Liyuan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liyuan Wang has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Jun Zhu
Tsinghua University, Beijing, China
6 shared publications - Hang Su
Tsinghua University
5 shared publications - Kanglei Zhou
Dept. of Psychological and Cognitive Sciences, Tsinghua University, Beijing, China
4 shared publications - Xiaohui Liang
Beihang University
4 shared publications - Xingxing Zhang
School of Computer Science, Tsinghua University, Beijing, China
4 shared publications - Yi Zhong
School of Life Sciences, IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing, China
4 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Springer Nature in Nature Communications
- Vol. 17  (1) , 10912
Cephalopod-inspired embodied camouflage system for simultaneous evasion of artificial and human visual perception
- 26 October 2026
- Published by Springer Nature in Nature Communications
- Vol. 17  (1) , 10912
Open AccessCephalopod-inspired embodied camouflage system for simultaneous evasion of artificial and human visual perception
- Open Access
- 28 July 2026
- Published by Springer Nature in Research Square
Steering topology distributions for unified generative design of architected metamaterials
Architected metamaterials derive their functions from structure, creating vast opportunities to program physical responses through topology design. However, existing design methods are often tailored to individual design problems, making limited use of topology knowledge for effective and broadly applicable design as objectives, constraints, and physical functions change. Here we introduce Generative Topology Optimization (GenTO), a unified framework that turns a learned topology prior into a reusable design engine. GenTO trains a diffusion model on a large full-order topology dataset and then iteratively steers the resulting topology distribution toward task-specific high-performing regions using user-defined physical objectives and constraints. This shifts the object of optimization from a single structure to a task-adapted topology distribution. Across topology design problems spanning thermal extremization, multi-objective morphology control, property-targeted auxetic design, and vibration transmission design, GenTO reuses pretrained topology priors for heterogeneous tasks, preserves structural diversity, and reaches high-performing solutions supported by numerical benchmarks and experimental validation. These results establish reusable topology knowledge as a unified principle for effective and scalable architected metamaterial design.
- 28 July 2026
- Published by Springer Nature in Research Square
Open AccessSteering topology distributions for unified generative design of architected metamaterials
Architected metamaterials derive their functions from structure, creating vast opportunities to program physical responses through topology design. However, existing design methods are often tailored to individual design problems, making limited use of topology knowledge for effective and broadly applicable design as objectives, constraints, and physical functions change. Here we introduce Generative Topology Optimization (GenTO), a unified framework that turns a learned topology prior into a reusable design engine. GenTO trains a diffusion model on a large full-order topology dataset and then iteratively steers the resulting topology distribution toward task-specific high-performing regions using user-defined physical objectives and constraints. This shifts the object of optimization from a single structure to a task-adapted topology distribution. Across topology design problems spanning thermal extremization, multi-objective morphology control, property-targeted auxetic design, and vibration transmission design, GenTO reuses pretrained topology priors for heterogeneous tasks, preserves structural diversity, and reaches high-performing solutions supported by numerical benchmarks and experimental validation. These results establish reusable topology knowledge as a unified principle for effective and scalable architected metamaterial design.
- Open Access
- 27 June 2026
- Published by Springer Nature in Nature Communications
- Vol. 17  (1)
Brain-inspired spatial intelligence for embodied agents
Spatial cognition enables adaptive goal-directed behavior through structured internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: landmarks for salient cues, route knowledge for movement trajectories, and survey knowledge for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse embodied navigation tasks (e.g., improving success weighted by path length from 17.6% to 44.9% in instance-level navigation and from 42.7% to 53.1% in zero-shot long-horizon instruction-following), while also supporting versatile embodied behaviors in the real physical world. These results highlight a scalable path toward general-purpose spatial intelligence.
- 27 June 2026
- Published by Springer Nature in Nature Communications
- Vol. 17  (1)
Open AccessBrain-inspired spatial intelligence for embodied agents
Spatial cognition enables adaptive goal-directed behavior through structured internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: landmarks for salient cues, route knowledge for movement trajectories, and survey knowledge for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse embodied navigation tasks (e.g., improving success weighted by path length from 17.6% to 44.9% in instance-level navigation and from 42.7% to 53.1% in zero-shot long-horizon instruction-following), while also supporting versatile embodied behaviors in the real physical world. These results highlight a scalable path toward general-purpose spatial intelligence.
