4 papers
Enhanced image classification via hybridizing quantum dynamics with classical neural networks
Ruiyang Zhou, Saubhik Sarkar, Sougato Bose +1
The integration of quantum computing and machine learning has emerged as a promising frontier in computational science. We present a hybrid protocol which combines classical neural…
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
Ruiyang Zhou, Shuozhe Li, Amy Zhang +1
Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without gu…
Depth as Points: Center Point-based Depth Estimation
Zhiheng Tu, Xinjian Huang, Yong He +3
The perception of vehicles and pedestrians in urban scenarios is crucial for autonomous driving. This process typically involves complicated data collection, imposes high computati…
Analysis of Levenshtein Transformer's Decoder and Its Variants
Ruiyang Zhou
Levenshtein transformer (LevT) is a non-autoregressive machine translation model with high decoding efficiency and comparable translation quality in terms of bleu score, due to its…