Picture for Lizhong Chen

Lizhong Chen

ML For Hardware Design Interpretability: Challenges and Opportunities

Add code
Apr 11, 2025
Viaarxiv icon

Hessian-aware Training for Enhancing DNNs Resilience to Parameter Corruptions

Add code
Apr 02, 2025
Viaarxiv icon

MatrixKAN: Parallelized Kolmogorov-Arnold Network

Add code
Feb 11, 2025
Viaarxiv icon

Neurons for Neutrons: A Transformer Model for Computation Load Estimation on Domain-Decomposed Neutron Transport Problems

Add code
Nov 05, 2024
Viaarxiv icon

LLM-Ref: Enhancing Reference Handling in Technical Writing with Large Language Models

Add code
Nov 04, 2024
Viaarxiv icon

LLM-RankFusion: Mitigating Intrinsic Inconsistency in LLM-based Ranking

Add code
May 31, 2024
Viaarxiv icon

LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions

Add code
May 18, 2024
Figure 1 for LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
Figure 2 for LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
Figure 3 for LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
Figure 4 for LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions
Viaarxiv icon

Simultaneous Masking, Not Prompting Optimization: A Paradigm Shift in Fine-tuning LLMs for Simultaneous Translation

Add code
May 16, 2024
Viaarxiv icon

FLAASH: Flexible Accelerator Architecture for Sparse High-Order Tensor Contraction

Add code
Apr 25, 2024
Viaarxiv icon

Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models

Add code
Dec 12, 2023
Viaarxiv icon