- Open Access
- 4 May 2026
- Published by Springer Nature in Research Square
Neuro-inspired cascaded memory coordination enables continual generalization
Biological systems continually incorporate new experiences while preserving prior knowledge through coordinated interactions across distributed memory systems. Artificial neural networks, by contrast, typically address continual learning by reducing interference, often through replay buffers or parameter isolation. Although effective for limiting forgetting, these strategies do not explicitly support the integration of new information into existing knowledge. Here we introduce the Cascaded Memory Network (CaMNet), a neuro-inspired continual learning framework that organizes memory into a progressive cascade of modules and uses compact cues to trigger targeted reinstatement of prior representations. Instead of retraining on stored samples, CaMNet stabilizes task-relevant knowledge by coordinating internal memory states and enforcing consistency across the cascade. Across continual vision–language and reinforcement learning benchmarks, CaMNet improves both retention and forward transfer relative to strong continual learning baselines. CaMNet also enables cue-driven recovery of latent memory traces after substantial performance degradation, indicating that previously acquired knowledge can be functionally re-engaged without revisiting prior inputs. In dynamic physical environments, the framework allows a humanoid robot to rapidly adapt to perceptual shifts and bridge the sim-to-real gap while preserving pre-trained capabilities. These results identify cascaded memory coordination as an effective computational principle for continual generalization and replay-free continual learning across domains.
- 4 May 2026
- Published by Springer Nature in Research Square
Open AccessNeuro-inspired cascaded memory coordination enables continual generalization
Biological systems continually incorporate new experiences while preserving prior knowledge through coordinated interactions across distributed memory systems. Artificial neural networks, by contrast, typically address continual learning by reducing interference, often through replay buffers or parameter isolation. Although effective for limiting forgetting, these strategies do not explicitly support the integration of new information into existing knowledge. Here we introduce the Cascaded Memory Network (CaMNet), a neuro-inspired continual learning framework that organizes memory into a progressive cascade of modules and uses compact cues to trigger targeted reinstatement of prior representations. Instead of retraining on stored samples, CaMNet stabilizes task-relevant knowledge by coordinating internal memory states and enforcing consistency across the cascade. Across continual vision–language and reinforcement learning benchmarks, CaMNet improves both retention and forward transfer relative to strong continual learning baselines. CaMNet also enables cue-driven recovery of latent memory traces after substantial performance degradation, indicating that previously acquired knowledge can be functionally re-engaged without revisiting prior inputs. In dynamic physical environments, the framework allows a humanoid robot to rapidly adapt to perceptual shifts and bridge the sim-to-real gap while preserving pre-trained capabilities. These results identify cascaded memory coordination as an effective computational principle for continual generalization and replay-free continual learning across domains.
- Open Access
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collectively known as general continual learning (GCL), encapsulates practical challenges such as online datastreams and blurry task boundaries. Although leveraging pretrained models (PTMs) has greatly advanced conventional continual learning (CL), these methods remain limited in reconciling the diverse and temporally mixed information along a single pass, resulting in sub-optimal GCL performance. Inspired by meta-plasticity and reconstructive memory in neuroscience, we introduce here an innovative approach named Meta Post-Refinement (MePo) for PTMs-based GCL. This approach constructs pseudo task sequences from pretraining data and develops a bi-level meta-learning paradigm to refine the pretrained backbone, which serves as a prolonged pretraining phase but greatly facilitates rapid adaptation of representation learning to downstream GCL tasks. MePo further initializes a meta covariance matrix as the reference geometry of pretrained representation space, enabling GCL to exploit second-order statistics for robust output alignment. MePo serves as a plug-in strategy that achieves significant performance gains across a variety of GCL benchmarks and pretrained checkpoints in a rehearsal-free manner (e.g., 15.10\%, 13.36\%, and 12.56\% on CIFAR-100, ImageNet-R, and CUB-200 under Sup-21/1K). Our source code is available at \href{https://github.com/SunGL001/MePo}{MePo}
Open AccessMePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collectively known as general continual learning (GCL), encapsulates practical challenges such as online datastreams and blurry task boundaries. Although leveraging pretrained models (PTMs) has greatly advanced conventional continual learning (CL), these methods remain limited in reconciling the diverse and temporally mixed information along a single pass, resulting in sub-optimal GCL performance. Inspired by meta-plasticity and reconstructive memory in neuroscience, we introduce here an innovative approach named Meta Post-Refinement (MePo) for PTMs-based GCL. This approach constructs pseudo task sequences from pretraining data and develops a bi-level meta-learning paradigm to refine the pretrained backbone, which serves as a prolonged pretraining phase but greatly facilitates rapid adaptation of representation learning to downstream GCL tasks. MePo further initializes a meta covariance matrix as the reference geometry of pretrained representation space, enabling GCL to exploit second-order statistics for robust output alignment. MePo serves as a plug-in strategy that achieves significant performance gains across a variety of GCL benchmarks and pretrained checkpoints in a rehearsal-free manner (e.g., 15.10\%, 13.36\%, and 12.56\% on CIFAR-100, ImageNet-R, and CUB-200 under Sup-21/1K). Our source code is available at \href{https://github.com/SunGL001/MePo}{MePo}
- Open Access
PACE: Pretrained Audio Continual Learning
Audio is a fundamental modality for analyzing speech, music, and environmental sounds. Although pretrained audio models have significantly advanced audio understanding, they remain fragile in real-world settings where data distributions shift over time. In this work, we present the first systematic benchmark for audio continual learning (CL) with pretrained models (PTMs), together with a comprehensive analysis of its unique challenges. Unlike in vision, where parameter-efficient fine-tuning (PEFT) has proven effective for CL, directly transferring such strategies to audio leads to poor performance. This stems from a fundamental property of audio backbones: they focus on low-level spectral details rather than structured semantics, causing severe upstream-downstream misalignment. Through extensive empirical study, we identify analytic classifiers with first-session adaptation (FSA) as a promising direction, but also reveal two major limitations: representation saturation in coarse-grained scenarios and representation drift in fine-grained scenarios. To address these challenges, we propose PACE, a novel method that enhances FSA via a regularized analytic classifier and enables multi-session adaptation through adaptive subspace-orthogonal PEFT for improved semantic alignment. In addition, we introduce spectrogram-based boundary-aware perturbations to mitigate representation overlap and improve stability. Experiments on six diverse audio CL benchmarks demonstrate that PACE substantially outperforms state-of-the-art baselines, marking an important step toward robust and scalable audio continual learning with PTMs.
