55 citations · 240 across the 40 of their papers we have counts for
42 papers
Uncertainty-Aware Budget Allocation for Efficient LLM Tree Search
Jianguo Huang, Zhiyi Lyu, Fuxiang Zhang +3
Tree search enhances multi-step reasoning in large language models (LLMs), yet prevailing methods expand every step with a fixed budget, irrespective of the marginal utility of exp…
Human-in-Context: Unified Cross-Domain 3D Human Motion Modeling via In-Context Learning
Mengyuan Liu, Xinshun Wang, Zhongbin Fang +6
This paper aims to model 3D human motion across domains, where a single model is expected to handle multiple modalities, tasks, and datasets. Existing cross-domain models often rel…
Yan: Foundational Interactive Video Generation
Deheng Ye, Fangyun Zhou, Jiacheng Lv +15
We present Yan, a foundational framework for interactive video generation, covering the entire pipeline from simulation and generation to editing. Specifically, Yan comprises three…
Aligning Generative Speech Enhancement with Perceptual Feedback
Haoyang Li, Nana Hou, Yuchen Hu +6
Language Model (LM)-based speech enhancement (SE) has recently emerged as a promising direction, but existing approaches predominantly rely on token-level likelihood objectives tha…
Multi-objective Large Language Model Alignment with Hierarchical Experts
Zhuo Li, Guodong Du, Weiyang Guo +8
Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of hu…
Playable Game Generation
Mingyu Yang, Junyou Li, Zhongbin Fang +5
In recent years, Artificial Intelligence Generated Content (AIGC) has advanced from text-to-image generation to text-to-video and multimodal video synthesis. However, generating pl…
Learning Versatile Skills with Curriculum Masking
Yao Tang, Zhihui Xie, Zichuan Lin +2
Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across va…
Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
Yun Qu, Boyuan Wang, Jianzhun Shao +15
The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected o…
A Survey on Self-play Methods in Reinforcement Learning
Ruize Zhang, Zelai Xu, Chengdong Ma +8
Self-play, a learning paradigm where agents iteratively refine their policies by interacting with historical or concurrent versions of themselves or other evolving agents, has show…
Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models
Fuxiang Zhang, Junyou Li, Yi-Chen Li +3
Low sample efficiency is an enduring challenge of reinforcement learning (RL). With the advent of versatile large language models (LLMs), recent works impart common-sense knowledge…
Reaching Consensus in Cooperative Multi-Agent Reinforcement Learning with Goal Imagination
Liangzhou Wang, Kaiwen Zhu, Fengming Zhu +6
Reaching consensus is key to multi-agent coordination. To accomplish a cooperative task, agents need to coherently select optimal joint actions to maximize the team reward. However…
More Agents Is All You Need
Junyou Li, Qin Zhang, Yangbin Yu +2
We find that, simply via a sampling-and-voting method, the performance of large language models (LLMs) scales with the number of agents instantiated. Also, this method, termed as A…
Affordable Generative Agents
Yangbin Yu, Qin Zhang, Junyou Li +2
The emergence of large language models (LLMs) has significantly advanced the simulation of believable interactive agents. However, the substantial cost on maintaining the prolonged…
Replay-enhanced Continual Reinforcement Learning
Tiantian Zhang, Kevin Zehua Shen, Zichuan Lin +4
Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are sti…
Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints
Hanchi Huang, Li Shen, Deheng Ye +1
We propose a novel master-slave architecture to solve the top- combinatorial multi-armed bandits problem with non-linear bandit feedback and diversity constraints, which, to the…
RLTF: Reinforcement Learning from Unit Test Feedback
Jiate Liu, Yiqin Zhu, Kaiwen Xiao +4
The goal of program synthesis, or code generation, is to generate executable code based on given descriptions. Recently, there has been an increasing number of studies employing re…
Future-conditioned Unsupervised Pretraining for Decision Transformer
Zhihui Xie, Zichuan Lin, Deheng Ye +3
Recent research in offline reinforcement learning (RL) has demonstrated that return-conditioned supervised learning is a powerful paradigm for decision-making problems. While promi…
Deploying Offline Reinforcement Learning with Human Feedback
Ziniu Li, Ke Xu, Liu Liu +3
Reinforcement learning (RL) has shown promise for decision-making tasks in real-world applications. One practical framework involves training parameterized policy models from an of…
Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning
Haoxuan Pan, Deheng Ye, Xiaoming Duan +4
We revisit the estimation bias in policy gradients for the discounted episodic Markov decision process (MDP) from Deep Reinforcement Learning (DRL) perspective. The objective is fo…
Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization
Zichuan Lin, Xiapeng Wu, Mingfei Sun +4
Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for s…
A Survey on Transformers in Reinforcement Learning
Wenzhe Li, Hao Luo, Zichuan Lin +3
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings. Recently, a similar surge of using Transformers has appeared in…
RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Boxuan Zhao, Jun Zhang, Deheng Ye +4
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 rele…
Pretraining in Deep Reinforcement Learning: A Survey
Zhihui Xie, Zichuan Lin, Junyou Li +2
The past few years have seen rapid progress in combining reinforcement learning (RL) with deep learning. Various breakthroughs ranging from games to robotics have spurred the inter…
Curriculum-based Asymmetric Multi-task Reinforcement Learning
Hanchi Huang, Deheng Ye, Li Shen +1
We introduce CAMRL, the first curriculum-based asymmetric multi-task learning (AMTL) algorithm for dealing with multiple reinforcement learning (RL) tasks altogether. To mitigate t…