Author name cluster

Zhen Tian

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

JBHI Journal 2026 Journal Article

Adaptive Feature Selection With Hierarchical Learning for Drug-Target Interaction Prediction

Zhen Tian
Miao Jiang
Jin Li
Wenjie Zhang
Mingliang Xu

Accurate prediction of drug–target interactions (DTIs) is essential for drug discovery and repurposing. Although deep learning has driven substantial progress, critical limitations remain: a singular focus on intermolecular associations results in suboptimal representation learning, and the failure to leverage key features during interactions constrains further performance gains. Here, we propose ASHL-DTI, a novel framework that integrates hierarchical learning with adaptive feature selection to significantly boost both feature quality and model generalizability. Specifically, the hierarchical learning component captures multi-level intramolecular associations to learn more discriminative representations. Simultaneously, we incorporate an adaptive Top-k selection mechanism to retain the most predictive features, facilitating effective interaction between drugs and targets. Experimental results across multiple public benchmark datasets demonstrate that ASHL-DTI achieves superior performance compared with state-of-the-art approaches. Moreover, ASHL-DTI exhibits strong generalization ability in predicting novel drug–target pairs, underscoring its potential in drug discovery. The complete source code of ASHL-DTI is available at https://github.com/Miwkwh/ASHL-DTI.

Details DOI

AAMAS Conference 2026 Conference Paper

Scalable and Safe Multi-Agent Coordination with Reconstructed Level-k Monte Carlo Tree Search

Zhihao Lin
Lin Wu
Zhen Tian
Alessio Lomuscio
Jianglin Lan

Multi-agent coordination without central control requires balancing safety and computational efficiency. We present a novel frameworkthattransformsLevel-𝑘 cognitivereasoningfromadescriptive modelofboundedrationalityintoaconstructiveplanningalgorithm for agent coordination. Our key insight is to replace Level-𝑘 reasoning’s assumption of random Level-0 behavior with safety-oriented baselineswhereallagentscomputeconservativetrajectories. Safety emergesnaturallyfromtherecursivestructure: eachreasoninglevel inherits and strengthens the safety margins of lower levels, creating cascading conservatism that prevents collisions without explicit constraints. Beyond ensuring safety, this hierarchical conservatism also provides a natural foundation for efficient planning. By integrating this reconstructed hierarchy with Monte Carlo Tree Search (MCTS), we achieve significant computational advantages through two complementary mechanisms: a Dynamic Interaction Graph that constrains candidate interactions and reduces complexity from exponential to linear in agent count, and Safety-aware Pruning within MCTS that eliminates infeasible actions before evaluation. Weevaluateourframeworkonsymmetricmulti-agentintersections, demonstrating collision-free coordination and real-time efficiency across scenarios of varying complexity, highlighting its scalability and robustness for safety-critical planning.

PDF

JBHI Journal 2025 Journal Article

DSANIB: Drug-Target Interaction Predictions With Dual-View Synergistic Attention Network and Information Bottleneck Strategy

Zhen Tian
Zhuangzhuang Zhang
Wanning Zhou
Zhixia Teng
Wei Song
Quan Zou

Prediction of drug-target interactions (DTIs) is one of the crucial steps for drug repositioning. Identifying DTIs through bio-experimental manners is always expensive and time-consuming. Recently, deep learning-based approaches have shown promising advancements in DTI prediction, but they face two notable challenges: (i) how to explicitly capture local interactions between drug-target pairs and learn their higher-order substructure embeddings; (ii) How to filter out redundant information to obtain effective embeddings for drugs and targets. Results: In this study, we propose a novel approach, termed DSANIB, to infer potential interactions between drugs and targets. DSANIB comprises two primary components: (1) DSAN component: The Inter-view Attention Network Module explicitly learns the local interactions between drugs and targets, while the Intra-view Attention Network Module aggregates information from local interaction features to obtain their higher-order substructure embeddings. (2) Information Bottleneck (IB) component: DSANIB adopts the IB strategy, which could retain relevant information while minimizing the redundant features to obtain their discriminative representations. Extensive experimental results demonstrate that DSANIB outperforms other SOTA prediction models. In addition, visualization of drug and target embeddings learned through DSANIB could provide interpretable insights for the prediction results.

