Wang, Shuo

C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs

Recently, significant accuracy improvement has been achieved for acoustic recognition systems by increasing the model size of Long Short-Term Memory (LSTM) networks. Unfortunately, the...

Idioms Understood, Yet Translated Literally: Diagnosing Literal Translation Bias in Multilingual LLMs

Staying on Task: Defending Against Prompt Injection via Task Consistency Checking

Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts

Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data

Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval

Open Human Value Mining: Constrained Argument Extraction and Value Concept Induction with LLMs

Writing As Reasoning: Interleaving Drafting and Deepening for Open-Ended Deep Research

Latent Visual Sensitive Fingerprinting for Black-Box Vision--Language Model Tamper Detection

MegaCode: A Repository-Level Dataset for Long-Context Code Reasoning

MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents

ScholarGraph:a Chinese Knowledge Graph of Chinese Scholars

Improving Back-Translation with Uncertainty-based Confidence Estimation

On the Inference Calibration of Neural Machine Translation

THUMT: An Open-Source Toolkit for Neural Machine Translation

On the Language Coverage Bias for Neural Machine Translation

Integrating Vectorized Lexical Constraints for Neural Machine Translation

MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators