Berkeley, CA · available May 2026

Parham builds systems for autonomy

EECS & MEng at UC Berkeley. Research on safe imitation learning, multi-agent coordination, and LLM reasoning. Currently shipping computer-vision pipelines at IntuigenceAI.

↓ Resume Projects Publications About GitHub ↗
Portrait of Parham Sharafoleslami
Now Decentralized fleet coordination for airport ground ops · MEng thesis on safe imitation learning for race-car controllers

Selected work

all 20 →
Robotics · 2025

MPC for UR5e Robotic Arm — Warehouse Sorting

Model Predictive Control for a UR5e manipulator with analytical DH kinematics and real-time obstacle avoidance. Picks and stacks colored cubes around obstacles using a receding-horizon CasADi/IPOPT solver, replanning every timestep in MuJoCo — deployed on real hardware.

PythonMuJoCoCasADiOptimal Control
Read case study →
Robotics · 1 min read

Decentralized Fleet Coordination for Airport Ground Operations

Multi-agent coverage control for airport ground vehicles using Buffered Voronoi Cells, Lloyd's algorithm, and game-theoretic demand response — zero collisions across all test scenarios.

PythonMulti-Agent SystemsOptimal ControlGame Theory
Machine Learning · 3 min read

Deep Learning from Scratch

The full arc: backpropagation in raw NumPy, CNNs with BatchNorm and Dropout trained to 78% on CIFAR-10, multi-head self-attention for text summarization, and a Masked Autoencoder that reconstructs images from 25% of their patches — then transfers those features to downstream tasks.

PythonNumPyPyTorchCIFAR-10
Machine Learning · 3 min read

Classical ML from Scratch

Two learning paradigms built from NumPy up — tree-based spam classification (decision tree, Random Forest, AdaBoost) and SVD/ALS matrix factorization for movie recommendations. No frameworks; matched scikit-learn on both.

PythonNumPySciPyMachine Learning
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
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

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

Working with

Python 15 NumPy 9 PyTorch 4 Computer Vision 4 Optimal Control 2 Game Theory 2 SciPy 2 scikit-image 2 RISC-V 2 Information Theory 2 Matplotlib 2 Java 2 MuJoCo 1 CasADi 1 Multi-Agent Systems 1 CIFAR-10 1