Papers by Xuan Zhu
TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents (2025.emnlp-demos)
Copied to clipboard
Haofei Yu, Keyang Xuan, Fenghai Li, Kunlun Zhu, Zijie Lei, Jiaxun Zhang, Ziheng Qi, Kyle Richardson, Jiaxuan You
| Challenge: | Existing research systems often design and use agentic workflows to perform research tasks such as ideation, scientific coding, review writing, and tree-based search. |
| Approach: | They propose an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer. |
| Outcome: | The proposed framework adapts easily to new tools and supports iterative growth. |
Improving Robustness of Language Models from a Geometry-aware Perspective (2022.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. |
| Approach: | They propose friendly adversarial data augmentation and geometry-aware adversarial training to achieve stronger robustness using fewer search steps. |
| Outcome: | The proposed method can obtain stronger robustness using fewer steps than existing methods. |
Spotlighter: Revisiting Prompt Tuning from a Representative Mining View (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Spotlighter is a lightweight token-selection framework that enhances accuracy and efficiency in prompt tuning. |
| Approach: | They propose a token-selection framework that enhances accuracy and efficiency in prompt tuning by preserving only the top-scoring tokens for downstream prediction. |
| Outcome: | The proposed framework outperforms CLIP by up to 11.19% in harmonic mean accuracy and achieves 0.8K additional FPS, with only 21 extra parameters. |
InfoEnh: Towards Multimodal Sentiment Analysis via Information Bottleneck Filter and Optimal Transport Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for multi-modal sentiment analysis have been developed to overcome these challenges. |
| Approach: | They propose a method that utilizes a masking technique as the bottleneck for information filtering and integrates all modalities into a common feature space via domain adaptation. |
| Outcome: | Extensive experiments on two benchmark MSA datasets show the proposed method performs better than baselines. |
Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing descriptive statistics are inadequate to summarize text collections by quantitative measures. |
| Approach: | They propose a set of characteristic metrics that quantitatively measure the dispersion, sparsity, and uniformity of a text collection. |
| Outcome: | The proposed metrics are highly correlated with text classification performance of a renowned model, which could inspire future applications. |
When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models (2026.acl-long)
Copied to clipboard
| Challenge: | Vision-Language-Action models have shown strong performance in language-conditioned robotic manipulation, yet their robustness to linguistic variation remains poorly understood. |
| Approach: | They propose a step-wise inference-time intervention that aligns representations according to step language sensitivity, significantly improving performance under linguistic variation. |
| Outcome: | The proposed model significantly improves performance under linguistic variation under non-English instructions under language-agnostic steps. |
Context-Aware Tracking and Dynamic Introduction for Incomplete Utterance Rewriting in Extended Multi-Turn Dialogues (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reconstruct utterance with omitted information and pronouns are limited to brief multi-turn dialogues. |
| Approach: | They propose a method to reconstruct utterance with omitted information and pronouns to be standalone and complete based on context. |
| Outcome: | The proposed method improves existing models and achieves state-of-the-art on three benchmarks. |
Quantifying Context Overlap for Training Word Embeddings (D18-1)
Copied to clipboard
| Challenge: | Experimental results show that word embeddings can be improved using word embeds . word embedings are a popular form of natural language processing . |
| Approach: | They propose to estimate second order co-occurrence relations based on context overlap . they use the augmented data to enhance word embeddings learning . |
| Outcome: | The proposed model improves word vectors for word similarity and downstream NLP tasks. |
How to Improve LLMs’ Performance on Specific Languages: A Perspective on LLM-Derived Language Similarity (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit uneven performance across languages. |
| Approach: | They propose to use a framework to quantify the similarity within each language pair through both the lenses of language-specific performance patterns and cross-lingual transferability. |
| Outcome: | The proposed approach outperforms traditional linguistic typology and cross-lingual transferability measures on multilingual LLMs. |