Yujin Tang

EDBT 2026 Demo / reviewers in the wild / expert

dblp:190/1177 · DBLP profile ↗

← Back

23ranked-venue papers

5as first author

17since 2021 · last 2026

—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 19 · 3 first-author · 17 since 2021Graphics, computer vision, multimedia, augmented reality and games · 3 · 2 since 2021Systems, architecture and hardware · 2 · 1 first-author · 1 since 2021Human-computer interaction and ubiquitous computing · 2 · 1 first-authorDatabases, data management, data science and information retrieval · 1 · 1 first-authorApplied, interdisciplinary, general and emerging computing · 1

Year	Publication	Venue	Position
2026	Digital Red Queen: Adversarial Program Evolution in Core War with LLMs abstract Large language models (LLMs) are increasingly used to evolve solutions to problems. However, most LLM-evolution frameworks solve static optimization problems, overlooking the open-ended adversarial dynamics that characterize real-world evolutionary processes. Here, we study Digital Red Queen (DRQ), a simple self-play algorithm that embraces these "Red Queen" dynamics via a changing objective. DRQ uses an LLM to evolve assembly programs (warriors) which compete for control of a virtual machine in the game of Core War, a Turing-complete environment studied in artificial life and connected to cybersecurity. In each round of DRQ, the model evolves a new warrior to defeat all previous ones. Over many rounds, warriors become increasingly general (relative to a set of held-out human warriors). Interestingly, across independent runs, we observe a convergence pressure toward a single generalpurpose behavioral strategy, much like convergent evolution in nature. Our work positions Core War as a rich, controllable sandbox for studying adversarial adaptation in artificial systems and for evaluating LLM-based evolution methods. More broadly, the simplicity and effectiveness of DRQ suggest that similarly minimal self-play approaches could prove useful in practical multi-agent adversarial domains, like real-world cybersecurity or combating drug resistance. Akarsh Kumar, Ryan Bahlous-Boldi, Prafull Sharma, Phillip Isola, Sebastian Risi, Yujin Tang, David Ha	GECCO	6
2025	Mamba-Adaptor: State Space Model Adaptor for Visual Recognition abstract Recent State Space Models (SSM), especially Mamba, have demonstrated impressive performance in visual modeling and possess superior model efficiency. However, the application of Mamba to visual tasks suffers inferior performance due to three main constraints existing in the sequential model: 1) Casual computing is incapable of accessing global context; 2) Long-range forgetting when computing the current hidden states; 3) Weak spatial structural modeling due to the transformed sequential input. To address these issues, we investigate a simple yet powerful vision task adapter for Mamba models, which consists of two functional modules: Adaptor-T and Adapator-S. When solving the hidden states for SSM, we apply a lightweight prediction module Adaptor-T to select a set of learnable locations as memory augmentations to ease long-range forgetting issues. Moreover, we leverage Adapator-S, composed of multi-scale dilated convolutional kernels, to enhance the spatial modeling and introduce the image inductive bias into the feature output. Both modules can enlarge the context modeling in casual computing, as the output is enhanced by the inaccessible features. We explore three usages of Mamba-Adaptor: A general visual backbone for various vision tasks; A booster module to raise the performance of pretrained backbones; A highly efficient fine-tuning module that adapts the base model for transfer learning tasks. Extensive experiments verify the effectiveness of Mamba-Adapter in three settings. Notably, our Mamba-Adapter achieves state-of-the-art performance on the ImageNet and COCO benchmarks. Jiahao Nie 0001, Yujin Tang, Hongshen Zhao	CVPR	3
2025	Competition and Attraction Improve Model Fusion abstract Model merging is a powerful technique for integrating the specialized knowledge of multiple machine learning models into a single model. However, existing methods require manually partitioning model parameters into fixed groups for merging, which restricts the exploration of potential combinations and limits performance. To overcome these limitations, we propose Model Merging of Natural Niches (M2N2), an evolutionary algorithm with three key features: (1) dynamic adjustment of merging boundaries to progressively explore a broader range of parameter combinations; (2) a diversity preservation mechanism inspired by the competition for resources in nature, to maintain a population of diverse, high-performing models that are particularly well-suited for merging; and (3) a heuristic-based attraction metric to identify the most promising pairs of models for fusion. Our experimental results demonstrate, for the first time, that model merging can be used to evolve models entirely from scratch. Specifically, we apply M2N2 to evolve MNIST classifiers from scratch and achieve performance comparable to CMA-ES, while being computationally more efficient. Furthermore, M2N2 scales to merge specialized language and image generation models, achieving state-of-the-art performance. Notably, it preserves crucial model capabilities beyond those explicitly optimized by the fitness function, highlighting its robustness and versatility. Our code is available at https://github.com/AnonScientist/natural_niches. João Abrantes, Robert T. Lange, Yujin Tang	GECCO	3
