5 papers
Forward Pass Domain Adaptation (Without Cross-Layer Backpropagation)
Rivaan Patil, Simon Dennis, Hao Guo +1
Forward-Pass-Only MLP training (FPO) adapts large language models without a backward pass through the model body, achieving 2.7--3.2x the throughput of standard fine-tuning at ~40%…
MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents
Zeying Hao, Hao Guo, Mengtao Xu +5
Online shoppers increasingly turn to AI shopping assistants, using images and multi-turn dialogue to express and refine product needs that are difficult to articulate in text alone…
Procedural Knowledge Is Not Low-Rank: Why LoRA Fails to Internalize Multi-Step Procedures
Simon Dennis, Kevin Shabahang, Hao Guo +1
Parameter-efficient fine-tuning methods like LoRA have become the default for adapting large language models, succeeding across instruction following, style transfer, and factual a…
Simulating Teams with LLM Agents: Interactive 2D Environments for Studying Human-AI Dynamics
Mohammed Almutairi, Charles Chiang, Haoze Guo +9
Enabling users to create their own simulations offers a powerful way to study team dynamics and performance. We introduce VirTLab, a system that allows researchers and practitioner…
VirtLab: An AI-Powered System for Flexible, Customizable, and Large-scale Team Simulations
Mohammed Almutairi, Charles Chiang, Haoze Guo +9
Simulating how team members collaborate within complex environments using Agentic AI is a promising approach to explore hypotheses grounded in social science theories and study tea…