107 citations · 135 across the 14 of their papers we have counts for
14 papers
A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization
Shiye Lei, Zhihao Cheng, Dacheng Tao
Reinforcement learning (RL) post-training has increasingly demonstrated strong ability to elicit reasoning behaviors in large language models (LLMs). For training efficiency, rollo…
Offline Behavioral Data Selection
Shiye Lei, Zhihao Cheng, Dacheng Tao
Behavioral cloning is a widely adopted approach for offline policy learning from expert demonstrations. However, the large scale of offline behavioral datasets often results in com…
State Diversity Matters in Offline Behavior Distillation
Shiye Lei, Zhihao Cheng, Dacheng Tao
Offline Behavior Distillation (OBD), which condenses massive offline RL data into a compact synthetic behavioral dataset, offers a promising approach for efficient policy training…
EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance
Siyao Song, Cong Ma, Zhihao Cheng +5
Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcom…
Revisiting LLM Reasoning via Information Bottleneck
Shiye Lei, Zhihao Cheng, Kai Jia +1
Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR). By leveraging s…
EarthSynth: Generating Informative Earth Observation with Diffusion Models
Jiancheng Pan, Shiye Lei, Yuqian Fu +7
Remote sensing image (RSI) interpretation typically faces challenges due to the scarcity of labeled data, which limits the performance of RSI interpretation tasks. To tackle this c…
Offline Behavior Distillation
Shiye Lei, Sen Zhang, Dacheng Tao
Massive reinforcement learning (RL) data are typically collected to train policies offline without the need for interactions, but the large data volume can cause training inefficie…
Image Captions are Natural Prompts for Text-to-Image Models
Shiye Lei, Hao Chen, Sen Zhang +2
With the rapid development of Artificial Intelligence Generated Content (AIGC), it has become a common practice to train models on synthetic data due to data-scarcity and privacy l…
A Comprehensive Survey of Dataset Distillation
Shiye Lei, Dacheng Tao
Deep learning technology has developed unprecedentedly in the last decade and has become the primary choice in many application domains. This progress is mainly attributed to a sys…
Understanding Deep Learning via Decision Boundary
Shiye Lei, Fengxiang He, Yancheng Yuan +1
This paper discovers that the neural network with lower decision boundary (DB) variability has better generalizability. Two new notions, algorithm DB variability and -data…
Spatial-Temporal-Fusion BNN: Variational Bayesian Feature Layer
Shiye Lei, Zhuozhuo Tu, Leszek Rutkowski +4
Bayesian neural networks (BNNs) have become a principal approach to alleviate overconfident predictions in deep learning, but they often suffer from scaling issues due to a large n…
Spectral Complexity-scaled Generalization Bound of Complex-valued Neural Networks
Haowen Chen, Fengxiang He, Shiye Lei +1
Complex-valued neural networks (CVNNs) have been widely applied to various fields, especially signal processing and image recognition. However, few works focus on the generalizatio…
Neural networks behave as hash encoders: An empirical study
Fengxiang He, Shiye Lei, Jianmin Ji +1
The input space of a neural network with ReLU-like activations is partitioned into multiple linear regions, each corresponding to a specific activation pattern of the included ReLU…
Accelerating temporal action proposal generation via high performance computing
Tian Wang, Shiye Lei, Youyou Jiang +3
Temporal action recognition always depends on temporal action proposal generation to hypothesize actions and algorithms usually need to process very long video sequences and output…