2025	An Evolved Universal Transformer Memory abstract Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with Neural Attention Memory Models (NAMMs), introducing a learned network for memory management that improves both the performance and efficiency of transformers. We evolve NAMMs atop pre-trained transformers to provide different latent contexts focusing on the most relevant information for individual layers and attention heads. NAMMs are universally applicable to any model using self-attention as they condition exclusively on the values in the produced attention matrices. Learning NAMMs on a small set of problems, we achieve substantial performance improvements across multiple long-context benchmarks while cutting the model's input contexts up to a fraction of the original sizes. We show the generality of our conditioning enables zero-shot transfer of NAMMs trained only on language to entirely new transformer architectures even across input modalities, with their benefits carrying over to vision and reinforcement learning. Edoardo Cetin, Tianyu Zhao 0001, Yujin Tang	ICLR	4
2025	Agent Skill Acquisition for Large Language Models via CycleQD abstract Training large language models to acquire specific skills remains a challenging endeavor. Conventional training approaches often struggle with data distribution imbalances and inadequacies in objective functions that do not align well with task-specific performance. To address these challenges, we introduce CycleQD, a novel approach that leverages the Quality Diversity framework through a cyclic adaptation of the algorithm, along with a model merging based crossover and an SVD-based mutation. In CycleQD, each task’s performance metric is alternated as the quality measure while the others serve as the behavioral characteristics. This cyclic focus on individual tasks allows for concentrated effort on one task at a time, eliminating the need for data ratio tuning and simplifying the design of the objective function. Empirical results from AgentBench indicate that applying CycleQD to LLAMA3-8B-INSTRUCT based models not only enables them to surpass traditional fine-tuning methods in coding, operating systems, and database tasks, but also achieves performance on par with GPT-3.5-TURBO, which potentially contains much more parameters, across these domains. Crucially, this enhanced performance is achieved while retaining robust language capabilities, as evidenced by its performance on widely adopted language benchmark tasks. We highlight the key design choices in CycleQD, detailing how these contribute to its effectiveness. Furthermore, our method is general and can be applied to image segmentation models, highlighting its applicability across different domains. So Kuroki, Taishi Nakamura, Takuya Akiba, Yujin Tang	ICLR	4
2025	Transformer-Squared: Self-adaptive LLMs abstract Self-adaptive large language models (LLMs) aim to solve the challenges posed by traditional fine-tuning methods, which are often computationally intensive and static in their ability to handle diverse tasks. We introduce Transformer-Squared, a novel self-adaptation framework that adapts LLMs for unseen tasks in real-time by selectively adjusting only the singular components of their weight matrices. During inference, Transformer-Squared employs a two-pass mechanism: first, a dispatch system identifies the task properties, and then task-specific 'expert' vectors, trained using reinforcement learning, are dynamically mixed to obtain targeted behavior for the incoming prompt. Our method consistently outperforms ubiquitous approaches such as LoRA, with fewer parameters and greater efficiency. Furthermore, Transformer-Squared demonstrates versatility across different LLM architectures and modalities, including vision-language tasks. Transformer-Squared represents a significant leap forward, offering a scalable, efficient solution for enhancing the adaptability and task-specific performance of LLMs, paving the way for truly dynamic, self-organizing AI systems. Edoardo Cetin, Yujin Tang	ICLR	3
2025	Large Language Models to Diffusion Finetuning abstract We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve monotonically increasing accuracy, directly translating to improved performance across downstream tasks. Furthermore, our finetuned models can expertly answer questions on specific topics by integrating powerful guidance techniques, and autonomously determine the compute required for a given problem by leveraging adaptive ODE solvers. Our method is applicable to any foundation model pre-trained with cross-entropy and does not modify any of its original weights, fully preserving its strong single-step generation capabilities. We show our method can be more effective and is fully compatible with traditional finetuning and search approaches, introducing an orthogonal new direction to unify the strengths of the autoregressive and diffusion frameworks. Edoardo Cetin, Tianyu Zhao 0001, Yujin Tang	ICML	3
2025	Text-to-LoRA: Instant Transformer Adaption abstract While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyperparameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2L), a model capable of adapting large language models (LLMs) on the fly solely based on a natural language description of the target task. T2L is a hypernetwork trained to construct LoRAs in a single inexpensive forward pass. After training T2L on a suite of 9 pre-trained LoRA adapters (GSM8K, Arc, etc.), we show that the ad-hoc reconstructed LoRA instances match the performance of task-specific adapters across the corresponding test sets. Furthermore, T2L can compress hundreds of LoRA instances and zero-shot generalize to entirely unseen tasks. This approach provides a significant step towards democratizing the specialization of foundation models and enables language-based adaptation with minimal compute requirements. Our code is available at https://github.com/SakanaAI/text-to-lora Rujikorn Charakorn, Edoardo Cetin, Yujin Tang, Robert T. Lange	ICML	3
