Izzeddin Gur

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

A2Perf: Real-World Autonomous Agents Benchmark

Small-scale proxies for large-scale Transformer training instabilities

A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

Language Model Agents Suffer from Compositional Decision Making

Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability

Geometric-Averaged Preference Optimization for Soft Preference Labels

Multimodal Web Navigation with Instruction-Finetuned Foundation Models