Publications

• [arXiv] ImageNet-Think-250K: A Large-Scale Synthetic Dataset for Multimodal Reasoning for Vision Language Models
  Krishna Teja Chitty-Venkata, Murali Emani
  [Paper] [HuggingFace]


• [arXiv] PreLoRA: Hybrid Pre-training of Vision Transformers with Full Training and Low-Rank Adapters
  Krishu K Thapa, Reet Barik, Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath
  [Paper]


• [arXiv] PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
  Krishna Teja Chitty-Venkata, Jie Ye, Xian-He Sun, Anthony Kougkas, Murali Emani, Venkatram Vishwanath, Bogdan Nicolae
  [Paper]


• [arXiv] LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference
  Krishna Teja Chitty-Venkata, Sandeep Madireddy, Murali Emani, Venkatram Vishwanath
  [Paper]


• [arXiv] BaKlaVa -- Budgeted Allocation of KV cache for Long-context Inference
  Ahmed Burak Gulhan, Krishna Teja Chitty-Venkata, Murali Emani, Mahmut Kandemir, Venkatram Vishwanath
  [Paper]


• [Bivision at ICCV 2025] MoPEQ: Mixture of Mixed Precision Quantized Experts
  Krishna Teja Chitty-Venkata, Jie Ye, Murali Emani
  Binary and Extreme Quantization for Computer Vision Workshop at ICCV 2025
  [Paper]


• [ICIP 2025] Langvision-Lora-Nas: Neural Architecture Search for Variable Lora Rank In Vision Language Models
  Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath
  2025 IEEE International Conference on Image Processing
  [Paper]


• [PMBS at SC 2025] MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
  Krishna Teja Chitty-Venkata, Sylvia Howland, Golara Azar, Daria Soboleva, Natalia Vassilieva, Siddhisanket Raskar, Murali Emani, Venkatram Vishwanath
  2025 IEEE/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High-Performance Computer Systems (PMBS)
  [Paper]


• [PMBS at SC 2024] LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators
  Krishna Teja Chitty-Venkata, Siddhisanket Raskar, Bharat Kale, Farah Ferdaus, Aditya Tanikanti, Ken Raffenetti, Valerie Taylor, Murali Emani, Venkatram Vishwanath
  2024 IEEE/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High-Performance Computer Systems (PMBS)
  [Paper] [Code]


• [MDPI AI 2024] ConVision Benchmark: A Contemporary Framework to Benchmark CNN and ViT Models
  Shreyas Bangalore Vijayakumar, Krishna Teja Chitty-Venkata, Kanishk Arya, Arun K Somani
  MDPI AI Journal
  [Paper] [Code]


• [EuroPar 2024] WActiGrad: Structured Pruning for Efficient Finetuning and Inference of Large Language Models on AI Accelerators
  Krishna Teja Chitty-Venkata, Varuni Katti Sastry, Murali Emani, Venkatram Vishwanath, Sanjif Shanmugavelu, Sylvia Howland
  European Conference on Parallel Processing
  [Paper]


• [IEEE Access 2023] Differentiable Neural Architecture, Mixed Precision and Accelerator Co-search
  Krishna Teja Chitty-Venkata, Yiming Bian, Murali Emani, Venkatram Vishwanath, Arun K Somani
  IEEE Access Journal
  [Paper]


• [JSA 2023] A Survey of Techniques for Optimizing Transformer Inference
  Krishna Teja Chitty-Venkata, Yiming Bian, Murali Emani, Venkatram Vishwanath, Arun K Somani
  Journal of Systems Architecture Journal
  [Paper]


• [IEEE Access 2023] Neural Architecture Search Benchmarks: Insights and Survey
  Krishna Teja Chitty-Venkata, Yiming Bian, Murali Emani, Venkatram Vishwanath, Arun K Somani
  IEEE Access Journal
  [Paper] [GitHub]


• [ACM CSUR 2022] Neural Architecture Search Survey: A Hardware Perspective
  Krishna Teja Chitty-Venkata, Arun K Somani
  ACM Computing Surveys
  [Paper]


• [IEEE Access 2022] Neural Architecture Search for Transformers: A Survey
  Krishna Teja Chitty-Venkata, Arun K Somani
  IEEE Access Journal
  [Paper]


• [ACM HPDC 2022] Efficient Design Space Exploration for Sparse Mixed Precision Neural Architectures
  Krishna Teja Chitty-Venkata, Arun K Somani
  31st International Symposium on High-Performance Parallel and Distributed Computing (HPDC)
  [Paper]


• [IEEE ICIP 2021] Searching Architecture and Precision for U-net based Image Restoration Tasks
  Krishna Teja Chitty-Venkata, Arun K Somani
  2021 IEEE International Conference on Image Processing (ICIP)
  [Paper]


• [IEEE ASAP 2021] Array-aware Neural Architecture Search
  Krishna Teja Chitty-Venkata, Arun K Somani
  2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP)
  [Paper]


• [IEEE HPCC/DSS 2021] Calibration Data-based CNN Filter Pruning for Efficient Layer Fusion
  Krishna Teja Chitty-Venkata, Arun K Somani
  2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP)
  [Paper]


• [IEEE PRDC 2020] Model Compression on Faulty Array-based Neural Network Accelerator
  Krishna Teja Chitty-Venkata, Arun K Somani
  2020 IEEE 25th Pacific Rim International Symposium on Dependable Computing (PRDC)
  [Paper]


• [IEEE ASAP 2020] Array Aware Training/Pruning: Methods for Efficient Forward Propagation on Array-based Neural Network Accelerators
  Krishna Teja Chitty-Venkata, Arun K Somani
  2020 IEEE 31st International Conference on Application-specific Systems, Architectures and Processors (ASAP)
  [Paper]


• [IEEE ASAP 2019] Impact of Structural Faults on Neural Network Performance
  Krishna Teja Chitty-Venkata, Arun K Somani
  2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP)
  [Paper]