AIConfPaper
← Search

Deheng Ye

36 accepted papers

2026

ALIGNING GENERATIVE SPEECH ENHANCEMENT WITH PERCEPTUAL FEEDBACK

Haoyang Li, Nana Hou, Yuchen Hu, Jixun Yao, Sabato Marco Siniscalchi, Norwegian University of Science and Technology +4
ICASSP 2026oral

Language Model (LM)-based speech enhancement (SE) has recently emerged as a promising direction, but existing approaches predominantly rely on token-level likelihood objectives that weakly reflect human perception. This mismatch limits progress, as optimizing signal accuracy does not always improve…

Cited by 0Source ↗PDF ↗Scholar ↗
2026

AdaptVision: Efficient Vision-Language Models via Adaptive Visual Acquisition

Zichuan Lin, Yicheng Liu, Yang Yang, Lvfang Tao, Deheng Ye
CVPR 2026

Vision-Language Models (VLMs) have achieved remarkable success in visual question answering tasks, but their reliance on large numbers of visual tokens introduces significant computational overhead. While existing efficient VLM approaches reduce visual tokens through fixed-ratio compression, they op

Cited by 0Source ↗code ↗Scholar ↗
2026

Debiased Model-based Representations for Sample-efficient Continuous Control

Jiafei Lyu, Zichuan Lin, Scott Fujimoto, Kai Yang, Yangkun Chen, Saiyong Yang +2
ICML 2026poster

Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic learning. It implicitly combines the advantages of both model-free and model-based approaches while avoiding the training co…

Cited by 0Source ↗Scholar ↗
2026

GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training

Tong Wei, Yijun Yang, Changhao Zhang, Junliang Xing, Yuanchun Shi, Zongqing Lu +1
CVPR 2026

Multi-turn reinforcement learning (RL) for multi-modal agents built upon vision-language models (VLMs) is hampered by sparse rewards and long-horizon credit assignment. Recent methods densify the reward by querying a teacher that provides step-level feedback, e.g., Guided Thought Reinforcement (GTR)

Cited by 0Source ↗Scholar ↗
2026

Multi-agent In-context Coordination via Decentralized Memory Retrieval

Tao Jiang, Zichuan Lin, Lihe Li, Yi-Chen Li, Cong Guan, Lei Yuan +3
AAAI 2026technical

Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve conte

Cited by 0Source ↗PDF ↗Scholar ↗
2026

Multi-objective Large Language Model Alignment with Hierarchical Experts

Zhuo Li, Guodong DU, Weiyang Guo, Yigeng Zhou, Xiucheng Li, Wenya Wang +5
ICLR 2026poster

Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of human preferences. Existing alignment methods struggle to balance trade-offs effectively, often requiring costly retrainin…

Cited by 0Source ↗Scholar ↗
2026

Powerful and Theoretically Guaranteed Independence Testing on Heterogeneous Federated Clients

YiXin Ren, Hongquan Liu, Juncai Zhang, Yewei Xia, Zichuan Lin, Deheng Ye +3
ICML 2026poster

In this paper, we present a novel federated independence testing method that addresses both theoretical and practical challenges arising from client heterogeneity. We begin by revisiting existing federated independence testing methods and showing why they fail to provide valid guarantees or maintain…

Cited by 0Source ↗Scholar ↗
2026

Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning

Ziyi Zhang, Li Shen, Deheng Ye, Yong Luo, Huangxuan Zhao, Meng Liu +2
CVPR 2026

Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality, such as per-view fidelity and cross-view consisten

Cited by 0Source ↗code ↗Scholar ↗
2026

Streaming Covariate Balancing via Discrepancy-Based Feature Coresets

YiXin Ren, Chenghou Jin, Yewei Xia, Zichuan Lin, Deheng Ye, Hao Zhang +2
ICML 2026poster

Real-time estimation of average treatment effects (ATE) in streaming observational data poses two key challenges: strict memory constraints that preclude storing the full data history, and distributional shifts in both treatment assignment and outcome-generating process. Existing methods either requ…

Cited by 0Source ↗Scholar ↗
2025

Ad Hoc Teamwork via Offline Goal-Based Decision Transformers

Xinzhi Zhang, Hohei Chan, Deheng Ye, Yi Cai, Mengchen Zhao
ICML 2025poster

The ability of agents to collaborate with previously unknown teammates on the fly, known as ad hoc teamwork (AHT), is crucial in many real-world applications. Existing approaches to AHT require online interactions with the environment and some carefully designed teammates. However, these prerequisit…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data

Xin-Cheng Wen, Yijun Yang, Cuiyun Gao, Yang Xiao, Deheng Ye
ACL 2025finding

Large language models (LLMs) demonstrate considerable proficiency in numerous coding-related tasks; however, their capabilities in detecting software vulnerabilities remain limited. This limitation primarily stems from two factors: (1) the absence of reasoning data related to vulnerabilities, which…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks

