69 citations · 151 across the 30 of their papers we have counts for
30 papers
EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making
Yang Cheng, Weiyu Ma, Zilai Wang +6
Complex decision-making often requires agents to progress through intermediate tasks rather than solve the final target directly. Existing LLM self-refinement methods typically ite…
Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
Bihan Xu, Shiwei Zhao, Runze Wu +10
Within the domain of Massively Multiplayer Online (MMO) economy research, Agent-Based Modeling (ABM) has emerged as a robust tool for analyzing game economics, evolving from rule-b…
The Effects of Data Augmentation on Confidence Estimation for LLMs
Rui Wang, Renyu Zhu, Minmin Lin +4
Confidence estimation is crucial for reflecting the reliability of large language models (LLMs), particularly in the widely used closed-source models. Utilizing data augmentation f…
Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards
Zhaohui Jiang, Xuening Feng, Paul Weng +6
In practice, reinforcement learning (RL) agents are often trained with a possibly imperfect proxy reward function, which may lead to a human-agent alignment issue (i.e., the learne…
StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads
Suzhen Wang, Yifeng Ma, Yu Ding +5
Individuals have unique facial expression and head pose styles that reflect their personalized speaking styles. Existing one-shot talking head methods cannot capture such personali…
Bayesian Design Principles for Offline-to-Online Reinforcement Learning
Hao Hu, Yiqin Yang, Jianing Ye +7
Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and fu…
vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement
Yiwen Zhu, Jinyi Liu, Wenya Wei +7
Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhanci…
Preconditioned Nonlinear Conjugate Gradient Method for Real-time Interior-point Hyperelasticity
Xing Shen, Runyuan Cai, Mengxiao Bi +1
The linear conjugate gradient method is widely used in physical simulation, particularly for solving large-scale linear systems derived from Newton's method. The nonlinear conjugat…
A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment
Fei Wang, Haoyu Liu, Haoyang Bi +9
For the purpose of efficient and cost-effective large-scale data labeling, crowdsourcing is increasingly being utilized. To guarantee the quality of data labeling, multiple annotat…
Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation
Renshuai Liu, Bowen Ma, Wei Zhang +5
In human-centric content generation, the pre-trained text-to-image models struggle to produce user-wanted portrait images, which retain the identity of individuals while exhibiting…
Towards Long-term Annotators: A Supervised Label Aggregation Baseline
Haoyu Liu, Fei Wang, Minmin Lin +6
Relying on crowdsourced workers, data crowdsourcing platforms are able to efficiently provide vast amounts of labeled data. Due to the variability in the annotation quality of crow…
AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
Zibin Dong, Yifu Yuan, Jianye Hao +7
Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human pre…
Examining the Effect of Pre-training on Time Series Classification
Jiashu Pu, Shiwei Zhao, Ling Cheng +4
Although the pre-training followed by fine-tuning paradigm is used extensively in many fields, there is still some controversy surrounding the impact of pre-training on the fine-tu…
Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
Renyu Zhu, Haoyu Liu, Runze Wu +4
In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambigui…
Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation
Haowei Wang, Jiji Tang, Jiayi Ji +8
In recent years, 3D understanding has turned to 2D vision-language pre-trained models to overcome data scarcity challenges. However, existing methods simply transfer 2D alignment s…
FlowFace++: Explicit Semantic Flow-supervised End-to-End Face Swapping
Yu Zhang, Hao Zeng, Bowen Ma +5
This work proposes a novel face-swapping framework FlowFace++, utilizing explicit semantic flow supervision and end-to-end architecture to facilitate shape-aware face-swapping. Spe…
Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning
Jinyi Liu, Yi Ma, Jianye Hao +4
In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL h…
Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations
Yufeng Huang, Jiji Tang, Zhuo Chen +8
Large-scale vision-language pre-training has achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on i…
TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles
Yifeng Ma, Suzhen Wang, Yu Ding +6
Audio-driven talking head generation has drawn growing attention. To produce talking head videos with desired facial expressions, previous methods rely on extra reference videos to…
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas +27
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 20…
DINet: Deformation Inpainting Network for Realistic Face Visually Dubbing on High Resolution Video
Zhimeng Zhang, Zhipeng Hu, Wenjin Deng +3
For few-shot learning, it is still a critical challenge to realize photo-realistic face visually dubbing on high-resolution videos. Previous works fail to generate high-fidelity du…
Towards Skilled Population Curriculum for Multi-Agent Reinforcement Learning
Rundong Wang, Longtao Zheng, Wei Qiu +7
Recent advances in multi-agent reinforcement learning (MARL) allow agents to coordinate their behaviors in complex environments. However, common MARL algorithms still suffer from s…
StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles
Yifeng Ma, Suzhen Wang, Zhipeng Hu +5
Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial express…
TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective
Pengfei Xi, Guifeng Wang, Zhipeng Hu +8
Determining causal effects of temporal multi-intervention assists decision-making. Restricted by time-varying bias, selection bias, and interactions of multiple interventions, the…