Papers by Zhangyang Wang

6 papers
Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration (2026.findings-acl)

Copied to clipboard

Challenge: CadLLM is a plug-and-play model-agnostic with KV caching based dLLMs.
Approach: They propose a lightweight adaptive method that can control the generation block size, step size, and threshold based on the average confidence score of unmasked tokens.
Outcome: The proposed method can increase throughput by up to 1.1-2.28x over the state-of-the-art model with competitive accuracy.
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets (2021.acl-long)

Copied to clipboard

Challenge: Large-scale pre-trained language models require enormous computational resources and long training time.
Approach: They propose an algorithm to reduce inference time and train large NLP models by slimming the self-attention and fully-connected sub-layers inside a transformer.
Outcome: The proposed algorithm achieves comparable performance to standard BERT with 35 45% less training time.
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement (2025.acl-long)

Copied to clipboard

Challenge: Existing time series models focus on a narrow spectrum of tasks, such as forecasting or anomaly detection.
Approach: They propose a framework that enables natural language queries across multiple time series tasks such as numerical analytical tasks and open-ended question answering with reasoning.
Outcome: The proposed framework enables natural language queries across multiple time series tasks and allows for more advanced and intuitive interactions with temporal data.
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models (2023.acl-long)

Copied to clipboard

Challenge: Conventional fine-tuning works through updating all of the parameters in the pre-trained model, but as the size of pre-train models grows, it can be time-consuming and computationally expensive.
Approach: They propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights.
Outcome: The proposed framework saves 25% inference FLOPs while maintaining competitive downstream performance.
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) generate plausible but factually incorrect outputs, posing serious risks to patient safety and clinical decision-making.
Approach: They propose a benchmark for medical hallucination detection using 10,000 question-answer pairs derived from PubMedQA.
Outcome: The proposed model achieves an F1 score as low as 0.625 for detecting 'hard' category hallucinations.
RankMean: Module-Level Importance Score for Merging Fine-tuned LLM Models (2024.findings-acl)

Copied to clipboard

Challenge: Traditionally, developing new language models involves fine-tuning pre-trained LMs . model merging is a cost-effective alternative to fine-timing LM models for multiple tasks .
Approach: They propose an algorithm for merging fine-tuned language models without additional training.
Outcome: The proposed algorithm outperforms baseline methods on multiple benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations