Papers by Alex Lu
Evolutionary Strategies at Scale lead to Catastrophic Forgetting (2026.acl-short)
Copied to clipboard
| Challenge: | ES has been shown to improve performance on specific tasks, but it is accompanied by significant forgetting of prior abilities. |
| Approach: | They propose to use Evolutionary Strategies to train gradient-free algorithms to improve performance. |
| Outcome: | The proposed algorithm achieves performance numbers closer to GRPO for math and reasoning tasks, but forgets prior abilities. |
Let’s Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought (2023.emnlp-main)
Copied to clipboard
Vaishnavi Himakunthala, Andy Ouyang, Daniel Rose, Ryan He, Alex Mei, Yujie Lu, Chinmay Sonar, Michael Saxon, William Wang
| Challenge: | Existing studies show vision-language systems can reason about images using natural language, but their capacity for video reasoning remains underexplored. |
| Approach: | They propose to frame video reasoning as the sequential understanding of a small number of keyframes, thereby leveraging the power and robustness of vision-language systems' capacity to reason about images using natural language. |
| Outcome: | The proposed models can generate multiple intermediate keyframes and predict future keyframe, and they perform poorly on GPT-4, GPT-3, and VICUNA. |
ASL STEM Wiki: Dataset and Benchmark for Interpreting STEM Articles (2024.emnlp-main)
Copied to clipboard
Kayo Yin, Chinmay Singh, Fyodor Minakov, Vanessa Milan, Hal Daumé Iii, Cyril Zhang, Alex Lu, Danielle Bragg
| Challenge: | Deaf and hard-of-hearing students face significant barriers in accessing STEM education due to the scarcity of STEM resources in signed languages. |
| Approach: | They develop models to identify fingerspelled words in American Sign Language (ASL) given an English sentence and a video, the model detects which English phrase is fingerspelled in the clip. |
| Outcome: | ASL STEM Wiki is the first continuous signing dataset focused on STEM . it detects fingerspelled words and queries them for appropriate signs to suggest to interpreters. |
CluSanT: Differentially Private and Semantically Coherent Text Sanitization (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing implementations of Differential Privacy (DP) in NLP typically degrade semantic integrity and readability for humans, posing significant challenges for applications requiring high-quality, coherent text processing. |
| Approach: | They propose a text sanitization framework based on Metric Local Differential Privacy (MLDP) that uses large language models to create a set of potential substitute tokens and a parameterized cluster embedding to samaritize/substitute sensitive tokens. |
| Outcome: | The proposed framework can be tuned with parameters such that existing state-of-the-art token sanitization algorithms can be described and improved. |