Wenlong Deng
Scholar

Wenlong Deng

Google Scholar ID: qckUjrMAAAAJ
University of British Columbia, Vector Institute
Machine LearningLarge Language Model
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
449
 
H-index
9
 
i10-index
9
 
Publications
19
 
Co-authors
2
list available
Contact
No contact links provided.
Publications
13 items
Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models
2026
Cited
0
Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents
2026
Cited
0
When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LVLMs
2026
Cited
0
Textual Equilibrium Propagation for Deep Compound AI Systems
2026
Cited
0
On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral
2025
Cited
0
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
2025
Cited
0
Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
2025
Cited
0
Efficient Forward-Only Data Valuation for Pretrained LLMs and VLMs
2025
Cited
0
Resume (English only)
Co-authors
2 total
Xiaoxiao Li
Xiaoxiao Li
Assistant Professor, UBC; Vector Institute; CIFAR AI Chair; Canada Research Chair
Christos Thrampoulidis
Christos Thrampoulidis
Assistant Professor, University of British Columbia, ECE Department