Qi Chai, Zhang Zheng, Junlong Ren, Deheng Ye, Zichuan Lin, Hao Wang
EMNLP 2025

Minecraft, as an open-world virtual interactive environment, has become a prominent platform for research on agent decision-making and execution. Existing works primarily adopt a single Large Language Model (LLM) agent to complete various in-game tasks. However, for complex tasks requiring lengthy s

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Cross-Domain Offline Policy Adaptation with Optimal Transport and Dataset Constraint

Jiafei Lyu, Mengbei Yan, Zhongjian Qiao, Runze Liu, Xiaoteng Ma, Deheng Ye +3
ICLR 2025poster

We explore cross-domain offline reinforcement learning (RL) where offline datasets from another domain can be accessed to facilitate policy learning. However, the underlying environments of the two datasets may have dynamics mismatches, incurring inferior performance when simply merging the data of…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

Decision Mixer: Integrating Long-term and Local Dependencies via Dynamic Token Selection for Decision-Making

Hongling Zheng, Li Shen, Yong Luo, Deheng Ye, Bo Du, Jialie Shen +1
ICML 2025poster

The Conditional Sequence Modeling (CSM) paradigm, benefiting from the transformer's powerful distribution modeling capabilities, has demonstrated considerable promise in offline Reinforcement Learning (RL) tasks. Depending on the task's nature, it is crucial to carefully balance the interplay betwee…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training

Tong Wei, Yijun Yang, Junliang Xing, Yuanchun Shi, Zongqing Lu, Deheng Ye
ICCV 2025poster

Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs). Yet, its efficacy in training vision-language model (VLM) agents for goal-directed action reasoning in visual environments is less established. Th…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and Data

Hao Luo, Zihao Yue, Wanpeng Zhang, Yicheng Feng, Sipeng Zheng, Deheng Ye +1
NeurIPS 2025poster

Recent advances in large multimodal models have significantly advanced video comprehension, yet their performance remains limited in first-person scenarios. The interactive nature of egocentric videos is critical for applications like embodied intelligence, but introduces complex visual contexts tha…

Cited by 0Source ↗code ↗Scholar ↗
2025

Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption

Longxiang He, Deheng Ye, Junbo Tan, Xueqian Wang, Li Shen
NeurIPS 2025poster

Pretraining a policy on offline data followed by fine-tuning through online interactions, known as Offline-to-Online Reinforcement Learning (O2O RL), has emerged as a promising paradigm for real-world RL deployment. However, both offline datasets and online interactions in practical environments are…

Cited by 0Source ↗code ↗Scholar ↗
2025

Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings

Hongling Zheng, Li Shen, Yong Luo, Deheng Ye, Shuhan Xu, Bo Du +2
NeurIPS 2025poster

The Conditional Sequence Modeling (CSM) paradigm, benefiting from the transformer's powerful distribution modeling capabilities, has demonstrated considerable promise in Reinforcement Learning (RL) tasks. However, much of the work has focused on applying CSM to single online or offline settings, wit…

Cited by 0Source ↗Scholar ↗
2025

VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft

Honghao Fu, Junlong Ren, Qi Chai, Deheng Ye, Yujun Cai, Hao Wang
EMNLP 2025

Large language models (LLMs) have shown significant promise in embodied decision-making tasks within virtual open-world environments. Nonetheless, their performance is hindered by the absence of domain-specific knowledge. Methods that finetune on large-scale domain-specific data entail prohibitive d

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Siyu Zhou, Tianyi Zhou, Yijun Yang, Guodong Long, Deheng Ye, Jing Jiang +1
NeurIPS 2025poster

Can we build accurate world models out of large language models (LLMs)? How can world models benefit LLM agents? The gap between the prior knowledge of LLMs and the specified environment's dynamics usually bottlenecks LLMs' performance as world models. To bridge the gap, we propose a training-free "…

Cited by 0Source ↗Scholar ↗
2024

LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay

Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao +3
EMNLP 2024main

This paper explores the open research problem of understanding the social behaviors of LLM-based agents. Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. While previous studies have touched on gameplay with LLM agents, research on their social behaviors is lacking…

Cited by 38Source ↗PDF ↗code ↗Scholar ↗
2024

Language Model Adaption for Reinforcement Learning with Natural Language Action Space

Jiangxing Wang, Jiachen Li, Xiao Han, Deheng Ye, Zongqing Lu
ACL 2024long

Reinforcement learning with natural language action space often suffers from the curse of dimensionality due to the combinatorial nature of the natural language. Previous research leverages pretrained language models to capture action semantics and reduce the size of the action space. However, since…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

