collaborators

7 papers

cs.LG2026

Depth Exploration for LLM Decoding

Weisi Yang, Zipeng Sun, Stephen Xia

Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths. Existing lossless depth…

cs.LG2026

Attention Drift: What Autoregressive Speculative Decoding Models Learn

Doğaç Eldenk, Payal Mohapatra, Yigitcan Comlek +3

Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturbation and long-context inputs.…

cs.LG2026

Modality-Aware Zero-Shot Pruning and Sparse Attention for Efficient Multimodal Edge Inference

Yueyuan Sui, Payal Mohapatra, Doğaç Eldenk +5

Edge devices increasingly run multimodal sensing pipelines that must remain accurate despite fluctuating power budgets and unpredictable sensor dropout. Existing pruning methods fa…

cs.DC2026

UNIFERENCE: A Discrete Event Simulation Framework for Developing Distributed AI Models

Doğaç Eldenk, Stephen Xia

Developing and evaluating distributed inference algorithms remains difficult due to the lack of standardized tools for modeling heterogeneous devices and networks. Existing studies…

cs.LG2025

MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series

Payal Mohapatra, Yueyuan Sui, Akash Pandey +2

From clinical healthcare to daily living, continuous sensor monitoring across multiple modalities has shown great promise for real-world intelligent decision-making but also faces…

cs.LG2025

MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs

Hongjun Xu, Junxi Xia, Weisi Yang +2

Deploying Mamba models on microcontrollers (MCUs) remains challenging due to limited memory, the lack of native operator support, and the absence of embedded-friendly toolchains. W…