arXiv subjects

Ethan Zhang

Publications and source records attributed to Ethan Zhang.

5 recordsLinked to original sources

arXiv2026

ISER-MoE: Dynamic In-Switch Replication of Hot Experts for Load Balancing in Expert-Parallel

Expert-parallel mixture-of-experts (MoE) layers run at the pace of the most loaded GPU, and a few hot experts carry most of the excess load. Replicating them at every MoE layer balances the load only if their weights arrive within the layer, and broadcasting from the owner is the bottleneck: point-to-point copies overload it, and baseline broadcasts pay latency or bandwidth overheads. We present ISER-MoE (In-Switch Expert Replication for MoE), built in TensorRT-LLM, which multicasts hot experts through the NVLink switch to fixed GPU groups, so each byte leaves its owner once. A GPU scheduler assigns hot experts to groups per layer, and a multi-port broadcast spreads the injection over the group's ports, both overlapped with the shared expert. In trace replay, the scheduler removed 98-99% of the excess load; in prefill serving of DeepSeek-V4-Pro, throughput rose 17.4% on a math benchmark and 7.2% on agentic prompts.

cs.DC↗

arXiv2026

VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in Verus

We introduce VeriStruct, a novel framework that extends AI-assisted automated verification from single functions to more complex data structure modules in Verus. VeriStruct employs a planner module to orchestrate the systematic generation of abstractions, type invariants, specifications, and proof code. To address the challenge that LLMs often misunderstand Verus' annotation syntax and verification-specific semantics, VeriStruct embeds syntax guidance within prompts and includes a repair stage to automatically correct annotation errors. In an evaluation on eleven Rust data structure modules, VeriStruct succeeds on ten of the eleven, successfully verifying 128 out of 129 functions (99.2%) in total. These results represent an important step toward the goal of automatic AI-assisted formal verification.

cs.SE↗

arXiv2026

Uncovering Latent Bias in LLM-Based Emergency Department Triage Through Proxy Variables

Recent advances in large language models (LLMs) have enabled their integration into clinical decision-making; however, hidden biases against patients across racial, social, economic, and clinical backgrounds persist. In this study, we investigate bias in LLM-based medical AI systems applied to emergency department (ED) triage. We employ 32 patient-level proxy variables, each represented by paired positive and negative qualifiers, and evaluate their effects using both public (MIMIC-IV-ED Demo, MIMIC-IV Demo) and restricted-access credentialed (MIMIC-IV-ED and MIMIC-IV) datasets as appropriate~\cite{mimiciv_ed_demo,mimiciv_ed,mimiciv}. Our results reveal discriminatory behavior mediated through proxy variables in ED triage scenarios, as well as a systematic tendency for LLMs to modify perceived patient severity when specific tokens appear in the input context, regardless of whether they are framed positively or negatively. These findings indicate that AI systems is still imperfectly trained on noisy, sometimes non-causal signals that do not reliably reflect true patient acuity. Consequently, more needs to be done to ensure the safe and responsible deployment of AI technologies in clinical settings.

cs.AI↗

arXiv2024

SAPI: Surroundings-Aware Vehicle Trajectory Prediction at Intersections

In this work we propose a deep learning model, i.e., SAPI, to predict vehicle trajectories at intersections. SAPI uses an abstract way to represent and encode surrounding environment by utilizing information from real-time map, right-of-way, and surrounding traffic. The proposed model consists of two convolutional network (CNN) and recurrent neural network (RNN)-based encoders and one decoder. A refiner is proposed to conduct a look-back operation inside the model, in order to make full use of raw history trajectory information. We evaluate SAPI on a proprietary dataset collected in real-world intersections through autonomous vehicles. It is demonstrated that SAPI shows promising performance when predicting vehicle trajectories at intersection, and outperforms benchmark methods. The average displacement error(ADE) and final displacement error(FDE) for 6-second prediction are 1.84m and 4.32m respectively. We also show that the proposed model can accurately predict vehicle trajectories in different scenarios.

cs.LG↗

arXiv2024

MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR

Motion prediction has been an essential component of autonomous driving systems since it handles highly uncertain and complex scenarios involving moving agents of different types. In this paper, we propose a Multi-Granular TRansformer (MGTR) framework, an encoder-decoder network that exploits context features in different granularities for different kinds of traffic agents. To further enhance MGTR's capabilities, we leverage LiDAR point cloud data by incorporating LiDAR semantic features from an off-the-shelf LiDAR feature extractor. We evaluate MGTR on Waymo Open Dataset motion prediction benchmark and show that the proposed method achieved state-of-the-art performance, ranking 1st on its leaderboard (https://waymo.com/open/challenges/2023/motion-prediction/).

cs.CV↗