2025	Reinforcement Learning Teachers of Test Time Scaling abstract Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of reasoning LMs is to act as teachers for distilling new students and cold-starting future RL iterations rather than being deployed themselves. From these considerations, we introduce a new framework that avoids RL's exploration challenge by training a new class of Reinforcement-Learned Teachers (RLTs) focused on yielding the most effective downstream distillation. RLTs are prompted with both the question and solution to each problem, and tasked to simply "connect-the-dots" with detailed explanations tailored for their students. We train RLTs with dense rewards obtained by feeding each explanation to the student and testing its understanding of the problem's solution. In practice, the raw outputs of a 7B RLT provide higher final performance on competition and graduate-level tasks than existing distillation and cold-starting pipelines that collect and postprocess the reasoning traces of orders of magnitude larger LMs. Furthermore, RLTs maintain their effectiveness when training larger students and when applied zero-shot to out-of-distribution tasks, unlocking new levels of efficiency and re-usability for the RL reasoning framework. Edoardo Cetin, Tianyu Zhao 0001, Yujin Tang	NeurIPS	3
2024	LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views abstract Fine-tuning is becoming widely used for leveraging the power of pre-trained foundation models in new downstream tasks. While there are many successes of fine-tuning on various tasks, recent studies have observed challenges in the generalization of fine-tuned models to unseen distributions (i.e., out-of-distribution; OOD). To improve OOD generalization, some previous studies identify the limitations of fine-tuning data and regulate fine-tuning to preserve the general representation learned from pre-training data. However, potential limitations in the pre-training data and models are often ignored. In this paper, we contend that overly relying on the pre-trained representation may hinder fine-tuning from learning essential representations for downstream tasks and thus hurt its OOD generalization. It can be especially catastrophic when new tasks are from different (sub)domains compared to pre-training data. To address the issues in both pre-training and fine-tuning data, we propose a novel generalizable fine-tuning method LEVI (Layer-wise Ensemble of different VIews), where the pre-trained model is adaptively ensembled layer-wise with a small task-specific model, while preserving its efficiencies. By combining two complementing models, LEVI effectively suppresses problematic features in both the fine-tuning data and pre-trained model and preserves useful features for new tasks. Broad experiments with large language and vision models show that LEVI greatly improves fine-tuning generalization via emphasizing different views from fine-tuning data and pre-trained features. Yuji Roh, Qingyun Liu 0003, Huan Gui, Yujin Tang, Steven Euijong Whang, Liang Liu 0017, Shuchao Bi, Lichan Hong, Ed H. Chi, Zhe Zhao 0001	ICML	5
2024	Position: Leverage Foundational Models for Black-Box Optimization abstract Undeniably, Large Language Models (LLMs) have stirred an extraordinary wave of innovation in the machine learning research domain, resulting in substantial impact across diverse fields such as reinforcement learning, robotics, and computer vision. Their incorporation has been rapid and transformative, marking a significant paradigm shift in the field of machine learning research. However, the field of experimental design, grounded on black-box optimization, has been much less affected by such a paradigm shift, even though integrating LLMs with optimization presents a unique landscape ripe for exploration. In this position paper, we frame the field of black-box optimization around sequence-based foundation models and organize their relationship with previous literature. We discuss the most promising ways foundational language models can revolutionize optimization, which include harnessing the vast wealth of information encapsulated in free-form text to enrich task comprehension, utilizing highly flexible sequence models such as Transformers to engineer superior optimization strategies, and enhancing performance prediction over previously unseen search spaces. Xingyou Song, Yingtao Tian, Robert T. Lange, Chansoo Lee, Yujin Tang, Yutian Chen 0001	ICML	5
2024	Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin	ICRA	267
