Udbhav Bamba

ubamba98@gmail.com

I am an Applied Scientist II at Amazon Lab126, where I build efficient large language models for Alexa+. My work focuses on mixture-of-experts systems and model compression, including dense-to-MoE conversion and quantization-friendly training for low-latency on-device and cloud inference at 200B+ parameter scale. Previously, I productionized vision-language models at Amazon Ads, researched resource-efficient machine learning at Mila, and co-founded Transmute AI Research at IIT (ISM) Dhanbad.

I am also a Kaggle Competitions Master (top 0.02%, peak rank 45 worldwide). Outside work, I enjoy gaming, cycling, and badminton. For updates, see my Google Scholar or LinkedIn.

News

Jun 01, 2026	Received an ICML 2026 Silver Reviewer Award.
May 01, 2026	Three papers accepted at ICML 2026 : XRPO, DOT-MoE, and Reward Under Attack.
Feb 26, 2026	S2D accepted at CVPR 2026.
Jan 15, 2026	CRoPS accepted at TMLR.
Jul 01, 2025	Joined Amazon Lab126 as an Applied Scientist II, working on efficient GenAI for Alexa+.

Selected publications

^* Equal contribution

XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation

Udbhav Bamba^*, Minghao Fang^*, Yifan Yu^*, and 2 more authors

In International Conference on Machine Learning (ICML), 2026

Bib PDF

@inproceedings{bamba2025xrpo,
  title = {XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation},
  author = {Bamba, Udbhav and Fang, Minghao and Yu, Yifan and Zheng, Haizhong and Lai, Fan},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://arxiv.org/abs/2510.06672},
}

DOT-MoE: Differentiable Optimal Transport for MoEfication

Udbhav Bamba^*, Arnav Chavan^*, Aryamaan Thakur^*, and 2 more authors

In International Conference on Machine Learning (ICML), 2026

Bib PDF

@inproceedings{bamba2026dotmoe,
  title = {DOT-MoE: Differentiable Optimal Transport for MoEfication},
  author = {Bamba, Udbhav and Chavan, Arnav and Thakur, Aryamaan and Teig, Steve and Gupta, Deepak K.},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://arxiv.org/abs/2606.01666},
}

S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations

Arnav Chavan^*, Nahush Lele^*, Udbhav Bamba^*, and 3 more authors

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Bib PDF

@inproceedings{chavan2025s2d,
  title = {S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations},
  author = {Chavan, Arnav and Lele, Nahush and Bamba, Udbhav and Dayal, Sankalp and Raghunathan, Aditi and Gupta, Deepak K.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://arxiv.org/abs/2602.14432},
}

CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models

Neeraj Anand, Samyak Jha, Udbhav Bamba, and 1 more author

Transactions on Machine Learning Research, 2026

Bib PDF

@article{anand2025crops,
  title = {CRoPS: A Training-Free Hallucination Mitigation Framework for Vision-Language Models},
  author = {Anand, Neeraj and Jha, Samyak and Bamba, Udbhav and Rahaman, Rahul},
  journal = {Transactions on Machine Learning Research},
  year = {2026},
  url = {https://openreview.net/forum?id=KQSoZDPVGX},
}

Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models

Rishabh Tiwari^*, Aditya Tomar^*, Udbhav Bamba^*, and 5 more authors

In International Conference on Machine Learning (ICML), 2026

Bib PDF

@inproceedings{bamba2026reward,
  title = {Reward Under Attack: Analyzing the Robustness and Hackability of Process Reward Models},
  author = {Tiwari, Rishabh and Tomar, Aditya and Bamba, Udbhav and Maheswaran, Monishwaran and Yang, Heng and Mahoney, Michael W. and Keutzer, Kurt and Gholami, Amir},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://arxiv.org/abs/2603.06621},
}