Khawaja Abaid Ullah.

How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans

Hasan Mahmud, Khawaja Abaid Ullah, Mohammad Javad Khojasteh, Jamison Heard, Prabu David

Evaluated social-judgment reliability and human-LLM alignment across 34 large language models and 198 human participants using theory-grounded persona ratings, including controlled analyses of gender presentation.

@misc{mahmud2026socialattraction,
  title = {How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans},
  author = {Hasan Mahmud and Khawaja Abaid Ullah and Mohammad Javad Khojasteh and Jamison Heard and Prabu David},
  year = {2026},
  eprint = {2608.09717},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url = {https://arxiv.org/abs/2608.09717}
}

Reversing the Incentive to Distill: A Review of Test-Time Antidistillation Defenses for Classification

Khawaja Abaid Ullah, Mohammad Javad Khojasteh

Built a unified matched-cost benchmark and a method-agnostic top-1-preservation wrapper; directed perturbations drove distilled students 34.5 pp (CIFAR-10) and 47.7 pp (CIFAR-100) below the hard-label baseline. Reimplemented prior test-time defenses under a common threat model and matched-cost evaluation protocol to isolate which perturbation mechanisms genuinely suppress student learning.

@unpublished{ullah2026reversing,
  title = {Reversing the Incentive to Distill: A Review of Test-Time Antidistillation Defenses for Classification},
  author = {Khawaja Abaid Ullah and Mohammad Javad Khojasteh},
  year = {2026},
  note = {Under review}
}

ADS-C: Antidistillation Sampling for Classification

Khawaja Abaid Ullah, Mohammad Javad Khojasteh

Proposed a margin-aware inference-time defense that preserves every served top-1 prediction while reducing distilled-student accuracy by 29.6 pp on CIFAR-10, 17.4 pp on CIFAR-100, and 13.3 pp on Tiny-ImageNet. Released with an open-source PyTorch evaluation harness across all three benchmarks and multiple student architectures.

@misc{ullah2026adsc,
  title = {ADS-C: Antidistillation Sampling for Classification},
  author = {Khawaja Abaid Ullah and Mohammad Javad Khojasteh},
  year = {2026},
  eprint = {2607.15467},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2607.15467}
}

ADS-C — Antidistillation Sampling for Classification

Open-source PyTorch implementation and reproducible evaluation harness for ADS-C, preserving every served top-1 prediction while reducing distilled-student accuracy by 29.6 pp on CIFAR-10, 17.4 pp on CIFAR-100, and 13.3 pp on Tiny-ImageNet across multiple student architectures.

Teras

Created a Keras 3-based tabular deep-learning library supporting JAX, PyTorch, and TensorFlow backends. Implemented state-of-the-art research architectures (SAINT, TabNet, TabTransformer, FT-Transformer, CTGAN, TVAE, GAIN, PCGAIN) for classification, regression, data imputation, and synthetic-data generation.

Fontus — Multi-Agent RL for Aerial UAV Recharging

Built a custom PettingZoo Parallel multi-agent environment with vectorized NumPy dynamics, energy-aware transitions, and proximity-triggered charging; trained parameter-shared IPPO/PPO policies with PyTorch and Ray RLlib. Established an analytical no-charge baseline and diagnosed a reward-hacking ‘lazy agent’ local optimum.

Keras 3 (Official Contributions)

Contributed Beta and Binomial random-sampling functionality (keras.random.beta, keras.random.binomial) and multi-backend consistency fixes to the official Keras 3 API across JAX, PyTorch, and TensorFlow.

codriver (260M Distilled Code LLM)

Inspired by GitHub Copilot, built a custom 260M-parameter contextual code-generation model based on Google DeepMind’s Gemma LLMs. Ported Gemma 2 from Flax Linen to the NNX API and applied staged knowledge distillation—first using Gemma 2 2B on text (FineWebEdu) and then CodeGemma 2B on fill-in-the-middle code (CodeContests) across 8× H100 GPUs.

micrograd_c

Implemented Andrej Karpathy’s micrograd from scratch in pure C: a scalar reverse-mode autograd engine and neural-network library exposing a PyTorch-like API.