3 citations · 3 across the 13 of their papers we have counts for
9 papers · 1 filter
BARTER: Compact Dynamic Sparse Training with Standard Dense Kernels
Yueyuan Sui, Payal Mohapatra, Qi Zhu +1
Dynamic sparse training (DST) aims to reduce training costs while maintaining accuracy. Existing DST methods mask out parameters but keep matrix dimensions unchanged. Training spee…
Source-Learned Reliance for Selective Test-Time Adaptation of Multimodal Time Series
Payal Mohapatra, Yueyuan Sui, Haodong Yang +3
Multimodal wearable systems must remain reliable when sensor streams become noisy or unavailable. Existing multimodal test-time adaptation (TTA) methods often assess reliability on…
Efficient Multimodal Inference through Adaptive Acquisition and Sequential Fusion
Payal Mohapatra, Haodong Yang, Yueyuan Sui +3
Multimodal systems often encode every available input, even when a subset suffices for prediction. Adaptive acquisition can reduce this cost by using predictions from incrementally…
Towards Localizing Conversation Partners using Head Motion
Payal Mohapatra, Calvin Murdock, Ali Aroudi +4
Many individuals struggle to understand conversation partners in noisy settings, particularly amid background speakers or due to hearing impairments. Emerging wearables like smartg…
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.…
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…
EmboAlign: Aligning Video Generation with Compositional Constraints for Zero-Shot Manipulation
Gehao Zhang, Zhenyang Ni, Payal Mohapatra +3
Video generative models (VGMs) pretrained on large-scale internet data can produce temporally coherent rollout videos that capture rich object dynamics, offering a compelling found…
STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models
Xiangyu Shi, Junyang Ding, Xu Zhao +8
Computer-aided design (CAD) is vital to modern manufacturing, yet model creation remains labor-intensive and expertise-heavy. To enable non-experts to translate intuitive design in…
TimeSliver : Symbolic-Linear Decomposition for Explainable Time Series Classification
Akash Pandey, Payal Mohapatra, Wei Chen +2
Identifying the extent to which every temporal segment influences a model's predictions is essential for explaining model decisions and increasing transparency. While post-hoc expl…