14 citations · 18 across the 11 of their papers we have counts for
11 papers
Clear Preferences Leave Traces: Reference Model-Guided Sampling for Preference Learning
Nirav Diwan, Tolga Ergen, Dongsub Shim +1
Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on tra…
MapExplorer: New Content Generation from Low-Dimensional Visualizations
Xingjian Zhang, Ziyang Xiong, Shixuan Liu +6
Low-dimensional visualizations, or "projection maps," are widely used in scientific and creative domains to interpret large-scale and complex datasets. These visualizations not onl…
MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows
Xingjian Zhang, Yutong Xie, Jin Huang +8
Scientific innovation relies on detailed workflows, which include critical steps such as analyzing literature, generating ideas, validating these ideas, interpreting results, and i…
TOD-Flow: Modeling the Structure of Task-Oriented Dialogues
Sungryull Sohn, Yiwei Lyu, Anthony Liu +4
Task-Oriented Dialogue (TOD) systems have become crucial components in interactive artificial intelligence applications. While recent advances have capitalized on pre-trained langu…
Code Models are Zero-shot Precondition Reasoners
Lajanugen Logeswaran, Sungryull Sohn, Yiwei Lyu +5
One of the fundamental skills required for an agent acting in an environment to complete tasks is the ability to understand what actions are plausible at any given point. This work…
MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning
Dong-Ki Kim, Sungryull Sohn, Lajanugen Logeswaran +2
Recently, there has been an increasing interest in automated prompt optimization based on reinforcement learning (RL). This approach offers important advantages, such as generating…
Preserving Linear Separability in Continual Learning by Backward Feature Projection
Qiao Gu, Dongsub Shim, Florian Shkurti
Catastrophic forgetting has been a major challenge in continual learning, where the model needs to learn new tasks with limited or no access to data from previously seen tasks. To…
Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective
Sungmin Cha, Jihwan Kwak, Dongsub Shim +4
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evalu…
ExCon: Explanation-driven Supervised Contrastive Learning for Image Classification
Zhibo Zhang, Jongseong Jang, Chiheb Trabelsi +4
Contrastive learning has led to substantial improvements in the quality of learned embedding representations for tasks such as image classification. However, a key drawback of exis…
EDDA: Explanation-driven Data Augmentation to Improve Explanation Faithfulness
Ruiwen Li, Zhibo Zhang, Jiani Li +5
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be fa…
Online Class-Incremental Continual Learning with Adversarial Shapley Value
Dongsub Shim, Zheda Mai, Jihwan Jeong +3
As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while…