4 papers · 1 filter
Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
Cuong Dang, Hoang Anh Just, Ruoxi Jia
Terminal agents are commonly trained by imitating long teacher trajectories, yet how much of each trajectory to supervise remains unexplored. We study the \emph{supervision horizon…
Capacity-Dependent Effects of Data Selection for Reasoning
Cuong Dang, Hoang Anh Just, Ruoxi Jia
In reasoning supervised fine-tuning, candidate responses for the same instruction can differ substantially in how well they match the student's current distribution. Recent likelih…
The Confidence Trap: Calibration Attacks for Graph Neural Networks
Cuong Dang, Jiahao Zhang, Hieu Ta Quang +3
While confidence calibration is essential for trustworthy decision-making in safety-critical applications, the robustness of calibrated GNNs to adversarial structural perturbations…
A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
Cuong Dang, Dung D. Le, Thai Le
Existing works have shown that fine-tuned textual transformer models achieve state-of-the-art prediction performances but are also vulnerable to adversarial text perturbations. Tra…