2024	Learning to Generalize With Object-Centric Agents in the Open World Survival Game Crafter abstract Reinforcement learning agents must generalize beyond their training experience. Prior work has focused mostly on identical training and evaluation environments. Starting from the recently introducedCrafterbenchmark, a 2-D open world survival game, we introduce a new set of environments suitable for evaluating some agent's ability to generalize on previously unseen (numbers of) objects and to adapt quickly (meta-learning). InCrafter, the agents are evaluated by the number of unlocked achievements (such as collecting resources) when trained for 1 M steps. We show that current agents struggle to generalize, and introduce novel object-centric agents that improve over strong baselines. We also provide critical insights of general interest for future work onCrafterthrough several experiments. We show that careful hyperparameter tuning improves the PPO baseline agent by a large margin and that even feedforward agents can unlock almost all achievements by relying on the inventory display. We achieve a new state-of-the-art performance on the originalCrafterenvironment. In addtion, when trained beyond 1 M steps, our tuned agents can unlock almost all achievements. We show that the recurrent PPO agents improve over feedforward ones, even with the inventory information removed. We introduceCrafterOOD, a set of 15 new environments that evaluate OOD generalization. OnCrafterOOD, we show that the current agents fail to generalize, whereas our novel object-centric agents achieve state-of-the-art OOD generalization while also being interpretable. Our code is public. Aleksandar Stanic, Yujin Tang, David Ha, Jürgen Schmidhuber	IEEE Trans. Games	2
2023	DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards abstract Exploration is a fundamental aspect of reinforcement learning (RL), and its effectiveness is a deciding factor in the performance of RL algorithms, especially when facing sparse extrinsic rewards. Recent studies have shown the effectiveness of encouraging exploration with intrinsic rewards estimated from novelties in observations. However, there is a gap between the novelty of an observation and an exploration, as both the stochasticity in the environment and the agent's behavior may affect the observation. To evaluate exploratory behaviors accurately, we propose DEIR, a novel method in which we theoretically derive an intrinsic reward with a conditional mutual information term that principally scales with the novelty contributed by agent explorations, and then implement the reward with a discriminative forward model. Extensive experiments on both standard and advanced exploration tasks in MiniGrid show that DEIR quickly learns a better policy than the baselines. Our evaluations on ProcGen demonstrate both the generalization capability and the general applicability of our intrinsic reward. Shanchuan Wan, Yujin Tang, Yingtao Tian, Tomoyuki Kaneko	IJCAI	2
2023	NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications abstract Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e.g. meta-learning through long inner loop unrolls or optimizing non-differentiable operators. One core reason for this trend has been the recent innovation in hardware acceleration and compatible software -- making distributed population evaluations much easier than before. Unlike for gradient descent-based methods though, there is a lack of hyperparameter understanding and best practices for EO – arguably due to severely less `graduate student descent' and benchmarking being performed for EO methods. Additionally, classical benchmarks from the evolutionary community provide few practical insights for Deep Learning applications. This poses challenges for newcomers to hardware-accelerated EO and hinders significant adoption. Hence, we establish a new benchmark of EO methods (NEB) tailored toward Deep Learning applications and exhaustively evaluate traditional and meta-learned EO. We investigate core scientific questions including resource allocation, fitness shaping, normalization, regularization & scalability of EO. The benchmark is open-sourced at https://github.com/neuroevobench/neuroevobench under Apache-2.0 license. Robert T. Lange, Yujin Tang, Yingtao Tian	NeurIPS	2
2022	Evolving modular soft robots without explicit inter-module communication using local self-attention abstract Modularity in robotics holds great potential. In principle, modular robots can be disassembled and reassembled in different robots, and possibly perform new tasks. Nevertheless, actually exploiting modularity is yet an unsolved problem: controllers usually rely on inter-module communication, a practical requirement that makes modules not perfectly interchangeable and thus limits their flexibility. Here, we focus on Voxel-based Soft Robots (VSRs), aggregations of mechanically identical elastic blocks. We use the same neural controller inside each voxel, but without any inter-voxel communication, hence enabling ideal conditions for modularity: modules are all equal and interchangeable. We optimize the parameters of the neural controller---shared among the voxels---by evolutionary computation. Crucially, we use a local self-attention mechanism inside the controller to overcome the absence of inter-module communication channels, thus enabling our robots to truly be driven by the collective intelligence of their modules. We show experimentally that the evolved robots are effective in the task of locomotion: thanks to self-attention, instances of the same controller embodied in the same robot can focus on different inputs. We also find that the evolved controllers generalize to unseen morphologies, after a short fine-tuning, suggesting that an inductive bias related to the task arises from true modularity.1 Federico Pigozzi, Yujin Tang, Eric Medvet, David Ha	GECCO	2
