6 papers
Memory-Efficient Continual Learning with CLIP Models
Ryan King, Gang Li, Bobak Mortazavi +1
Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forgetting prior knowledge. To a…
DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
Gang Li, Yan Chen, Ming Lin +1
Recent large reasoning models (LRMs) driven by reinforcement learning algorithms (e.g., GRPO) have achieved remarkable performance on challenging reasoning tasks. However, these mo…
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
Gang Li, Ming Lin, Tomer Galanti +2
The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning…
Single-loop Algorithms for Stochastic Non-convex Optimization with Weakly-Convex Constraints
Ming Yang, Gang Li, Quanqi Hu +2
Constrained optimization with multiple functional inequality constraints has significant applications in machine learning. This paper examines a crucial subset of such problems whe…
A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety
Gang Li, Wendi Yu, Yao Yao +4
In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training…
Multi-Output Distributional Fairness via Post-Processing
Gang Li, Qihang Lin, Ayush Ghosh +1
The post-processing approaches are becoming prominent techniques to enhance machine learning models' fairness because of their intuitiveness, low computational cost, and excellent…