26 citations · 42 across the 18 of their papers we have counts for
18 papers
Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization
Juntao Dai, Taiye Chen, Yaodong Yang +2
Reinforcement learning from human feedback (RLHF) is an effective method for aligning large language models (LLMs) with human values. However, reward over-optimization remains an o…
Darkit: A User-Friendly Software Toolkit for Spiking Large Language Model
Xin Du, Shifan Ye, Qian Zheng +7
Large language models (LLMs) have been widely applied in various practical applications, typically comprising billions of parameters, with inference processes requiring substantial…
Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation
Juntao Dai, Yaodong Yang, Qian Zheng +1
A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy…
Copiloting Diagnosis of Autism in Real Clinical Scenarios via LLMs
Yi Jiang, Qingyang Shen, Shuzhong Lai +5
Autism spectrum disorder(ASD) is a pervasive developmental disorder that significantly impacts the daily functioning and social participation of individuals. Despite the abundance…
Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directions
Yangfan Hu, Qian Zheng, Guoqi Li +2
Deep learning has revolutionized artificial intelligence (AI), achieving remarkable progress in fields such as computer vision, speech recognition, and natural language processing.…
Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline
Wenjia Meng, Qian Zheng, Long Yang +2
Policy-based methods have achieved remarkable success in solving challenging reinforcement learning problems. Among these methods, off-policy policy gradient methods are particular…
Spiking NeRF: Representing the Real-World Geometry by a Discontinuous Representation
Zhanfeng Liao, Qian Zheng, Yan Liu +1
A crucial reason for the success of existing NeRF-based methods is to build a neural density field for the geometry representation via multiple perceptron layers (MLPs). MLPs are c…
Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification
Dong Xing, Pengjie Gu, Qian Zheng +5
Ad hoc teamwork requires an agent to cooperate with unknown teammates without prior coordination. Many works propose to abstract teammate instances into high-level representation o…
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN
Yangfan Hu, Qian Zheng, Xudong Jiang +1
Spiking neural networks (SNNs) have shown advantages in computation and energy efficiency over traditional artificial neural networks (ANNs) thanks to their event-driven representa…
DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering
Zongrui Li, Qian Zheng, Boxin Shi +2
Uncalibrated photometric stereo (UPS) is challenging due to the inherent ambiguity brought by the unknown light. Although the ambiguity is alleviated on non-Lambertian objects, the…
NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereo
Zongrui Li, Qian Zheng, Feishi Wang +3
Uncalibrated photometric stereo (UPS) is challenging due to the inherent ambiguity brought by unknown light. Existing solutions alleviate the ambiguity by either explicitly associa…
TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources
Dong Xing, Qian Zheng, Qianhui Liu +1
Recent advances in deep reinforcement learning (DRL) have largely promoted the performance of adaptive traffic signal control (ATSC). Nevertheless, regarding the implementation, mo…
On Convergence of Gradient Expected Sarsa()
Long Yang, Gang Zheng, Yu Zhang +3
We study the convergence of with linear function approximation. We show that applying the off-line estimate (multi-step bootstrapping) to $\mathtt{Expe…
Sample Complexity of Policy Gradient Finding Second-Order Stationary Points
Long Yang, Qian Zheng, Gang Pan
The goal of policy-based reinforcement learning (RL) is to search the maximal point of its objective. However, due to the inherent non-concavity of its objective, convergence to a…
Gradient Q: A Unified Algorithm with Function Approximation for Reinforcement Learning
Long Yang, Yu Zhang, Qian Zheng +2
Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q is the firs…
Policy Optimization with Stochastic Mirror Descent
Long Yang, Yu Zhang, Gang Zheng +5
Improving sample efficiency has been a longstanding goal in reinforcement learning. This paper proposes algorithm: a sample efficient policy gradient method with s…
Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network
Wenjia Meng, Qian Zheng, Long Yang +2
The deep Q-network (DQN) and return-based reinforcement learning are two promising algorithms proposed in recent years. DQN brings advances to complex sequential decision problems,…
A Unified Approach for Multi-step Temporal-Difference Learning with Eligibility Traces in Reinforcement Learning
Long Yang, Minhao Shi, Qian Zheng +2
Recently, a new multi-step temporal learning algorithm, called , unifies -step Tree-Backup (when ) and -step Sarsa (when ) by introducing a sampling parameter…