activity
20172026
most citedPruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

3 citations · 6 across the 6 of their papers we have counts for

collaborators

7 papers

cs.LG2026

When Does Longer Reasoning Help? Predicting Mathematical Reasoning Through Discovery and Execution

Adib Hasan, Lay Jain, Thanic Nur Samin

Test-time compute can improve mathematical reasoning, but can short-budget runs predict how mathematical reasoning scales with additional compute? We introduce a Discovery--Executi…

cs.AI2026

AutoFyn Technical Report: Non-Parametric Expert Iteration for Long-Horizon Agents

Adib Hasan, Daniel Schaffield, Akashnil Dutta +1

We introduce AutoFyn, an agent harness inspired by the Expert Iteration algorithm, adapting a frozen model across many rounds by updating persistent state from verified reward sign…

cs.CL2026

Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memes

Muhammad Jawad Chowdhury, Adiba Hasan, Ishrak Hossain +2

Memes have turned out to be a powerful tool through which individuals share their ideas concerning contemporary social and political problems. Their anonymity, as well as their abi…

cs.LG2025

VITA: Variational Pretraining of Transformers for Climate-Robust Crop Yield Forecasting

Adib Hasan, Mardavij Roozbehani, Munther Dahleh

Accurate crop yield forecasting is essential for global food security. However, current AI models systematically underperform when yields deviate from historical trends. We attribu…

cs.CV2024★ 1 cited

WeatherFormer: A Pretrained Encoder Model for Learning Robust Weather Representations from Small Datasets

Adib Hasan, Mardavij Roozbehani, Munther Dahleh

This paper introduces WeatherFormer, a transformer encoder-based model designed to learn robust weather features from minimal observations. It addresses the challenge of modeling c…

cs.LG2024★ 3 cited

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

Adib Hasan, Ileana Rugina, Alex Wang

This paper investigates the impact of model compression on the way Large Language Models (LLMs) process prompts, particularly concerning jailbreak resistance. We show that moderate…

cs.DS2017★ 2 cited

Graphettes: Constant-time determination of graphlet and orbit identity including (possibly disconnected) graphlets up to size 8

Adib Hassan, Po-Chien Chung, Wayne B. Hayes

Graphlets are small connected induced subgraphs of a larger graph . Graphlets are now commonly used to quantify local and global topology of networks in the field. Methods exist…