● Berkeley, CA

Parham — engineer at UC Berkeley. autonomy, controls, machine learning.

↓ Resume Projects Publications About GitHub ↗

Working with

Python 19 NumPy 12 PyTorch 7 Computer Vision 5 Machine Learning 3 Transformers 2 OpenCV 2 scikit-image 2 Scikit-learn 2 RISC-V 2 Information Theory 2 Matplotlib 2 Java 2 CLIP 1 GPT-2 1 Neural Rendering 1

Featured projects

all 25 →
Natural Language Processing · 5 min read

Modern NLP — From Statistical MT to Multimodal Foundation Models

Four paradigm shifts in one semester: IBM Model 1 → attention-based NMT → transformer parsing → LLM fine-tuning → CLIP multimodal retrieval with pragmatic reasoning. Each technique subsumes and extends the previous.

PythonPyTorchTransformersCLIP +1
Computer Vision · 3 min read

Neural Radiance Fields (NeRF)

Training an MLP to represent a 3D scene as a continuous function from (x, y, z, θ, φ) to (RGB, density). Volume rendering turns the field back into images; the field itself is the 3D model.

PythonPyTorchNeural Rendering3D Vision
Deep Learning · 1 min read

Vision Transformer + Masked Autoencoder

ViT classifier achieving 73.5% on CIFAR-10, then self-supervised MAE pretraining boosts finetuned accuracy to 76.8%. Full implementation of patchify, attention pooling, and mask reconstruction.

PythonPyTorchVision TransformersSelf-Supervised Learning
Computer Vision · 3 min read

Fun With Diffusion Models

Sampling from DeepFloyd IF — CFG, SDEdit, inpainting, visual anagrams. Then training a time- and class-conditioned U-Net from scratch on MNIST to learn the diffusion process end-to-end.

PythonPyTorchDiffusion ModelsGenerative AI
Deep Learning · 1 min read

Transformer for News Summarization

Self-attention, multi-head attention, and encoder-decoder architecture implemented from scratch. Trained on CNN/DailyMail achieving 35.1 ROUGE-L, outperforming LSTM baseline by 60%.

PythonPyTorchTransformersNLP
Deep Learning · 1 min read

RNN Sequence Modeling

Recurrent networks from scratch — forward pass, backpropagation through time, and gradient flow analysis. Vectorized NumPy implementation validated to 5e-5 tolerance.

PythonNumPyPyTorchSequence Models

Selected publications

all →
Preprint · 2026 · advisor

Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering

Nathan Mao , Varun Kaushik , Shreya Shivkumar , Parham Sharafoleslami , Kevin Zhu , Sunishchal Dev

FalseCite — a curated dataset of 82k false claims paired with fabricated citations — reveals that LLMs hallucinate more readily when misleading references are present, especially in smaller models like GPT-4o-mini. Hidden-state clustering exposes a distinctive 'horn-like' geometry across hallucinating and non-hallucinating activations.

arXiv ↗ PDF ↗ #hallucination#benchmark#interpretability
Preprint · 2025

COMPASS: Context-Modulated PID Attention Steering System for Hallucination Mitigation

Kenji Sahay , Snigdha Pandya , Rohan Nagale , Anna Lin , Shikhar Shiromani , Parham Sharaf , Kevin Zhu , Sunishchal Dev

A decoding-time intervention that dynamically steers attention toward retrieved context using a PID controller driven by a per-head Context Reliance Score. No retraining, no multi-pass decoding — just interpretable, single-stream control of evidence grounding. Reduces hallucinations by 2.8–5.8% absolute across HotpotQA, XSum, HaluEval, and RAGTruth.

arXiv ↗ PDF ↗ #hallucination#decoding#attention#interpretability
NeurIPS 2025 · 2025 · advisor

Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis

Abhishek More , Anthony Zhang , Nicole Bonilla , Ashvik Vivekan , Kevin Zhu , Parham Sharafoleslami , Maheep Chaudhary

EDTR estimates LLM confidence by treating each chain-of-thought as a vector in semantic space and analyzing the geometry of the reasoning distribution. Combined with Dirichlet-based uncertainty quantification, it achieves 41% better calibration than competing methods and perfect accuracy on AIME.

arXiv ↗ PDF ↗ #calibration#chain-of-thought#uncertainty