Hamid Palangi

GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning

Watch and Learn: Learning to Use Computers from Online Videos

LLM-based Multi-Agent Blackboard System for Information Discovery in Data Science

VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation

HEART: Emotionally-driven test-time scaling of Language Models

Judging with Confidence: Calibrating Autoraters to Preference Distributions

InfSplign: Inference-Time Spatial Alignment of Text-to-Image Diffusion Models

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence

AI Debate Aids Assessment of Controversial Claims

Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents

MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark

Exploring Group and Symmetry Principles in Large Language Models