Dongzhou Cheng

Orcid: 0000-0003-1575-6292

According to our database¹, Dongzhou Cheng authored at least 23 papers between 2023 and 2026.

Collaborative distances:

Dijkstra number² of five.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

Sensor-Prompt Tuning: Aligning Time Series Foundational Models With Motion Sensors for Few-Shot Activity Recognition.

[BibT_eX]

[DOI]

IEEE Trans. Mob. Comput., July, 2026

One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement.

[BibT_eX]

[DOI]

CoRR, April, 2026

Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL.

[BibT_eX]

[DOI]

CoRR, February, 2026

Deep convolutional state space model as human activity recognizer.

[BibT_eX]

[DOI]

Inf. Fusion, 2026

Diffusion-facilitated knowledge distillation in human activity recognition.

[BibT_eX]

[DOI]

Neurocomputing, 2026

DeepSenseMoE: Harnessing Power of Time Series Foundation Models for Few-Shot Human Activity Recognition.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

RLFR: Extending Reinforcement Learning for LLMs with Flow Environment.

[BibT_eX]

[DOI]

CoRR, October, 2025

Learning Sensor Sample-Reweighting for Dynamic Early-Exit Activity Recognition Via Meta Learning.

[BibT_eX]

[DOI]

IEEE J. Biomed. Health Informatics, June, 2025

Deconfounding Causal Inference through Two-branch Framework with Early-forking for Sensor-based Cross-domain Activity Recognition.

[BibT_eX]

[DOI]

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., June, 2025

WaveHAR: Learning Wavelet Representation for Wearable Human Activity Recognition.

[BibT_eX]

[DOI]

IEEE Trans. Instrum. Meas., 2025

Long kernel distillation in human activity recognition.

[BibT_eX]

[DOI]

Knowl. Based Syst., 2025

Ensemble early exit network on human activity recognition using wearable sensors.

[BibT_eX]

[DOI]

Comput. Networks, 2025

Fixing deep early exit ensembles for sensor-based human activity recognition through uncertainty quantification.

[BibT_eX]

[DOI]

Appl. Soft Comput., 2025

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024

Towards Better Accuracy-Efficiency Trade-Offs: Dynamic Activity Inference via Collaborative Learning From Various Width-Resolution Configurations.

[BibT_eX]

[DOI]

IEEE Trans. Artif. Intell., December, 2024

MaskCAE: Masked Convolutional AutoEncoder via Sensor Data Reconstruction for Self-Supervised Human Activity Recognition.

[BibT_eX]

[DOI]

IEEE J. Biomed. Health Informatics, May, 2024

An automatic network structure search via channel pruning for accelerating human activity inference on mobile devices.

[BibT_eX]

[DOI]

Expert Syst. Appl., March, 2024

A General Multistage Deep Learning Framework for Sensor-Based Human Activity Recognition Under Bounded Computational Budget.

[BibT_eX]

[DOI]

IEEE Trans. Instrum. Meas., 2024

Learn From Others and Be Yourself in Federated Human Activity Recognition via Attention-Based Pairwise Collaborations.

[BibT_eX]

[DOI]

IEEE Trans. Instrum. Meas., 2024

Dynamic instance-aware layer-bit-select network on human activity recognition using wearable sensors.

[BibT_eX]

[DOI]

Eng. Appl. Artif. Intell., 2024

A sparse diverse-branch large kernel convolutional neural network for human activity recognition using wearables.

[BibT_eX]

[DOI]

Appl. Soft Comput., 2024

2023

ProtoHAR: Prototype Guided Personalized Federated Learning for Human Activity Recognition.

[BibT_eX]

[DOI]

IEEE J. Biomed. Health Informatics, August, 2023

Learning hierarchical time series data augmentation invariances via contrastive supervision for human activity recognition.

[BibT_eX]

[DOI]

Knowl. Based Syst., 2023

Dongzhou Cheng

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...