2 citations · 3 across the 10 of their papers we have counts for
10 papers
MedCache: Efficient and Temporally Valid Memory for Longitudinal Clinical Agents
Hei Ting Chan, Hei Ting, Chan +6
Longitudinal clinical agents must maintain an evolving patient state from evidence distributed across visits, time points, and specialties. However, how agent memory should be desi…
A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings
Hei Ting, Hei Ting Chan, Chan +9
Medical AI has demonstrated specialist-level diagnostic accuracy, yet these capabilities remain largely inaccessible in resource-constrained rural settings where bandwidth is scarc…
LLMVisor: A Real-Time Latency Attribution Model for Multi-Tenant LLM Serving
Shuowei Jin, Xueshen Liu, Jiaxin Shan +4
As LLM inference shifts to multi-tenant GPU clusters, co-batching improves throughput but obscures per-tenant usage and limits control. Enabling fractional sharing of the inference…
Dynamic Linear Attention
Xin Wang, Hui Shen, Boyuan Zheng +7
The scalability of Large Language Models (LLMs) to long contexts is fundamentally constrained by the quadratic complexity of standard attention, motivating the adoption of linear a…
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
Haizhong Zheng, Yizhuo Di, Jiahui Wang +7
Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensiv…
Dr. Post-Training: A Data Regularization Perspective on LLM Post-Training
Pingbang Hu, Xueshen Liu, Z. Morley Mao +1
Data selection methods address a critical challenge in LLM post-training: effectively leveraging scarce, high-fidelity target data alongside abundant but imperfectly aligned genera…
Foundry: Template-Based CUDA Graph Context Materialization for Fast LLM Serving Cold Start
Xueshen Liu, Yongji Wu, Yuncheng Yao +3
Modern LLM service providers increasingly rely on autoscaling and parallelism reconfiguration to respond to rapidly changing workloads, but cold-start latency remains a major bottl…
RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
Yongji Wu, Xueshen Liu, Haizhong Zheng +5
Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows involve interleaving rollout and traini…
HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs
Yongji Wu, Xueshen Liu, Shuowei Jin +6
The Mixture-of-Experts (MoE) architecture has become increasingly popular as a method to scale up large language models (LLMs). To save costs, heterogeneity-aware training solution…
Compute Or Load KV Cache? Why Not Both?
Shuowei Jin, Xueshen Liu, Qingzhao Zhang +1
Large Language Models (LLMs) are increasingly deployed in large-scale online services, enabling sophisticated applications. However, the computational overhead of generating key-va…