25 citations · 53 across the 23 of their papers we have counts for
25 papers
Energy Calculus: A Compositional Algebra of Energy in Computational Systems
Mosharaf Chowdhury, Jae-Won Chung, Jeff J. Ma +2
Energy is a binding constraint for AI scaling, yet it lacks the formal treatment that computation, communication, and learning have long enjoyed. Recent systems demonstrate large e…
ASPIRE: Agentic /Skills Discovery for Robotics
Runyu Lu, Yubo Wu, Ethan Kou +13
Traditional robot programming is notoriously challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse environment conf…
The Language-Energy Divide: Measuring Energy Costs of Multilingual LLM Inference
Naihao Deng, Alissa Shen, Yiming Feng +5
Large language models (LLMs) are increasingly deployed in multilingual settings, yet the energy costs of serving these models across different languages remain poorly understood. W…
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
Shiqi He, Yue Cui, Feijie Wu +5
Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action. When every act…
Addressing Variable Heterogeneity in Distributed Multimodal Training with Entrain
Insu Jang, Mosharaf Chowdhury
Multimodal LLM datasets are inherently heterogeneous, with significant data variability. Although each modality exhibits independent variability, sample-level entanglement makes it…
The Last Human-Written Paper: Agent-Native Research Artifacts
Jiachen Liu, Jiaxin Pei, Jintao Huang +34
Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation im…
Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models
Jae-Won Chung, Jeff J. Ma, Jisang Ahn +4
Any-to-Any models are an emerging class of multimodal models that accept combinations of multimodal data (e.g., text, image, video, audio) as input and generate them as output. Ser…
KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving
Yichao Yuan, Mosharaf Chowdhury, Nishil Talati
Power has become a central bottleneck for AI inference. This problem is becoming more urgent as agentic AI emerges as a major workload class, yet prior power-management techniques…
GPU-to-Grid: Voltage Regulation via GPU Utilization Control
Zhirui Liang, Jae-Won Chung, Mosharaf Chowdhury +2
While the rapid expansion of data centers poses challenges for power grids, it also offers new opportunities as flexible loads. Existing power system research often abstracts data…
Where Do the Joules Go? Diagnosing Inference Energy Consumption
Jae-Won Chung, Ruofan Wu, Jeff J. Ma +1
Energy is now a critical ML computing resource. While measuring energy consumption and observing trends is a valuable first step, accurately understanding and diagnosing why those…
Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training
Ruofan Wu, Jae-Won Chung, Mosharaf Chowdhury
The computing demand of AI is growing at an unprecedented rate, but energy supply is not keeping pace. As a result, energy has become an expensive and contended resource that requi…
Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving
Jeff J. Ma, Jae-Won Chung, Jisang Ahn +5
Any-to-Any models are an emerging class of multimodal models that accept combinations of text and multimodal data as input and generate them as output, introducing heterogeneous co…
Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement
Yuchen Xia, Souvik Kundu, Mosharaf Chowdhury +1
Novel View Synthesis (NVS) generates novel views of a scene from a sparse set of input images and is a key component in applications such as immersive rendering and 3D content gene…
Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory
Shiqi He, Yue Cui, Xinyu Ma +3
Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online…
TetriServe: Efficiently Serving Mixed DiT Workloads
Runyu Lu, Shiqi He, Wenxuan Tan +5
Diffusion Transformer (DiT) models excel at generating high-quality images through iterative denoising steps, but serving them under strict Service Level Objectives (SLOs) is chall…
EXP-Bench: Can AI Conduct AI Research Experiments?
Patrick Tser Jern Kon, Jiachen Liu, Xinyi Zhu +10
Automating AI research holds immense potential for accelerating scientific progress, yet current AI agents struggle with the complexities of rigorous, end-to-end experimentation. W…
The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
Jae-Won Chung, Jeff J. Ma, Ruofan Wu +5
As the adoption of Generative AI in real-world services grow explosively, energy has emerged as a critical bottleneck resource. However, energy remains a metric that is often overl…
Efficient Distributed MLLM Training with Cornstarch
Insu Jang, Runyu Lu, Nikhil Bansal +2
Multimodal large language models (MLLMs) extend the capabilities of large language models (LLMs) by combining heterogeneous model architectures to handle diverse modalities like im…
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
Patrick Tser Jern Kon, Jiachen Liu, Qiuyi Ding +7
Scientific experimentation, a cornerstone of human progress, demands rigor in reliability, methodical control, and interpretability to yield meaningful results. Despite the growing…
Mordal: Automated Pretrained Model Selection for Vision Language Models
Shiqi He, Insu Jang, Mosharaf Chowdhury
Incorporating multiple modalities into large language models (LLMs) is a powerful way to enhance their understanding of non-textual data, enabling them to perform multimodal tasks.…
FedTrans: Efficient Federated Learning via Multi-Model Transformation
Yuxuan Zhu, Jiachen Liu, Mosharaf Chowdhury +1
Federated learning (FL) aims to train machine learning (ML) models across potentially millions of edge client devices. Yet, training and customizing models for FL clients is notori…
Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services
Jiachen Liu, Jae-Won Chung, Zhiyu Wu +3
Large language models (LLMs) are now at the core of conversational AI services such as real-time translation and chatbots, which provide live user interaction by incrementally stre…
Toward Cross-Layer Energy Optimizations in AI Systems
Jae-Won Chung, Nishil Talati, Mosharaf Chowdhury
The "AI for Science, Energy, and Security" report from DOE outlines a significant focus on developing and optimizing artificial intelligence workflows for a foundational impact on…
Reducing Energy Bloat in Large Model Training
Jae-Won Chung, Yile Gu, Insu Jang +3
Training large AI models on numerous GPUs consumes a massive amount of energy, making power delivery one of the largest limiting factors in building and operating datacenters for A…