Research Assistant, UC Berkeley Data Innovation & AI Lab
📍 shreyas21447@gmail.com / f20200714@goa.bits-pilani.ac.in
🔗 LinkedIn | 💻 GitHub | 📄 CV
I'm a curiosity-driven researcher exploring how data and training shape large language models—and how the brain represents language. I graduated from BITS Pilani (B.E. ECE + M.Sc. Mathematics, minor in Data Science) and now work as a Research Assistant at UC Berkeley's Data Innovation & AI Lab with Dr. Abhishek Nagaraj.
At Berkeley, I study the impact of book datasets on LLM performance using a large-scale "name-cloze" evaluation across 12k+ titles.
I completed my Masters Thesis at Harvard's Kreiman Lab, under the supervision of Dr. Gabriel Kreiman. I analyzed intracranial iEEG during language tasks, built decoders for grammatical/semantic features, and co-designed a real-time memory-retrieval system with frontier LLMs.
Throughout my college journey, I worked with Prof. Snehanshu Saha, Prof. Amalin Prince, and Prof. Yuvaraj Rajamanickam at NTU Singapore on EEG-based emotion recognition and vision-based activity detection. I have also worked with Prof. Ganapathy Krishnamurthi at IIT Madras on implementing object detection and instance segmentation architectures.
Research interests: LLM evaluation, data selection & gradient-informed training, neuro+ML for language (iEEG), efficient training/benchmarking at scale, and vision/affective computing. Selected recognition: fully funded participant, MIT's CBMM "Science of Intelligence" course (Aug 2025).
In my free time, you'll likely find me playing the violin or engaging in other music-related activities. I also enjoy playing chess and was an active member of the Institute chess team.
Double Major: B.E. Electronics and Communication Engineering & M.Sc. Mathematics; Minor in Data Science
📅 Aug 2020 - Aug 2025
Thesis: Beyond modalities: robust neural representation of language in the brain
12th Grade: 94.6% (March 2020)
10th Grade: 93.8% (March 2018)
S. Krishnan, L. Murugan, A. Hassouneh, Y. Rajamanickam, A. Prince, T. Thiyagasundaram, M. Murugappan (2024). Emotion Recognition using ResNet Feature Extraction on EEG Signals. IET (UK), Book Chapter.
S. Krishnan (2025). Vision Transformer for Hand-Raise Recognition in Remote Learning (93.82% ± 2.16%, 5-fold CV). IEEE CIACON 2025.
Status: Accepted
S. Krishnan, A. Das (2025). Harnessing Chaos and Causality in Neural Networks: A Pruning Strategy for Enhanced Performance and Explainability. IJSCAI 2025.
Status: Accepted
S. Krishnan, A. Thamma (2025). Human-Prior Correction: Post-hoc Calibration that Aligns Vision Models with Human Uncertainty. ICCV - HiCV Workshop 2025.
Status: Accepted | Under Review: ICLR 2026
S. Krishnan, A. Thamma (2025). Plan–Check–Revise: A Token-Paritized Two-Agent Protocol for Verifiable Math Reasoning. Submitted to NeurIPS 2025 Workshop MATHAI.
Status: Under Review
S. Krishnan, A. Thamma (2025). Hallucination Guardrails for VLM Instructions: Sensor–Language Conflict Detection for Safer Human–Robot Interaction. Submitted to IEEE IROS 2025 Workshop HEAI.
Status: Under Review
D. Mayo, C. Zhang, S. Krishnan, A. Shaw, B. Katz, A. Barbu, B. Cheung (supervision). Look But Don't Touch: Gradient Informed Selection Training. Under Review ICLR 2026.
Status: Under Review
Ongoing Research with Dr. Abhishek Nagaraj on how access to pirated books (Books3 dataset) shapes large language model performance.
Status: Ongoing Research
Selected Participant - Science of Intelligence Course | Woods Hole, MA | Aug 2025
Selected (fully funded) among ~30 global graduate students/postdocs worldwide for a deep-dive course on the science of intelligence.
Nanyang Technological University | Singapore | 2024
Admitted to the PhD program with offer and service bond.
Carnegie Mellon University | Pittsburgh, USA | 2024
Admitted to the Master's program.
Research Assistant | Berkeley, California, USA | Aug 2025 – Present
Research Intern (Neuro-AI) | Boston, Massachusetts, USA | Jan 2024 – Aug 2025
Research Intern (EEG/ML & Vision) | Singapore | Oct 2022 – May 2024
AI Engineer Intern (LLM/RAG) | Bangalore, India | May 2024 – Aug 2024
Research Intern (Model Compression) | Bangalore, India | May 2023 – Present
Research Intern (Detection/Segmentation) | Chennai, India | Jun 2023 – Aug 2023
Python, MATLAB, HTML, CSS, JavaScript, C, C++
Pandas, NumPy, TensorFlow, Scikit-Learn, PyTorch, OpenCV
Robot Operating System (ROS), Gazebo
Adobe Photoshop, Adobe Premiere Pro
Python, TensorFlow, NumPy, Scikit-Learn
Developed a 1-hidden layer neural network model that adapts to the most suitable activation function according to the dataset.
Python
Worked on NLP using a mixup strategy on the TREC dataset and Bayesian Inference via MCMC for sampling MLP weights.
Python, Scikit-Learn, Pandas
Feature analysis, correlation-based feature selection, and classification of ECG signal data for predicting Arrhythmia.
Python, Qiskit, NumPy
Implemented a half adder circuit using the open source software development kit Qiskit.
Robot Operating System (ROS), Gazebo
Developed obstacle detection, PID controller, and path planning stack using ROS in Python, implementing the Dijkstra algorithm for path planning.
Machine Learning Foundations of Data Science (ongoing), Applied Statistical Methods, Statistical Inference and Applications, Optimization
Numerical Analysis, Probability and Statistics, Digital Signal Processing, Linear Algebra, Multivariate Calculus, Discrete Mathematics, Introduction To Functional Analysis, Ordinary Differential Equations, Control Systems
Machine Learning (BITS-F464), Fostered student input and communicated announcements. Oversaw course-related announcements and facilitating coordination between faculty and students - Aug-Dec 2023