most citedStratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving

7 citations · 7 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CL2026

JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting

Lanxiang Hu, Zhaoxiang Feng, Yulun Wu +9

Speculative decoding (SD) accelerates autoregressive Large Language Models (LLMs) by drafting multiple tokens and verifying them in parallel, but it faces a scaling limitation: inc…

cs.CV2026

HyperLiDAR: Adaptive Post-Deployment LiDAR Segmentation via Hyperdimensional Computing

Ivannia Gomez Moreno, Yi Yao, Ye Tian +7

LiDAR semantic segmentation plays a pivotal role in 3D scene understanding for edge applications such as autonomous driving. However, significant challenges remain for real-world d…

cs.CV2025

Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench

Lanxiang Hu, Abhilash Shankarampeta, Yixin Huang +7

The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical out…

cs.AR20257 cited

Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving

Yue Pan, Zihan Xia, Po-Kai Hsu +8

As Large Language Models (LLMs) continue to evolve, Mixture of Experts (MoE) architecture has emerged as a prevailing design for achieving state-of-the-art performance across a wid…

cs.AI2025

Towards Interpretable and Inference-Optimal COT Reasoning with Sparse Autoencoder-Guided Generation

Daniel Zhao, Abhilash Shankarampeta, Lanxiang Hu +2

We propose a novel method that leverages sparse autoencoders (SAEs) and clustering techniques to analyze the internal token representations of large language models (LLMs) and guid…

cs.CL2025

SensorQA: A Question Answering Benchmark for Daily-Life Monitoring

Benjamin Reichman, Xiaofan Yu, Lanxiang Hu +5

With the rapid growth in sensor data, effectively interpreting and interfacing with these data in a human-understandable way has become crucial. While existing research primarily f…