2021	The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning abstract In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the full picture. Such systems have inspired development of artificial intelligence algorithms in areas such as swarm optimization and cellular automata. Motivated by the emergence of collective behavior from complex cellular systems, we build systems that feed each sensory input from the environment into distinct, but identical neural networks, each with no fixed relationship with one another. We show that these sensory networks can be trained to integrate information received locally, and through communication via an attention mechanism, can collectively produce a globally coherent policy. Moreover, the system can still perform its task even if the ordering of its inputs is randomly permuted several times during an episode. These permutation invariant systems also display useful robustness and generalization properties that are broadly applicable. Interactive demo and videos of our results: https://attentionneuron.github.io Yujin Tang, David Ha	NeurIPS	1
2020	Neuroevolution of self-interpretable agents abstract Inattentional blindness is the psychological phenomenon that causes one to miss things in plain sight. It is a consequence of the selective attention in perception that lets us remain focused on important parts of our world without distraction from irrelevant details. Motivated by selective attention, we study the properties of artificial agents that perceive the world through the lens of a self-attention bottleneck. By constraining access to only a small fraction of the visual input, we show that their policies are directly interpretable in pixel space. We find neuroevolution ideal for training self-attention architectures for vision-based reinforcement learning (RL) tasks, allowing us to incorporate modules that can include discrete, non-differentiable operations which are useful for our agent. We argue that self-attention has similar properties as indirect encoding, in the sense that large implicit weight matrices are generated from a small number of key-query parameters, thus enabling our agent to solve challenging vision based tasks with at least 1000x fewer parameters than existing methods. Since our agent attends to only task critical visual hints, they are able to generalize to environments where task irrelevant elements are modified while conventional methods fail.1 Yujin Tang, David Ha	GECCO	1
2020	Learning Agile Locomotion via Adversarial Training abstract Developing controllers for agile locomotion is a long-standing challenge for legged robots. Reinforcement learning (RL) and Evolution Strategy (ES) hold the promise of automating the design process of such controllers. However, dedicated and careful human effort is required to design training environments to promote agility. In this paper, we present a multi-agent learning system, in which a quadruped robot (protagonist) learns to chase another robot (adversary) while the latter learns to escape. We find that this adversarial training process not only encourages agile behaviors but also effectively alleviates the laborious environment design effort. In contrast to prior works that used only one adversary, we find that training an ensemble of adversaries, each of which specializes in a different escaping strategy, is essential for the protagonist to master agility. Through extensive experiments, we show that the locomotion controller learned with adversarial training significantly outperforms carefully designed baselines. Yujin Tang, Jie Tan 0001, Tatsuya Harada	IROS	1
2020	Ovarian Cancer Prediction in Proteomic Data Using Stacked Asymmetric Convolution Cheng Yuan 0002, Yujin Tang, Dahong Qian	MICCAI (2)	2
2018	Binary Classification of Sequences Possessing Unilateral Common Factor with AMS and APR Yujin Tang, Kei Yonekawa, Mori Kurokawa, Shinya Wada, Kiyohito Yoshihara	PAKDD (3)	1
2017	Effects of objective feedback of facial expression recognition during video support chat abstract This paper examines the effects of objective feedback of facial expression recognition on the operators of a video support chat system. We have built a facial expression feedback (FEF) system, which recognizes the users' facial expressions, and displays a visual summary of the recognition results to the user, in order to raise self-awareness of his/her expressions during video communication. We evaluated our system in a supposed simulation of a call center, in which operators provide assistance to customers about how to use their smartphones. Experimental results have verified that our approach is useful to help operators improve their self-awareness of facial expression in the video support chat. Toshiyuki Hagiya, Yujin Tang, Keiichiro Hoashi	MUM	3
2016	Detecting Activities of Daily Living from Low Frequency Power Consumption Data abstract With the popularization of smart sensors, detecting activities of daily living (ADL) from sensor readings has attracted many interests in both the academic and the industrial societies. A majority of research works on this topic focus on data of high sampling rate, however, most existing smart sensor deployments support sampling rate much lower than 1 Hz. We are interested in the possibility of inferring ADLs from solely coarse home-level gross power consumptions. In this paper, we first tentatively adopt a layered hidden Markov model (LHMM) in the hope to uncover the association between ADLs and power consumption data. We conduct an exploratory data analysis with this preliminary model on a real-world dataset, and based on the findings from this exploratory study, we propose to infer ADLs from low frequency power consumption data using a hierarchical Dirichlet process hidden markov model (HDP-HMM). We perform experiments on the same dataset, and demonstrate that with sensor readings of 1/180 Hz and 1/900 Hz granularities, HDP-HMM outperforms comparative models and ADLs such as "Entertaining" and "Not at home" can be captured with high accuracy. Yujin Tang, Chihiro Ono	MobiQuitous	1