activity
20242026
collaborators

6 papers

cs.CV2026

ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models

Yihao Wang, Zijian He, Jie Ren +1

Multimodal large language models (MLLMs) are increasingly expected to act on visual information, yet the same scene may require different actions under different task contexts. How…

cs.DC2026

Nitsum: Serving Tiered LLM Requests with Adaptive Tensor Parallelism

Vikranth Srivatsa, Zijian He, Pu Guo +2

LLM serving is increasingly multi-tenant: the same deployment must handle latency-critical interactive requests and more relaxed background workloads under a fixed GPU budget. This…

cs.DC2026

VDCores: Resource Decoupled Programming and Execution for Asynchronous GPU

Zijian He, Adrian Sampson, Yiying Zhang +1

Modern GPUs increasingly rely on specialized and asynchronous hardware units to deliver high performance. Yet these units are often underutilized because today's GPU software stack…

cs.CL2026

ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals

Yihao Wang, Zijian He, Jie Ren +1

Retrieval shapes how language models access and ground knowledge in retrieval-augmented generation (RAG). In historical research, the target is often not an arbitrary relevant pass…

cs.LG2025

Cognify: Supercharging Gen-AI Workflows With Hierarchical Autotuning

Zijian He, Reyna Abhyankar, Vikranth Srivatsa +1

Today's gen-AI workflows that involve multiple ML model calls, tool/API calls, data retrieval, or generic code execution are often tuned manually in an ad-hoc way that is both time…

cs.DC2024

Preble: Efficient Distributed Prompt Scheduling for LLM Serving

Vikranth Srivatsa, Zijian He, Reyna Abhyankar +2

Prompts to large language models (LLMs) have evolved beyond simple user questions. For LLMs to solve complex problems, today's practices are to include domain-specific instructions…