From the 1 of 4 linked papers with an AI index.
4 papers
Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization
Zhiqi Gao, Albert Ge, Alexander Berenbeim +2
The paper investigates why text‑to‑optimization models struggle to correctly ground problem data, introduces a benchmark (Text2Opt‑Bench) to study this, and proposes a binding‑focu…
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
Gabriel Orlanski, Devjeet Roy, Alexander Yun +7
Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily…
R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training
Albert Ge, Tzu-Heng Huang, John Cooper +7
Data mixing strategies have successfully reduced the costs involved in training language models. While promising, such methods suffer from two flaws. First, they rely on predetermi…
Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition
Zheyang Xiong, Ziyang Cai, John Cooper +11
Large Language Models (LLMs) have demonstrated remarkable in-context learning (ICL) capabilities. In this study, we explore a surprising phenomenon related to ICL: LLMs can perform…