Ankur Mallick

35 papers A* 3A 1B 2Misc 2Journal 21Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Budget-Aware Agentic Routing via Boundary-Guided Training.
CoRR
Caiqi Zhang, Menglin Xia, Xuchao Zhang, Daniel Madrigal, Ankur Mallick, Samuel Kessler, Victor Rühle, Saravan Rajmohan
2025 J jnl
A Performance Analyzer for a Public Cloud's ML-Augmented VM Allocator.
CoRR
Roozbeh Bostandoost, Pooria Namyar, Siva Kesava Reddy Kakarla, Ryan Beckett, Santiago Segarra, Eli Cortez, Ankur Mallick, Kevin Hsieh, Rodrigo Fonseca, Mohammad Hajiesmaili, Behnaz Arzani
2025 A* conf
BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute.
ICML
Dujian Ding, Ankur Mallick, Shaokun Zhang, Chi Wang, Daniel Madrigal, Mirian del Carmen Hipolito Garcia, Menglin Xia, Laks V. S. Lakshmanan, Qingyun Wu, Victor Rühle
2025 J jnl
BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute.
CoRR
Dujian Ding, Ankur Mallick, Shaokun Zhang, Chi Wang, Daniel Madrigal, Mirian del Carmen Hipolito Garcia, Menglin Xia, Laks V. S. Lakshmanan, Qingyun Wu, Victor Rühle
2025 J jnl
Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search.
CoRR
Dongge Han, Menglin Xia, Daniel Madrigal Díaz, Samuel Kessler, Ankur Mallick, Xuchao Zhang, Mirian del Carmen Hipolito Garcia, Jin Xu, Victor Rühle, Saravan Rajmohan
2025 J jnl
Exploring How LLMs Capture and Represent Domain-Specific Knowledge.
CoRR
Mirian Hipolito Garcia, Camille Couturier, Daniel Madrigal Díaz, Ankur Mallick, Anastasios Kyrillidis, Robert Sim, Victor Rühle, Saravan Rajmohan
2025 — conf
Performance Aware LLM Load Balancer for Mixed Workloads.
EuroMLSys
Kunal Jain, Anjaly Parayil, Ankur Mallick, Esha Choukse, Xiaoting Qin, Jue Zhang, Íñigo Goiri, Rujia Wang, Chetan Bansal, Victor Rühle, Anoop Kulkarni, Steve Kofsky, Saravan Rajmohan
2025 — conf
PnM: Efficient Intra-Datacenter Calls Packing for Large Conferencing Services.
SoCC
Rohan Gandhi, Ankur Mallick
2025 J jnl
ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers.
CoRR
Shivam Patel, Neharika Jali, Ankur Mallick, Gauri Joshi
2025 J jnl
SAGESERVE: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-Scaling.
Proc. ACM Meas. Anal. Comput. Syst.
Shashwat Jaiswal, Kunal Jain, Yogesh Simmhan, Anjaly Parayil, Ankur Mallick, Rujia Wang, Renée St. Amant, Chetan Bansal, Victor Rühle, Anoop Kulkarni, Steve Kofsky, Saravan Rajmohan
2025 J jnl
Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems.
CoRR
Shashwat Jaiswal, Shrikara Arun, Anjaly Parayil, Ankur Mallick, Spyros Mastorakis, Alind Khare, Chloe Alverti, Renée St. Amant, Chetan Bansal, Victor Rühle, Josep Torrellas
2025 J jnl
Serving Models, Fast and Slow:Optimizing Heterogeneous LLM Inferencing Workloads at Scale.
CoRR
Shashwat Jaiswal, Kunal Jain, Yogesh Simmhan, Anjaly Parayil, Ankur Mallick, Rujia Wang, Renée St. Amant, Chetan Bansal, Victor Rühle, Anoop Kulkarni, Steve Kofsky, Saravan Rajmohan
2025 J jnl
Tetris: Efficient Intra-Datacenter Calls Packing for Large Conferencing Services.
CoRR
Rohan Gandhi, Ankur Mallick, Ken Sueda, Rui Liang
2024 J jnl
EcoAct: Economic Agent Determines When to Register What Action.
CoRR
Shaokun Zhang, Jieyu Zhang, Dujian Ding, Mirian Hipolito Garcia, Ankur Mallick, Daniel Madrigal, Menglin Xia, Victor Rühle, Qingyun Wu, Chi Wang
2024 J jnl
Ensuring Fair LLM Serving Amid Diverse Applications.
