Zhichao Liang

Zhichao Lin, Zhichao Liang, Gaoqiang Liu et al.

As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this end, building upon Tongyi DeepResearch, a powerful agentic foundation model, we focus on the Chinese medical deep search scenario and propose QuarkMedSearch, systematically exploring a full-pipeline approach spanning medical multi-hop data construction, training strategies, and evaluation benchmarks to further push and assess its performance upper bound in vertical domains. Specifically, for data synthesis, to address the scarcity of deep search training data in the medical domain, we combine a large-scale medical knowledge graph with real-time online exploration to construct long-horizon medical deep search training data; for post-training, we adopt a two-stage SFT and RL training strategy that progressively enhances the model's planning, tool invocation, and reflection capabilities required for deep search, while maintaining search efficiency; for evaluation, we collaborate with medical experts to construct the QuarkMedSearch Benchmark through rigorous manual verification. Experimental results demonstrate that QuarkMedSearch achieves state-of-the-art performance among open-source models of comparable scale on the QuarkMedSearch Benchmark, while also maintaining strong competitiveness on general benchmarks.

Wanguang Yin, Zhichao Liang, Jianguo Zhang et al.

Partial least square regression (PLSR) is a widely-used statistical model to reveal the linear relationships of latent factors that comes from the independent variables and dependent variables. However, traditional methods to solve PLSR models are usually based on the Euclidean space, and easily getting stuck into a local minimum. To this end, we propose a new method to solve the partial least square regression, named PLSR via optimization on bi-Grassmann manifold (PLSRbiGr). Specifically, we first leverage the three-factor SVD-type decomposition of the cross-covariance matrix defined on the bi-Grassmann manifold, converting the orthogonal constrained optimization problem into an unconstrained optimization problem on bi-Grassmann manifold, and then incorporate the Riemannian preconditioning of matrix scaling to regulate the Riemannian metric in each iteration. PLSRbiGr is validated with a variety of experiments for decoding EEG signals at motor imagery (MI) and steady-state visual evoked potential (SSVEP) task. Experimental results demonstrate that PLSRbiGr outperforms competing algorithms in multiple EEG decoding tasks, which will greatly facilitate small sample data learning.

Jinghao Xin, Zhichao Liang, Zihuan Zhang et al.

Deep Reinforcement Learning (DRL) has demonstrated potential in addressing robotic local planning problems, yet its efficacy remains constrained in highly unstructured and dynamic environments. To address these challenges, this study proposes the ColorDynamic framework. First, an end-to-end DRL formulation is established, which maps raw sensor data directly to control commands, thereby ensuring compatibility with unstructured environments. Under this formulation, a novel network, Transqer, is introduced. The Transqer enables online DRL learning from temporal transitions, substantially enhancing decision-making in dynamic scenarios. To facilitate scalable training of Transqer with diverse data, an efficient simulation platform E-Sparrow, along with a data augmentation technique leveraging symmetric invariance, are developed. Comparative evaluations against state-of-the-art methods, alongside assessments of generalizability, scalability, and real-time performance, were conducted to validate the effectiveness of ColorDynamic. Results indicate that our approach achieves a success rate exceeding 90% while exhibiting real-time capacity (1.2-1.3 ms per planning). Additionally, ablation studies were performed to corroborate the contributions of individual components. Building on this, the OkayPlan-ColorDynamic (OPCD) navigation system is presented, with simulated and real-world experiments demonstrating its superiority and applicability in complex scenarios. The codebase and experimental demonstrations have been open-sourced on our website to facilitate reproducibility and further research.

Zhichao Liang, Satoshi Nakamura

Existing dynamic Theory of Mind (ToM) benchmarks mostly place language models in a passive role: the model reads a sequence of connected scenarios and reports what people believe, feel, intend, and do as these states change. In real social interaction, ToM is also used for action: a speaker plans what to say in order to shift another person's mental-state trajectory toward a goal. We introduce SocialMindChange, a benchmark that moves from tracking minds to changing minds in social interaction. Each instance defines a social context with 4 characters and five connected scenes. The model plays one character and generates dialogue across the five scenes to reach the target while remaining consistent with the evolving states of all participants. SocialMindChange also includes selected higher-order states. Using a structured four-step framework, we construct 1,200 social contexts, covering 6000 scenarios and over 90,000 questions, each validated for realism and quality. Evaluations on ten state-of-the-art LLMs show that their average performance is 54.2% below human performance. This gap suggests that current LLMs still struggle to maintain and change mental-state representations across long, linked interactions.

Youzhi Qu, Junfeng Xia, Xinyao Jian et al.

Data reconstruction is a widely used pre-training task to learn the generalized features for many downstream tasks. Although reconstruction tasks have been applied to neural signal completion and denoising, neural signal reconstruction is less studied. Here, we employ the masked autoencoder (MAE) model to reconstruct functional magnetic resonance imaging (fMRI) data, and utilize a transfer learning framework to obtain the cognitive taskonomy, a matrix to quantify the similarity between cognitive tasks. Our experimental results demonstrate that the MAE model effectively captures the temporal dynamics patterns and interactions within the brain regions, enabling robust cross-subject fMRI signal reconstruction. The cognitive taskonomy derived from the transfer learning framework reveals the relationships among cognitive tasks, highlighting subtask correlations within motor tasks and similarities between emotion, social, and gambling tasks. Our study suggests that the fMRI reconstruction with MAE model can uncover the latent representation and the obtained taskonomy offers guidance for selecting source tasks in neural decoding tasks for improving the decoding performance on target tasks.