Details DOI

AAAI Conference 2025 Conference Paper

EchoDiffusion: Waveform Conditioned Diffusion Models for Echo-Based Depth Estimation

Wenjie Zhang
Jun Yin
Long Ma
Peng Yu
Xiaoheng Jiang
Zhen Tian
Mingliang Xu

To extract spatial information, depth estimation using conventional echo-based methods typically employs models with encoder-decoder architectures, such as UNet. However, these methods may face challenges in extracting fine details from echo waveforms and handling multi-scale feature extraction with high precision. To address these challenges, we introduce EchoDiffusion, a framework that incorporates diffusion models conditioned on waveform embeddings for echo-based depth estimation. This framework employs the Multi-Scale Adaptive Latent Feature Network (MALF-Net) to extract multi-scale spatial features and perform adaptive fusion, encoding the echo spectrograms into the latent space. Additionally, we propose the Echo Waveform Detail Embedder (EWDE), which leverages a pre-trained Wav2Vec model to extract detailed spatial information from echo waveforms, using these details as conditional inputs to guide the reverse diffusion process in the latent space. By embedding the echo waveforms into the reverse diffusion process, we can more accurately guide the generation of depth maps. Our extensive evaluations on the Replica and Matterport3D datasets demonstrate that EchoDiffusion establishes new benchmarks for state-of-the-art performance in echo-based depth estimation.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Irrational Complex Rotations Empower Low-bit Optimizers

Zhen Tian
Xin Zhao
Ji-Rong Wen

In this paper, we propose a novel optimizer state compression algorithm, namely \textbf{$\pi$-Quant}, which leverages the properties of irrational numbers (\eg $\pi$) for memory-efficient training. The core idea is based on our mathematical findings, which show that a pair of parameters can be represented by a single rotation angle using the complex rotation scheme. Building on this insight, we map the parameters into a complex space and perform quantization using the corresponding rotation angles. To efficiently integrate it into optimization process, we develop an efficient system of geometric equations that computes the precise rotation angles with linear complexity. We evaluate $\pi$-Quant on a wide range of tasks. Our experiments show that it can reduce the bit-width of parameters to 3. 32-bit, achieving a 41. 8\% decrease in GPU memory usage, all while maintaining full accuracy. \textcolor{blue}{We have submitted the code in supplementary materials}.

PDF Details

IROS Conference 2025 Conference Paper

MobiExo: GPS-SLAM Fusion for Seamless Indoor-Outdoor Mobile Manipulation with Hand-Foot Coordination

Jianpeng Wang
Zhen Tian
Wenlong Chen
Dian Yuan
Zhou Zhou
Ming Cen
Xia Hua
Fei Yu

Teleoperation systems for mobile robots face significant challenges in achieving seamless coordination across dynamic environments. We present MobiExo, a teleoperation system that unlocks seamless indoor-outdoor mobile manipulation. Our approach tackles two fundamental challenges: robust cross-environment localization and intuitive full-body control. A novel self-adaptive federated filter unifies GPS and SLAM, delivering continuous centimeter-level positioning (4. 5±0. 8 cm indoor, 6. 8±1. 2 cm outdoor) and eliminating transition errors. Simultaneously, an integrated hand-foot coordination framework translates the operator’s natural gait and gestures into fluid robot actions, maintaining remarkable millimeter-level end-effector precision (3. 5±0. 4 mm) during navigation. Extensive field trials validate our design, demonstrating high task success (96. 7% indoor, 94. 3% outdoor) and a 5. 9× efficiency improvement in multi-location tasks over stationary setups. Code is available at: https://github.com/wangjianpeng200/MobiExo.git

Details

NeurIPS Conference 2024 Conference Paper

Exploring Context Window of Large Language Models via Decomposed Positional Vectors

Zican Dong
Junyi Li
Xin Men
Wayne X. Zhao
Bingning Wang
Zhen Tian
weipeng chen
Ji-Rong Wen

Transformer-based large language models (LLMs) typically have a limited context window, resulting in significant performance degradation when processing text beyond the length of the context window. Extensive studies have been proposed to extend the context window and achieve length extrapolation of LLMs, but there is still a lack of in-depth interpretation of these approaches. In this study, we explore the positional information within and beyond the context window for deciphering the underlying mechanism of LLMs. By using a mean-based decomposition method, we disentangle positional vectors from hidden states of LLMs and analyze their formation and effect on attention. Furthermore, when texts exceed the context window, we analyze the change of positional vectors in two settings, i. e. , direct extrapolation and context window extension. Based on our findings, we design two training-free context window extension methods, positional vector replacement and attention window extension. Experimental results show that our methods can effectively extend the context window length.

PDF Details DOI