CoRR
Redwan Ibne Seraj Khan, Kunal Jain, Haiying Shen, Ankur Mallick, Anjaly Parayil, Anoop Kulkarni, Steve Kofsky, Pankhuri Choudhary, Renée St. Amant, Rujia Wang, Yue Cheng, Ali Raza Butt, Victor Rühle, Chetan Bansal, Saravan Rajmohan
2024 A* conf
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing.
ICLR
Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Rühle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah
2024 J jnl
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing.
CoRR
Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Rühle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah
2024 J jnl
Intelligent Router for LLM Workloads: Improving Performance Through Workload-Aware Scheduling.
CoRR
Kunal Jain, Anjaly Parayil, Ankur Mallick, Esha Choukse, Xiaoting Qin, Jue Zhang, Íñigo Goiri, Rujia Wang, Chetan Bansal, Victor Rühle, Anoop Kulkarni, Steve Kofsky, Saravan Rajmohan
2023 — —
Probabilistic Methods for Mitigating Uncertainties in Large-Scale Computing and Machine Learning
Ankur Mallick
2022 — conf
Matchmaker: Data Drift Mitigation in Machine Learning for Large-Scale Systems.
MLSys
Ankur Mallick, Kevin Hsieh, Behnaz Arzani, Gauri Joshi
2022 B conf
Rateless Sum-Recovery Codes For Distributed Non-Linear Computations.
ITW
Ankur Mallick, Gauri Joshi
2022 J jnl
Rateless codes for near-perfect load balancing in distributed matrix-vector multiplication.
Commun. ACM
Ankur Mallick, Malhar Chaudhari, Utsav Sheth, Ganesh Palanikumar, Gauri Joshi
2021 A conf
Deep kernels with probabilistic embeddings for small-data learning.
UAI
Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, Thomas Yong-Jin Han
2021 A* conf
Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation.
NeurIPS
Divyansh Jhunjhunwala, Ankur Mallick, Advait Gadhikar, Swanand Kadhe, Gauri Joshi
2021 J jnl
Leveraging Spatial and Temporal Correlations in Sparsified Mean Estimation.
CoRR
Divyansh Jhunjhunwala, Ankur Mallick, Advait Gadhikar, Swanand Kadhe, Gauri Joshi
2021 — conf
Rateless Codes for Distributed Non-linear Computations.
ISTC
Ankur Mallick, Sophie Smith, Gauri Joshi
2020 J jnl
Probabilistic Neighbourhood Component Analysis: Sample Efficient Uncertainty Estimation in Deep Learning.
CoRR
Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, Thomas Yong-Jin Han
2020 — conf
Rateless Codes for Near-Perfect Load Balancing in Distributed Matrix-Vector Multiplication.
SIGMETRICS (Abstracts)
Ankur Mallick, Malhar Chaudhari, Utsav Sheth, Ganesh Palanikumar, Gauri Joshi
2019 J jnl
Deep Probabilistic Kernels for Sample-Efficient Learning.
CoRR
Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, Thomas Yong-Jin Han
2019 Misc conf
Fast and Efficient Distributed Matrix-vector Multiplication Using Rateless Fountain Codes.
ICASSP
Ankur Mallick, Malhar Chaudhari, Gauri Joshi
2019 B conf
Rateless Codes for Distributed Computations with Sparse Compressed Matrices.
ISIT
Ankur Mallick, Gauri Joshi
2019 J jnl
Rateless Codes for Near-Perfect Load Balancing in Distributed Matrix-Vector Multiplication.
Proc. ACM Meas. Anal. Comput. Syst.
Ankur Mallick, Malhar Chaudhari, Utsav Sheth, Ganesh Palanikumar, Gauri Joshi
2018 J jnl
Rateless Codes for Near-Perfect Load Balancing in Distributed Matrix-Vector Multiplication.
CoRR
Ankur Mallick, Malhar Chaudhari, Gauri Joshi
2016 J jnl
Bandlimited Field Reconstruction from Samples Obtained at Unknown Random Locations on a Grid.
CoRR
Ankur Mallick, Animesh Kumar
2016 Misc conf
Bandlimited field reconstruction from samples obtained on a discrete grid with unknown random locations.
ICASSP
Ankur Mallick, Animesh Kumar