Picture for Izzeddin Gur

Izzeddin Gur

Fiona

Geometric-Averaged Preference Optimization for Soft Preference Labels

Add code
Sep 10, 2024
Viaarxiv icon

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

Add code
Aug 14, 2024
Viaarxiv icon

Scaling Exponents Across Parameterizations and Optimizers

Add code
Jul 08, 2024
Viaarxiv icon

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Add code
Dec 22, 2023
Viaarxiv icon

Language Model Agents Suffer from Compositional Generalization in Web Automation

Add code
Nov 30, 2023
Viaarxiv icon

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

Add code
Nov 15, 2023
Viaarxiv icon

Small-scale proxies for large-scale Transformer training instabilities

Add code
Sep 25, 2023
Viaarxiv icon

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

Add code
Jul 24, 2023
Viaarxiv icon

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

Add code
May 19, 2023
Viaarxiv icon

Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration

Add code
Nov 29, 2022
Viaarxiv icon