Ting-Yun Chang

Most-cited papers

Cosmos 3: Omnimodal World Models for Physical AI
Nvidia Aditi, Niket Agarwal, Arslan Ali, J. Allen +290 more
2026arXiv.org196 citations
Semantic Scholar
CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks
Tejas Srinivasan, Ting-Yun Chang, Leticia Pinto-Alva, Georgios Chochlakis +2 more
2022Neural Information Processing Systems97 citations Open access
Semantic Scholar
Data Curation Alone Can Stabilize In-context Learning
Ting-Yun Chang, Robin Jia
2022Annual Meeting of the Association for Computational Linguistics76 citations Open access
Semantic Scholar
Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks
Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan, Behnam Hedayatnia +2 more
2020Workshop on Knowledge Extraction and Integration for Deep Learning Architectures; Deep Learning Inside Out41 citations Open access
Semantic Scholar
What Does This Word Mean? Explaining Contextualized Embeddings with Natural Language Definition
Ting-Yun Chang, Yun-Nung (Vivian) Chen
2019Conference on Empirical Methods in Natural Language Processing41 citations Open access
Semantic Scholar
Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks
Ting-Yun Chang, Jesse Thomason, Robin Jia
2023North American Chapter of the Association for Computational Linguistics39 citations
Semantic Scholar
Rethinking Why Intermediate-Task Fine-Tuning Works
Ting-Yun Chang, Chi-Jen Lu
2021Conference on Empirical Methods in Natural Language Processing33 citations Open access
Semantic Scholar
TinyGAN: Distilling BigGAN for Conditional Image Generation
Ting-Yun Chang, Chi-Jen Lu
2020Asian Conference on Computer Vision27 citations Open access
Semantic Scholar
xSense: Learning Sense-Separated Sparse Representations and Textual Definitions for Explainable Word Sense Networks
Ting-Yun Chang, Ta-Chung Chi, Shang-Chi Tsai, Yun-Nung (Vivian) Chen
2018arXiv.org24 citations
Semantic Scholar
Leveraging Hierarchical Category Knowledge for Data-Imbalanced Multi-Label Diagnostic Text Understanding
Shang-Chi Tsai, Ting-Yun Chang, Yun-Nung (Vivian) Chen
2019Conference on Empirical Methods in Natural Language Processing13 citations Open access
Semantic Scholar
Value-Aware Stochastic KV Cache Eviction for Reasoning Models
Ting-Yun Chang, Harvey Yiyun Fu, Deqing Fu, Chenghao Yang +2 more
2026arXiv.org9 citations
Semantic Scholar
Why Do Some Inputs Break Low-Bit LLM Quantization?
Ting-Yun Chang, Muru Zhang, Jesse Thomason, Robin Jia
2025Conference on Empirical Methods in Natural Language Processing8 citations
Semantic Scholar
Careful Data Curation Stabilizes In-context Learning
Ting-Yun Chang, Robin Jia
2022arXiv.org8 citations Open access
Semantic Scholar
When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models
Ting-Yun Chang, Jesse Thomason, Robin Jia
2024Conference on Empirical Methods in Natural Language Processing7 citations
Semantic Scholar
SWE-IF: Aligning Code Evaluation with Human Preference
Ming Zhong, Xiang Zhou, Ting-Yun Chang, Qing-Ze Wang +8 more
20252 citations
Semantic Scholar
Go Beyond Plain Fine-Tuning: Improving Pretrained Models for Social Commonsense
Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan, Behnam Hedayatnia +2 more
2021Spoken Language Technology Workshop1 citations
Semantic Scholar