Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Not All Rollouts Are Worth Learning: On Trajectory Valuation for Post-Training Reinforcement Learning
Xuesong Jia, Ziao Yang, Zhanhe Huang +1
We consider the problem of trajectory valuation in reinforcement learning: how to identify and mitigate detrimental trajectories during online training. Unlike classification, wher…
cs.LG2026
Validation-Induced Shapley Shifts: How Validation Structure Distorts Data Valuation
Yinan Shen, Ziao Yang, Hongfu Liu
Shapley values are widely used to attribute value to training data based on their marginal contribution to performance on a validation set. Existing practice often assumes these va…
cs.CL2026
Recontextualizing Famous Quotes for Brand Slogan Generation
Ziao Yang, Zizhang Chen, Lei Zhang +1
Slogans are concise and memorable catchphrases that play a crucial role in advertising by conveying brand identity and shaping public perception. However, advertising fatigue reduc…