Open AccessPACE: Pretrained Audio Continual Learning
Audio is a fundamental modality for analyzing speech, music, and environmental sounds. Although pretrained audio models have significantly advanced audio understanding, they remain fragile in real-world settings where data distributions shift over time. In this work, we present the first systematic benchmark for audio continual learning (CL) with pretrained models (PTMs), together with a comprehensive analysis of its unique challenges. Unlike in vision, where parameter-efficient fine-tuning (PEFT) has proven effective for CL, directly transferring such strategies to audio leads to poor performance. This stems from a fundamental property of audio backbones: they focus on low-level spectral details rather than structured semantics, causing severe upstream-downstream misalignment. Through extensive empirical study, we identify analytic classifiers with first-session adaptation (FSA) as a promising direction, but also reveal two major limitations: representation saturation in coarse-grained scenarios and representation drift in fine-grained scenarios. To address these challenges, we propose PACE, a novel method that enhances FSA via a regularized analytic classifier and enables multi-session adaptation through adaptive subspace-orthogonal PEFT for improved semantic alignment. In addition, we introduce spectrogram-based boundary-aware perturbations to mitigate representation overlap and improve stability. Experiments on six diverse audio CL benchmarks demonstrate that PACE substantially outperforms state-of-the-art baselines, marking an important step toward robust and scalable audio continual learning with PTMs.
- 29 December 2025
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 8  (1) , 6-19
Versatile cardiovascular signal generation with a unified diffusion transformer
- 29 December 2025
- Published by Springer Nature in Nature Machine Intelligence
- Vol. 8  (1) , 6-19
Versatile cardiovascular signal generation with a unified diffusion transformer
- Open Access
- 27 October 2025
- Published by Springer Nature in Research Square
From reactive to cognitive: brain-inspired spatial intelligence for embodied agents
Spatial cognition enables adaptive goal-directed behavior by constructing internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: landmarks for salient cues, route knowledge for movement trajectories, and survey knowledge for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse navigation tasks, demonstrates strong zero-shot generalization, and supports versatile embodied behaviors in the real physical world, offering a scalable and biologically grounded path toward general-purpose spatial intelligence.
- 27 October 2025
- Published by Springer Nature in Research Square
Open AccessFrom reactive to cognitive: brain-inspired spatial intelligence for embodied agents
Spatial cognition enables adaptive goal-directed behavior by constructing internal models of space. Robust biological systems consolidate spatial knowledge into three interconnected forms: landmarks for salient cues, route knowledge for movement trajectories, and survey knowledge for map-like representations. While recent advances in multi-modal large language models (MLLMs) have enabled visual-language reasoning in embodied agents, these efforts lack structured spatial memory and instead operate reactively, limiting their generalization and adaptability in complex real-world environments. Here we present Brain-inspired Spatial Cognition for Navigation (BSC-Nav), a unified framework for constructing and leveraging structured spatial memory in embodied agents. BSC-Nav builds allocentric cognitive maps from egocentric trajectories and contextual cues, and dynamically retrieves spatial knowledge aligned with semantic goals. Integrated with powerful MLLMs, BSC-Nav achieves state-of-the-art efficacy and efficiency across diverse navigation tasks, demonstrates strong zero-shot generalization, and supports versatile embodied behaviors in the real physical world, offering a scalable and biologically grounded path toward general-purpose spatial intelligence.
- Open Access
Convergent multi-modular architecturefor adaptive learning in Drosophila and artificial intelligence