Qihang Chen

Dayang Liang, Qihang Chen, Yunlong Liu

How to accurately learn task-relevant state representations from high-dimensional observations with visual distractions is a realistic and challenging problem in visual reinforcement learning. Recently, unsupervised representation learning methods based on bisimulation metrics, contrast, prediction, and reconstruction have shown the ability for task-relevant information extraction. However, due to the lack of appropriate mechanisms for the extraction of task information in the prediction, contrast, and reconstruction-related approaches and the limitations of bisimulation-related methods in domains with sparse rewards, it is still difficult for these methods to be effectively extended to environments with distractions. To alleviate these problems, in the paper, the action sequences, which contain task-intensive signals, are incorporated into representation learning. Specifically, we propose a Sequential Action--induced invariant Representation (SAR) method, in which the encoder is optimized by an auxiliary learner to only preserve the components that follow the control signals of sequential actions, so the agent can be induced to learn the robust representation against distractions. We conduct extensive experiments on the DeepMind Control suite tasks with distractions while achieving the best performance over strong baselines. We also demonstrate the effectiveness of our method at disregarding task-irrelevant information by deploying SAR to real-world CARLA-based autonomous driving with natural distractions. Finally, we provide the analysis results of generalization drawn from the generalization decay and t-SNE visualization. Code and demo videos are available at https://github.com/DMU-XMU/SAR.git.

Yongzhu Chang, Rongsheng Zhang, Lin Jiang et al.

Lyrics generation is a well-known application in natural language generation research, with several previous studies focusing on generating accurate lyrics using precise control such as keywords, rhymes, etc. However, lyrics imitation, which involves writing new lyrics by imitating the style and content of the source lyrics, remains a challenging task due to the lack of a parallel corpus. In this paper, we introduce \textbf{\textit{Sudowoodo}}, a Chinese lyrics imitation system that can generate new lyrics based on the text of source lyrics. To address the issue of lacking a parallel training corpus for lyrics imitation, we propose a novel framework to construct a parallel corpus based on a keyword-based lyrics model from source lyrics. Then the pairs \textit{(new lyrics, source lyrics)} are used to train the lyrics imitation model. During the inference process, we utilize a post-processing module to filter and rank the generated lyrics, selecting the highest-quality ones. We incorporated audio information and aligned the lyrics with the audio to form the songs as a bonus. The human evaluation results show that our framework can perform better lyric imitation. Meanwhile, the \textit{Sudowoodo} system and demo video of the system is available at \href{https://Sudowoodo.apps-hp.danlu.netease.com/}{Sudowoodo} and \href{https://youtu.be/u5BBT_j1L5M}{https://youtu.be/u5BBT\_j1L5M}.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

Qihang Chen

Metro crew planning is a key component of smart city development as it directly impacts the operational efficiency and service reliability of public transportation. With the rapid expansion of metro networks, effective multi-line scheduling and emergency management have become essential for large-scale seamless operations. However, current research focuses primarily on individual metro lines,with insufficient attention on cross-line coordination and rapid replanning during disruptions. Here, a unified optimization framework is presented for multi-line metro crew planning and replanning with heterogeneous workforce. Specifically, a hierarchical time-space network model is proposed to represent the unified crew action space, and computationally efficient constraints and formulations are derived for the crew's heterogeneous qualifications and preferences. Solution algorithms based on column generation and shortest path adjustment are further developed, utilizing the proposed network model. Experiments with real data from Shanghai and Beijing Metro demonstrate that the proposed methods outperform benchmark heuristics in both cost reduction and task completion,and achieve notable efficiency gains by incorporating cross-line operations, particularly for urgent tasks during disruptions. This work highlights the role of global optimization and cross-line coordination in multi-line metro system operations, providing insights into the efficient and reliable functioning of public transportation in smart cities.

Junjie H. Xu, Zhou Fang, Qihang Chen et al.

This paper presents a commentator for providing real-time game commentary in a fighting game. The commentary takes into account highlight cues, obtained by analyzing scenes during gameplay, as input to adjust the pitch and loudness of commentary to be spoken by using a Text-to-Speech (TTS) technology. We investigate different designs for pitch and loudness adjustment. The proposed AI consists of two parts: a dynamic adjuster for controlling pitch and loudness of the TTS and a real-time game commentary generator. We conduct a pilot study on a fighting game, and our result shows that by adjusting the loudness significantly according to the level of game highlight, the entertainment of the gameplay can be enhanced.