Publications (16)
Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modeling
Chen Zhang, Weixin Bu, Wendong Xu +3
Transformers have achieved remarkable success in time series modeling, yet their internal mechanisms remain opaque. This work demystifies the Transformer encoder by establishing it…
DO-GAN: A Double Oracle Framework for Generative Adversarial Networks
Aye Phyu Phyu Aung, Xinrun Wang, Runsheng Yu +3
In this paper, we propose a new approach to train Generative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discriminator oracles. GA…
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Rundong Wang, Xu He, Runsheng Yu +3
We consider the problem of the limited-bandwidth communication for multi-agent reinforcement learning, where agents cooperate with the assistance of a communication protocol and a…
Particle Dynamics for Latent-Variable Energy-Based Models
Shiqin Tang, Shuxin Zhuang, Rong Feng +3
Latent-variable energy-based models (LVEBMs) assign a single normalized energy to joint pairs of observed data and latent variables, offering expressive generative modeling while c…
Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice
Shanbo Cheng, Yu Bao, Zhichao Huang +25
Simultaneous Interpretation (SI) represents one of the most daunting frontiers in the translation industry, with product-level automatic systems long plagued by intractable challen…
Tailed Low-Rank Matrix Factorization for Similarity Matrix Completion
Changyi Ma, Runsheng Yu, Xiao Chen +1
Similarity matrix serves as a fundamental tool at the core of numerous downstream machine-learning tasks. However, missing data is inevitable and often results in an inaccurate sim…
How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs
Shuxin Zhuang, Zi Liang, Runsheng Yu +4
Recent vision-centric approaches have made significant strides in long-context modeling. Represented by DeepSeek-OCR, these models encode rendered text into continuous vision token…
Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning
Runsheng Yu, Zhenyu Shi, Xinrun Wang +5
Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized t…
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
Wenyu Liu, Gaofeng Ren, Runsheng Yu +3
Though deep learning-based object detection methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from the low-quality ima…
Learning to Collaborate in Multi-Module Recommendation via Multi-Agent Reinforcement Learning without Communication
Xu He, Bo An, Yanghua Li +6
With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items wi…
Direct Alignment of Language Models via Quality-Aware Self-Refinement
Runsheng Yu, Yong Wang, Xiaoqi Jiao +2
Reinforcement Learning from Human Feedback (RLHF) has been commonly used to align the behaviors of Large Language Models (LLMs) with human preferences. Recently, a popular alternat…
Model Evolution Under Zeroth-Order Optimization: A Neural Tangent Kernel Perspective
Chen Zhang, Yuxin Cheng, Chenchen Ding +5
Zeroth-order (ZO) optimization enables memory-efficient training of neural networks by estimating gradients via forward passes only, eliminating the need for backpropagation. Howev…
Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
Runsheng Yu, Yu Gong, Xu He +4
A common challenge in personalized user preference prediction is the cold-start problem. Due to the lack of user-item interactions, directly learning from the new users' log data c…
Seed-X: Building Strong Multilingual Translation LLM with 7B Parameters
Shanbo Cheng, Yu Bao, Qian Cao +23
Multilingual translation stands as a challenging task for large language models (LLMs) to handle intricate language patterns and stilted translations that arise in automated transl…
BEYOND DIALOGUE: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model
Yeyong Yu, Runsheng Yu, Haojie Wei +2
The rapid advancement of large language models (LLMs) has revolutionized role-playing, enabling the development of general role-playing models. However, current role-playing traini…
RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
Wei Qiu, Xinrun Wang, Runsheng Yu +5
Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (…