activity
20242026
collaborators

7 papers

cs.CL2026

PrefDisco: Benchmarking Proactive Personalized Reasoning

Shuyue Stella Li, Avinandan Bose, Faeze Brahman +4

Current large language model (LLM) development treats task-solving and preference-alignment as separate challenges, optimizing first for objective correctness, then for alignment t…

cs.CL2026

Cold-Start Personalization via Training-Free Priors from Structured World Models

Avinandan Bose, Shuyue Stella Li, Faeze Brahman +6

Cold-start personalization requires inferring user preferences through interaction when no user-specific historical data is available. The core challenge is a routing problem: each…

cs.CR2025

DoomArena: A framework for Testing AI Agents Against Evolving Security Threats

Leo Boisvert, Mihir Bansal, Chandra Kiran Reddy Evuru +9

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic ag…

cs.LG2025

LoRe: Personalizing LLMs via Low-Rank Reward Modeling

Avinandan Bose, Zhihan Xiong, Yuejie Chi +3

Personalizing large language models (LLMs) to accommodate diverse user preferences is essential for enhancing alignment and user satisfaction. Traditional reinforcement learning fr…

cs.LG2025

Initializing Services in Interactive ML Systems for Diverse Users

Avinandan Bose, Mihaela Curmei, Daniel L. Jiang +4

This paper investigates ML systems serving a group of users, with multiple models/services, each aimed at specializing to a sub-group of users. We consider settings where upon depl…

cs.LG2025

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning

Avinandan Bose, Laurent Lessard, Maryam Fazel +1

The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustn…