A cross-site router for serving large language model inference at renewable-energy farms, balancing performance across geographically distributed sites under variable energy supply.
@unpublished{reddy2026xwind,title={XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms},author={Reddy, Tella Rajashekhar and Deshmukh, Atharva and Yu, Liangcheng and Zhang, Chaojie and Shepperd, Mike and Gandhi, Rohan and Parayil, Anjaly and Iyengar, Srinivasan and Manchepalli, Ajay and Bhattacherjee, Debopam},year={2027},note={Under review at ASPLOS 2027},}
2025
Preprint
Dynamic Negotiation Landscapes: MBPS and the Interplay of Buyer Personalities
Subrata* Das, Atharva* Deshmukh, Sriparna Saha, and 3 more authors
Introduces MBPS, a buyer-personality-aware negotiation simulator, and trains a UCB1-based seller agent that adapts to diverse personality types.
@unpublished{das2025mbps,title={Dynamic Negotiation Landscapes: MBPS and the Interplay of Buyer Personalities},author={Das, Subrata and Deshmukh, Atharva and Saha, Sriparna and Ramnani, Roshni and Maitra, Anutosh and Sengupta, Shubhashis},year={2025},note={Under review at Neurocomputing},url={https://arxiv.org/pdf/2510.15330},}
CS&L
Can Language Models Persuade? Exploring the Persuasive Efficacy of Large Language and Vision-Language Models
Rohan Kirti, Atharva Deshmukh, Kiran Kumar Dugana, and 5 more authors
A study of the persuasive efficacy of LLMs and VLMs across multiple contexts and modalities.
@article{kirti2025persuade,title={Can Language Models Persuade? Exploring the Persuasive Efficacy of Large Language and Vision-Language Models},author={Kirti, Rohan and Deshmukh, Atharva and Dugana, Kiran Kumar and Rathore, Yash and Shriparn, Shipra and Saha, Sriparna and Ramnani, Roshni R. and Maitra, Anutosh},journal={Computer Speech \& Language},year={2025}}
FAISys
BeLLMan: Controlling LLM Congestion
Tella Rajashekhar* Reddy, Atharva* Deshmukh, Karan Tandon, and 3 more authors
In Proceedings of the 1st Workshop on Foundations of AI Systems (FAISys), 2025
We study congestion in LLM inference and propose token-level output reduction together with predictive scheduling to improve throughput, fairness and energy efficiency in vLLM-style serving systems.
@inproceedings{reddy2025bellman,title={BeLLMan: Controlling LLM Congestion},author={Reddy, Tella Rajashekhar and Deshmukh, Atharva and Tandon, Karan and Gandhi, Rohan and Parayil, Anjaly and Bhattacherjee, Debopam},booktitle={Proceedings of the 1st Workshop on Foundations of AI Systems (FAISys)},year={2025},}
2023
ACL
APTSumm at BioLaySumm Task 1: Biomedical Breakdown, Improving Readability by Relevancy-Based Selection
A.S.* Poornash, Atharva* Deshmukh, Archit* Sharma, and 1 more author
In Proceedings of the 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, 2023
A three-step abstractive summarization pipeline that breaks biomedical articles into sections, generates candidate summaries with SIMCLS, and selects the top paragraph per section. Achieved 2nd place on readability metrics with high ROUGE.
@inproceedings{poornash2023aptsumm,title={APTSumm at BioLaySumm Task 1: Biomedical Breakdown, Improving Readability by Relevancy-Based Selection},author={Poornash, A.S. and Deshmukh, Atharva and Sharma, Archit and Saha, Sriparna},booktitle={Proceedings of the 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks},year={2023},publisher={Association for Computational Linguistics},url={https://aclanthology.org/2023.bionlp-1.61.pdf},}