Scholar

Daniel Becking

Google Scholar ID: 9iCPs2AAAAAJ

Research Associate, PhD candidate, Fraunhofer Heinrich Hertz Institute HHI, TU Berlin

efficient deep learningneural compressionneural network codingfederated learningXAI

Citations & Impact

All-time

Citations

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

1 items

2025

Cited

Resume (English only)

Academic Achievements

2025: Paper 'Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction' accepted for poster session at EuCNC & 6G Summit and full paper accepted at GLOBECOM.
2025/07: Speaker at the AI and Machine Learning in Communication Networks Workshop, ITU AI for Good Global Summit.
2024/11: Invited speaker on 'NN Coding for Energy-Efficient Communication in FL' at BIFOLD/TU Berlin workshop on the European AI Act.
2024/07: Contributed to finalization of Conformance and Reference Software (INCTM) for NNC ed. 2 at 147th MPEG meeting; initiated next-gen NNC draft.
2024/01: Published journal paper in IEEE Transactions on Multimedia on coding and transmitting neural data for efficient distributed learning.
2023/07: NNCodec awarded Spotlight at ICML Neural Compression Workshop.
2022/06: Presented talk on 'Adaptive Differential Filters for Fast and Communication-Efficient Federated Learning' at CVPR FedVision Workshop.
2022/04: Co-authored book chapter 'ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs' in 'xxAI - Beyond Explainable AI'.
2021/05: FantastIC4 project published in IEEE Open Journal of Circuits and Systems.
2020/06: Master’s thesis led to oral presentation of 'EC2T' paper at CVPR Workshop on Efficient Deep Learning.
2019/12: Ternary neural network submission ranked top-5 in NeurIPS MicroNet Challenge.

Co-authors

10 total