6 citations · 9 across the 11 of their papers we have counts for
13 papers
Human Demonstrations as Post-Training Data for Any Robot Body: Retargeting the Object, Not the Hand
Nagasrikanth Kallakuri
Human demonstrations are today used largely for pretraining vision-language-action models, with little ability to use the same data for target-embodiment or task-oriented training,…
Towards Efficient HPC Systems for Agents: Challenges and Opportunities
Yunjia Zheng, Bintang Dwi Marthen, Zachary Pan +5
Coding agents have become real users of high-performance computing (HPC) systems, yet today's HPC abstractions, interfaces, and policies remain designed for human-driven workflows.…
TrajectoryDB: A New Database for Agent Trajectories
Yunjia Zheng, Juncheng Yang
AI agents generate rich execution trajectories that capture their interactions with large language models, tools, and external environments. These trajectories are increasingly val…
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
William Nixon, Jon Durbin, Florian Standhartinger +2
Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems. However, existing LLM s…
HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models
Renjie Xie, Juncheng Yang, Aoting Hu +4
Long-context inference retains a growing key--value (KV) cache during decoding, which consumes substantial GPU memory and can reduce generation throughput. This bottleneck remains…
Demystifying and Improving Lazy Promotion in Cache Eviction
Qinghan Chen, Muhammad Haekal Muhyidin Al-Araby, Ziyue Qiu +3
Cache eviction algorithms play a critical role in the performance of modern data systems, yet their scalability is often limited by the high computational overhead associated with…
LAANN: I/O-Aware Look-Ahead Search for Disk-Based Approximate Nearest Neighbor Search
Dingyi Kang, Juncheng Yang, Bingzhe Li
Approximate nearest neighbor search (ANNS) is a fundamental primitive in large-scale retrieval, recommendation, and AI systems. As vector datasets grow to billions or even trillion…
LatentStore: An Efficient Latent-First Storage System for AI-Generated Images
Zirui Wang, Yunjia Zheng, Tingfeng Lan +4
The explosive growth of AI-generated images has created a sustainability challenge for storage infrastructure. Platforms like Midjourney and Adobe Firefly already host billions of…
MoE-Prefill: Zero Redundancy Overheads in MoE Prefill Serving
Zhaoyuan Su, Olatunji Ruwase, Karthik Ganesan +5
Production LLM workloads increasingly serve discriminative tasks, such as classification, recommendation, and verification, whose answers are read from the logits of a single prefi…
TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models
Tingfeng Lan, Zirui Wang, Yunjia Zheng +3
Modern model hubs store hundreds of petabytes of large language models (LLMs), with fine-tuned variants dominating the storage footprint. These variants contain substantial cross-m…
Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow
Yixuan Mei, Yonghao Zhuang, Xupeng Miao +3
This paper introduces Helix, a distributed system for high-throughput, low-latency large language model (LLM) serving in heterogeneous GPU clusters. The key idea behind Helix is to…
Can Increasing the Hit Ratio Hurt Cache Throughput? (Long Version)
Ziyue Qiu, Juncheng Yang, Mor Harchol-Balter
Software caches are an intrinsic component of almost every computer system. Consequently, caching algorithms, particularly eviction policies, are the topic of many papers. Almost a…
PACEMAKER: Avoiding HeART attacks in storage clusters with disk-adaptive redundancy
Saurabh Kadekodi, Francisco Maturana, Suhas Jayaram Subramanya +3
Data redundancy provides resilience in large-scale storage clusters, but imposes significant cost overhead. Substantial space-savings can be realized by tuning redundancy schemes t…