge. This calls for context learning, where LMs directly lear…
SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips
Jiahuan Yu, Mingtao Hu, Zichao Lin +1
Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates ex…
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference
Yushu Zhao, Zheng Wang, Minjia Zhang
Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input. However, their widespread…
VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing
Jiahuan Yu, Aryan Taneja, Junfeng Lin +1
The energy cost of Large Language Model (LLM) inference is rapidly becoming a barrier to sustainable and scalable deployment. Although modern serving architectures expose distinct…
MENTOR: Efficient Multimodal-Conditioned Tuning for Autoregressive Vision Generation Models
Haozhe Zhao, Zefan Cai, Shuzheng Si +5
Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex m…
MegaFold: Efficient Training of Next-Generation 3D Attention Protein Models on Cross-Platform GPUs
Hoa La, Ahan Gupta, Alex Morehead +2
Recent advances in biomolecular modeling have been catalyzed by models such as AlphaFold3 (AF3), which introduce science-informed changes to the transformer architecture. Unlike tr…
Supervising the search process produces reliable and generalizable information-seeking agents
Guangzhi Xiong, Qiao Jin, Xiao Wang +9
Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deployed as autonomous agentic search syste…
Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions
Guangzhi Xiong, Qiao Jin, Xiao Wang +3
The emergent abilities of large language models (LLMs) have demonstrated great potential in solving medical questions. They can possess considerable medical knowledge, but may stil…
Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
Zheng Wang, Boxiao Jin, Zhongzhi Yu +1
How to efficiently serve Large Language Models (LLMs) has become a pressing issue because of their huge computational cost in their autoregressive generation process. To mitigate c…
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
Haozhe Zhao, Xiaojian Ma, Liang Chen +7
This paper presents UltraEdit, a large-scale (approximately 4 million editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to addr…
Universal Checkpointing: A Flexible and Efficient Distributed Checkpointing System for Large-Scale DNN Training with Reconfigurable Parallelis
Xinyu Lian, Sam Ade Jacobs, Lev Kurilenko +4
Deep neural network (DNN) training continues to scale rapidly in terms of model size, data volume, and sequence length, to the point where multiple machines are required to fit lar…
Parcae: Proactive, Liveput-Optimized DNN Training on Preemptible Instances
Jiangfei Duan, Ziang Song, Xupeng Miao +5
Deep neural networks (DNNs) are becoming progressively large and costly to train. This paper aims to reduce DNN training costs by leveraging preemptible instances on modern clouds,…
Computing in the Era of Large Generative Models: From Cloud-Native to AI-Native
Yao Lu, Song Bian, Lequn Chen +19
In this paper, we investigate the intersection of large generative AI models and cloud-native computing architectures. Recent large models such as ChatGPT, while revolutionary in t…
DeepSpeed4Science Initiative: Enabling Large-Scale Scientific Discovery through Sophisticated AI System Technologies
Shuaiwen Leon Song, Bonnie Kruft, Minjia Zhang +89
In the upcoming decade, deep learning may revolutionize the natural sciences, enhancing our capacity to model and predict natural occurrences. This could herald a new era of scient…
Configuration Validation with Large Language Models
Xinyu Lian, Yinfang Chen, Runxiang Cheng +4
Misconfigurations are major causes of software failures. Existing practices rely on developer-written rules or test cases to validate configurations, which are expensive. Machine l…
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Suyu Ge, Yunan Zhang, Liyuan Liu +3
In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Differ…
RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model
Fengxiang Bie, Yibo Yang, Zhongzhu Zhou +10
Text-to-image generation (TTI) refers to the usage of models that could process text input and generate high fidelity images based on text descriptions. Text-to-image generation us…
FedHC: A Scalable Federated Learning Framework for Heterogeneous and Resource-Constrained Clients
Min Zhang, Fuxun Yu, Yongbo Yu +3
Federated Learning (FL) is a distributed learning paradigm that empowers edge devices to collaboratively learn a global model leveraging local data. Simulating FL on GPU is essenti…
A Survey of Multi-Tenant Deep Learning Inference on GPU
Fuxun Yu, Di Wang, Longfei Shangguan +3
Deep Learning (DL) models have achieved superior performance. Meanwhile, computing hardware like NVIDIA GPUs also demonstrated strong computing scaling trends with 2x throughput an…
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam
Yucheng Lu, Conglong Li, Minjia Zhang +2
1-bit gradient compression and local steps are two representative techniques that enable drastic communication reduction in distributed SGD. Their benefits, however, remain an open…