Publications

2025

1. 

   The Art of Scaling Reinforcement Learning Compute for LLMs

   Devvrit Khatri, Lovish Madaan, Rishabh Tiwari, Rachit Bansal, and 3 more authors

   International Conference on Learning Representations (ICLR), 2026  Oral

   Bib PDF arXiv OpenReview

   @inproceedings{khatri2025scalerl,
     title = {The Art of Scaling Reinforcement Learning Compute for LLMs},
     author = {Khatri, Devvrit and Madaan, Lovish and Tiwari, Rishabh and Bansal, Rachit and Duvvuri, Sai Surya and Zaheer, Manzil and Dhillon, Inderjit S and Brandfonbrener, David and Agarwal, Rishabh},
     booktitle = {International Conference on Learning Representations},
     year = {2026},
     url = {https://openreview.net/forum?id=FMjeC9Msws},
   }

2. 

   QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache

   Rishabh Tiwari, Haocheng Xi, Aditya Tomar, and 7 more authors

   Under Review, 2025

   Bib PDF

   @article{tiwari2025quantspec,
     title = {QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache},
     author = {Tiwari, Rishabh and Xi, Haocheng and Tomar, Aditya and Hooper, Coleman and Kim, Sehoon and Horton, Maxwell and Najibi, Mahyar and Mahoney, Michael W and Keutzer, Kurt and Gholami, Amir},
     journal = {Under Review},
     year = {2025},
   }

3. 

   Why Do Multi-Agent LLM Systems Fail?

   Mert Cemri, Melissa Z Pan, Shuyi Yang, and 8 more authors

   Under Review, 2025

   Bib PDF

   @article{cemri2025multi,
     title = {Why Do Multi-Agent LLM Systems Fail?},
     author = {Cemri, Mert and Pan, Melissa Z and Yang, Shuyi and Agrawal, Lakshya A and Chopra, Bhavya and Tiwari, Rishabh and Keutzer, Kurt and Parameswaran, Aditya and Klein, Dan and Ramchandran, Kannan and others},
     journal = {Under Review},
     year = {2025},
   }

2024

1. 

   Using Early Readouts to Mediate Featural Bias in Distillation

   Rishabh Tiwari, Durga Sivasubramanian, Anmol Mekala, and 2 more authors

   WACV, 2024

   Bib PDF

   @article{tiwari2023adversarial,
     title = {Using Early Readouts to Mediate Featural Bias in Distillation},
     author = {Tiwari, Rishabh and Sivasubramanian, Durga and Mekala, Anmol and Ramakrishnan, Ganesh and Shenoy, Pradeep},
     journal = {WACV},
     year = {2024},
   }

2023

1. 

   Overcoming Simplicity Bias in Deep Networks using a Feature Sieve

   Rishabh Tiwari, and Pradeep Shenoy

   ICML, 2023

   Bib PDF

   @article{tiwari2023adversariam,
     title = {Overcoming Simplicity Bias in Deep Networks using a Feature Sieve},
     author = {Tiwari, Rishabh and Shenoy, Pradeep},
     journal = {ICML},
     year = {2023},
   }

2. 

   Interactive Concept Bottleneck Models

   Kushal Chauhan, Rishabh Tiwari, Jan Freyberg, and 2 more authors

   AAAI, 2023

   Bib PDF

   @article{chauhan2022interactive,
     title = {Interactive Concept Bottleneck Models},
     author = {Chauhan, Kushal and Tiwari, Rishabh and Freyberg, Jan and Shenoy, Pradeep and Dvijotham, Krishnamurthy},
     journal = {AAAI},
     year = {2023},
   }

3. ICASSP

   On designing light-weight object trackers through network pruning: Use CNNs or transformers?

   Saksham Aggarwal, Taneesh Gupta, Pawan Kumar Sahu, and 4 more authors

   ICASSP, 2023

   Bib PDF

   @article{aggarwal2022designing,
     title = {On designing light-weight object trackers through network pruning: Use CNNs or transformers?},
     author = {Aggarwal, Saksham and Gupta, Taneesh and Sahu, Pawan Kumar and Chavan, Arnav and Tiwari, Rishabh and Prasad, Dilip K and Gupta, Deepak K},
     journal = {ICASSP},
     year = {2023},
   }

2022

1. 

   GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning

   Rishabh Tiwari, Krishnateja Killamsetty, Rishabh Iyer, and 1 more author

   In CVPR, 2022

   Bib PDF

   @inproceedings{tiwari2021gcr,
     title = {GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning},
     author = {Tiwari, Rishabh and Killamsetty, Krishnateja and Iyer, Rishabh and Shenoy, Pradeep},
     booktitle = {CVPR},
     year = {2022},
   }

2. 

   Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning

   Arnav Chavan, Rishabh Tiwari, Udbhav Bamba, and 1 more author

   In CVPR, 2022

   Bib PDF

   @inproceedings{chavan2022dynamic,
     title = {Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning},
     author = {Chavan, Arnav and Tiwari, Rishabh and Bamba, Udbhav and Gupta, Deepak K},
     booktitle = {CVPR},
     pages = {9851--9860},
     year = {2022},
   }

2021

1. 

   Chipnet: Budget-aware pruning with heaviside continuous approximations

   Rishabh Tiwari, Udbhav Bamba, Arnav Chavan, and 1 more author

   ICLR, 2021

   Bib PDF

   @article{tiwari2021chipnet,
     title = {Chipnet: Budget-aware pruning with heaviside continuous approximations},
     author = {Tiwari, Rishabh and Bamba, Udbhav and Chavan, Arnav and Gupta, Deepak K},
     journal = {ICLR},
     year = {2021},
   }

2. ICASSP

   Rescaling cnn through learnable repetition of network parameters

   Arnav Chavan, Udbhav Bamba, Rishabh Tiwari, and 1 more author

   In IEEE International Conference on Image Processing (ICIP), 2021

   Bib PDF

   @inproceedings{chavan2021rescaling,
     title = {Rescaling cnn through learnable repetition of network parameters},
     author = {Chavan, Arnav and Bamba, Udbhav and Tiwari, Rishabh and Gupta, Deepak},
     booktitle = {IEEE International Conference on Image Processing (ICIP)},
     year = {2021},
   }

2020

1. ISBI

   Multi-plateau ensemble for endoscopic artefact segmentation and detection

   Suyog Jadhav, Udbhav Bamba, Arnav Chavan, and 2 more authors

   In EndoCV2020 workshop ISBI, 2020

   Bib PDF

   @inproceedings{jadhav2020multi,
     title = {Multi-plateau ensemble for endoscopic artefact segmentation and detection},
     author = {Jadhav, Suyog and Bamba, Udbhav and Chavan, Arnav and Tiwari, Rishabh and Raj, Aryan},
     booktitle = {EndoCV2020 workshop ISBI},
     year = {2020},
   }