Learning Versatile Skills with Curriculum Masking

Yao Tang, Zhihui Xie, Zichuan Lin, Deheng Ye, Shuai Li
NeurIPS 2024poster

Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to bal…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

Future-conditioned Unsupervised Pretraining for Decision Transformer

Zhihui Xie, Zichuan Lin, Deheng Ye, QIANG FU, Yang Wei, Shuai Li
ICML 2023poster

Recent research in offline reinforcement learning (RL) has demonstrated that return-conditioned supervised learning is a powerful paradigm for decision-making problems. While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning fr…

Cited by 26Source ↗PDF ↗code ↗Scholar ↗
2023

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

Yun Qu, Boyuan Wang, Jianzhun Shao, Yuhang Jiang, Chen Chen, Zhenbin Ye +12
NeurIPS 2023poster

The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications. However, existing datasets often fall…

Cited by 9Source ↗PDF ↗code ↗Scholar ↗
2023

More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization

Jiangxing Wang, Deheng Ye, Zongqing Lu
ICLR 2023poster

In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for the partially observable environment. Given the goal of learning local policies that enable decentralized execution, agen…

Cited by 22Source ↗PDF ↗code ↗Scholar ↗
2023

RLogist: Fast Observation Strategy on Whole-Slide Images with Deep Reinforcement Learning

Boxuan Zhao, Jun Zhang, Deheng Ye, Jian Cao, Xiao Han, Qiang Fu +1
AAAI 2023technical

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learnin…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learning

Hua Wei, Jingxiao Chen, Xiyang Ji, Hongyang Qin, Minwen Deng, Siqin Li +8
NeurIPS 2022accept

This paper introduces Honor of Kings Arena, a reinforcement learning (RL) environment based on the Honor of Kings, one of the world’s most popular games at present. Compared to other environments studied in most previous work, ours presents new generalization challenges for competitive reinforcement…

Cited by 32Source ↗PDF ↗code ↗Scholar ↗
2022

JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning

Zichuan Lin, Junyou Li, Jianing Shi, Deheng Ye, Qiang Fu, Wei Yang
IJCAI 2022poster

Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hi…

Cited by 44Source ↗PDF ↗Scholar ↗
2021

Boosting Offline Reinforcement Learning with Residual Generative Modeling

Hua Wei, Deheng Ye, Zhao Liu, Hao Wu, Bo Yuan, Qiang Fu +2
IJCAI 2021poster

Offline reinforcement learning (RL) tries to learn the near-optimal policy with recorded offline experience without online exploration.Current offline RL research includes: 1) generative modeling, i.e., approximating a policy using fixed data; and 2) learning the state-action value function. While m…

Cited by 15Source ↗PDF ↗Scholar ↗
2021

Coordinated Proximal Policy Optimization

Zifan Wu, Chao Yu, Deheng Ye, Junge Zhang, haiyin piao, Hankz Hankui Zhuo
NeurIPS 2021poster

We present Coordinated Proximal Policy Optimization (CoPPO), an algorithm that extends the original Proximal Policy Optimization (PPO) to the multi-agent setting. The key idea lies in the coordinated adaptation of step size during the policy update process among multiple agents. We prove the monoton…

Cited by 65Source ↗PDF ↗code ↗Scholar ↗
2021

Learning Diverse Policies in MOBA Games via Macro-Goals

Yiming Gao, Bei Shi, Xueying Du, Liang Wang, Guangwei Chen, Zhenjie Lian +7
NeurIPS 2021poster

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings. Even though these AI systems have achieved or even exceeded human-level performance, they still suffer from the lack of po…

Cited by 12Source ↗PDF ↗Scholar ↗
2021

MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks

Menghui Zhu, Minghuan Liu, Jian Shen, Zhicheng Zhang, Sheng Chen, Weinan Zhang +4
IJCAI 2021poster

In Goal-oriented Reinforcement learning, relabeling the raw goals in past experience to provide agents with hindsight ability is a major solution to the reward sparsity problem. In this paper, to enhance the diversity of relabeled goals, we develop FGI (Foresight Goal Inference), a new relabeling st…

Cited by 30Source ↗PDF ↗code ↗Scholar ↗
2020

Relation-Aware Transformer for Portfolio Policy Learning

Ke Xu, Yifan Zhang, Deheng Ye, Peilin Zhao, Mingkui Tan
IJCAI 2020poster

Portfolio selection is an important yet challenging task in AI for FinTech. One of the key issues is how to represent the non-stationary price series of assets in a portfolio, which is important for portfolio decisions. The existing methods, however, fall short of capturing: 1) the complicated seq…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2020

Towards Playing Full MOBA Games with Deep Reinforcement Learning

Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu +12
NeurIPS 2020poster

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handli…

Cited by 235Source ↗PDF ↗code ↗Scholar ↗