Changjie Fan
YOU?
Author Swipe
View article: High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics
High-Precision and High-Efficiency Trajectory Tracking for Excavators Based on Closed-Loop Dynamics Open
The complex nonlinear dynamics of hydraulic excavators, such as time delays and control coupling, pose significant challenges to achieving high-precision trajectory tracking. Traditional control methods often fall short in such application…
View article: Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling Open
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-based agents to decision-making agents enhanced by reinforce…
View article: The Effects of Data Augmentation on Confidence Estimation for LLMs
The Effects of Data Augmentation on Confidence Estimation for LLMs Open
Confidence estimation is crucial for reflecting the reliability of large language models (LLMs), particularly in the widely used closed-source models. Utilizing data augmentation for confidence estimation is viable, but discussions focus o…
View article: Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection
Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection Open
Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame charac…
View article: DialogDraw: Image Generation and Editing System Based on Multi-Turn Dialogue
DialogDraw: Image Generation and Editing System Based on Multi-Turn Dialogue Open
In recent years, diffusion modeling has shown great potential for image generation and editing. Beyond single-model approaches, various drawing workflows now exist to handle diverse drawing tasks. However, few solutions effectively identif…
View article: LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation
LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation Open
Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In …
View article: Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its Applications
Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its Applications Open
View article: CrowdAgent: Multi-Agent Managed Multi-Source Annotation System
CrowdAgent: Multi-Agent Managed Multi-Source Annotation System Open
View article: Neteasecrowd: A Large-Scale Dataset for Long-Term and Online Crowdsourcing Truth Inference
Neteasecrowd: A Large-Scale Dataset for Long-Term and Online Crowdsourcing Truth Inference Open
View article: FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model
FreeAvatar: Robust 3D Facial Animation Transfer by Learning an Expression Foundation Model Open
Video-driven 3D facial animation transfer aims to drive avatars to reproduce\nthe expressions of actors. Existing methods have achieved remarkable results by\nconstraining both geometric and perceptual consistency. However, geometric\ncons…
View article: Rank Aggregation in Crowdsourcing for Listwise Annotations
Rank Aggregation in Crowdsourcing for Listwise Annotations Open
Rank aggregation through crowdsourcing has recently gained significant attention, particularly in the context of listwise ranking annotations. However, existing methods primarily focus on a single problem and partial ranks, while the aggre…
View article: Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards
Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards Open
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 learned policy either converges to non-optimal performance with l…
View article: Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection
Storynizor: Consistent Story Generation via Inter-Frame Synchronized and Shuffled ID Injection Open
Recent advances in text-to-image diffusion models have spurred significant interest in continuous story image generation. In this paper, we introduce Storynizor, a model capable of generating coherent stories with strong inter-frame charac…
View article: EA-RAS: Towards Efficient and Accurate End-to-End Reconstruction of Anatomical Skeleton
EA-RAS: Towards Efficient and Accurate End-to-End Reconstruction of Anatomical Skeleton Open
Efficient, accurate and low-cost estimation of human skeletal information is crucial for a range of applications such as biology education and human-computer interaction. However, current simple skeleton models, which are typically based o…
View article: MGMatch: Fast Matchmaking with Nonlinear Objective and Constraints via Multimodal Deep Graph Learning
MGMatch: Fast Matchmaking with Nonlinear Objective and Constraints via Multimodal Deep Graph Learning Open
As a core problem of online games, matchmaking is to assign players into multiple teams to maximize their gaming experience. With the rapid development of game industry, it is increasingly difficulty to explicitly model players' experience…
View article: LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation
LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation Open
Diffusion models have exhibited substantial success in text-to-image generation. However, they often encounter challenges when dealing with complex and dense prompts involving multiple objects, attribute binding, and long descriptions. In …
View article: Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization
Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization Open
Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have encou…
View article: Bayesian Design Principles for Offline-to-Online Reinforcement Learning
Bayesian Design Principles for Offline-to-Online Reinforcement Learning Open
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 further online fine-tuning is required. In this paper, we tac…
View article: vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement
vMFER: Von Mises-Fisher Experience Resampling Based on Uncertainty of Gradient Directions for Policy Improvement Open
Reinforcement Learning (RL) is a widely employed technique in decision-making problems, encompassing two fundamental operations -- policy evaluation and policy improvement. Enhancing learning efficiency remains a key challenge in RL, with …
View article: The MMO Economist: AI Empowers Robust, Healthy, and Sustainable P2W MMO Economies
The MMO Economist: AI Empowers Robust, Healthy, and Sustainable P2W MMO Economies Open
Massively Multiplayer Online Games (MMOs) feature intricate virtual economies that permeate various in-game activities. However, the balancing act between profitability and equality in MMO economic design proves to be a persistent conundru…
View article: EnMatch: Matchmaking for Better Player Engagement via Neural Combinatorial Optimization
EnMatch: Matchmaking for Better Player Engagement via Neural Combinatorial Optimization Open
Matchmaking is a core task in e-sports and online games, as it contributes to player engagement and further influences the game's lifecycle. Previous methods focus on creating fair games at all times. They divide players into different tie…
View article: Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning
Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning Open
In cooperative multi-agent reinforcement learning, decentralized agents hold the promise of overcoming the combinatorial explosion of joint action space and enabling greater scalability. However, they are susceptible to a game-theoretic pa…
View article: ICE: Interactive 3D Game Character Editing via Dialogue
ICE: Interactive 3D Game Character Editing via Dialogue Open
ost recent popular Role-Playing Games (RPGs) allow players to create in-game characters with hundreds of adjustable parameters, including bone positions and various makeup options. Although text-driven auto-customization systems have been …
View article: A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment
A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment Open
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 annotations need to be collected for each data sample, and truth i…
View article: XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques
XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques Open
Reinforcement Learning (RL) has demonstrated substantial potential across diverse fields, yet understanding its decision-making process, especially in real-world scenarios where rationality and safety are paramount, is an ongoing challenge…
View article: Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation
Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation Open
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 diverse expressions. This paper introduces our efforts tow…
View article: Towards Long-term Annotators: A Supervised Label Aggregation Baseline
Towards Long-term Annotators: A Supervised Label Aggregation Baseline Open
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 crowd workers, modern techniques resort to redundant annotation…
View article: A New Baseline Assumption of Integated Gradients Based on Shaply value
A New Baseline Assumption of Integated Gradients Based on Shaply value Open
Efforts to decode deep neural networks (DNNs) often involve mapping their predictions back to the input features. Among these methods, Integrated Gradients (IG) has emerged as a significant technique. The selection of appropriate baselines…
View article: AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model Open
Aligning agent behaviors with diverse human preferences remains a challenging problem in reinforcement learning (RL), owing to the inherent abstractness and mutability of human preferences. To address these issues, we propose AlignDiff, a …
View article: EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Prior
EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Prior Open
While image diffusion models have made significant progress in text-driven 3D content creation, they often fail to accurately capture the intended meaning of text prompts, especially for view information. This limitation leads to the Janus…