papers

Publications (16)

cs.LG2025

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…

cs.LG2022

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…

cs.AI2020

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…

cs.LG2025

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…

cs.CL2025

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…

cs.LG2024

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…

cs.LG2026

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…

cs.AI2019

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…

cs.CV2022

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…

cs.LG2020

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…

cs.CL2024

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…

cs.LG2026

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…

cs.IR2020

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…

cs.CL2025

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…

cs.CL2025

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…

cs.LG2021

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 (…