activity
20242026
collaborators

8 papers

cs.AI2026

Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input Perturbations

Zizhao Hu, Nathan Elijah Segura, Mohammad Rostami +1

Human input reaches language models by typing or speaking, and each channel leaves a distinct signature: orthographic noise for keyboards; for voice, disfluency from conventional t…

cs.CV2026

In-Context Collapse in Vision-Language Models and How to Mitigate it?

Mohammad Rostami

Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely assumed to improve as more demon…

cs.AI2026

Can You Trust the Confidence? ConfBench for Vision-Language Models on Document Extraction

Priyashree Roy, Sujitha Martin, Mohammad Rostami +6

Intelligent document processing (IDP) with vision-language models (VLMs) hinges on confidence scores trustworthy enough to route extractions between automation and human review. Ex…

cs.LG2026

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion

Zizhao Hu, Ameya Godbole, Johnny Tian-Zheng Wei +3

Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full…

cs.AI2026

Expert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM

Zizhao Hu, Mohammad Rostami, Jesse Thomason

Persona prompting can steer LLM generation towards a domain-specific tone and pattern. This behavior enables use cases in multi-agent systems where diverse interactions are crucial…

cs.LG2025

Multi-modal Synthetic Data Training and Model Collapse: Insights from VLMs and Diffusion Models

Zizhao Hu, Mohammad Rostami, Jesse Thomason

Recent research has highlighted the risk of generative model collapse, where performance progressively degrades when continually trained on self-generated data. However, existing e…