works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

cs.LG2026

Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion

Fengzhuo Zhang, Zhuoran Yang, Dirk Bergemann

The paper studies when users of large language models should use expensive supervised fine-tuning versus lightweight in‑context learning, considering how other users' choices creat…

cs.CV2026

MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs

Hantao Zhang, Jinru Sui, Ed Li +2

Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coheren…

cs.LG2026

COOPA: A Modular LLM Agent Architecture for Operations Research Problems

Chuanhao Li, Xiaoan Xu, Dirk Bergemann +3

Operations Research (OR) provides a rigorous framework for high-stakes decision-making, but effective OR modeling requires substantial domain knowledge, mathematical abstraction, a…

cs.LG2026

Why Muon Outperforms Adam: A Curvature Perspective

Shuche Wang, Fengzhuo Zhang, Jiaxiang Li +2

Muon improves training efficiency over Adam in large language-model training by about two times, but the local geometric source of this advantage remains unclear. Our work takes a…

cs.GT2026

Training Language Models for Bilateral Trade with Private Information

Dirk Bergemann, Soheil Ghili, Xinyang Hu +2

Bilateral bargaining under incomplete information provides a controlled testbed for evaluating large language model (LLM) agent capabilities. Bilateral trade demands individual rat…

econ.TH2025

Marketplace Operators Can Induce Competitive Pricing

Tiffany Ding, Dominique Perrault-Joncas, Orit Ronen +4

As e-commerce marketplaces continue to grow in popularity, it has become increasingly important to understand the role and impact of marketplace operators on competition and social…