Stanford linguists at ICLR 2026

The Fourteenth International Conference on Learning Representations (ICLR 2026) took place April 23-27, 2026 in Rio de Janeiro, Brazil. It featured work from several Stanford linguists:

• Lakshya Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael Ryan, Meng Jiang, Chris Potts, Koushik Sen, Alex Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab: "GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning" (poster)
• Martijn Bartelds, Ananjan Nandi, Moussa Koulako Bala Doumbouya, Dan Jurafsky, Tatsunori Hashimoto, Karen Livescu: "CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition"
• Myra Cheng, Sunny Yu, Cinoo Lee, Pranav Khadpe, Lujain Ibrahim, Dan Jurafsky: "ELEPHANT: Measuring and understanding social sycophancy in LLMs" (poster)
• Satchel Grant, Simon Jerome Han, Alexa Tartaglini, Chris Potts: "Addressing divergent representations from causal interventions on neural networks" (poster)
• Weiqiao Han, Chenlin Meng, Chris Manning, Stefano Ermon: "DistillKac: Few-Step Image Generation via Damped Wave Equations" (poster)
• Ethan Hsu, Hong Meng Yam, Ines Bouissou, Aaron John, Raj Thota, Josh Koe, Vivek Putta, G Dharesan, Alexander Spangher, Shikhar Murty, Tenghao Huang, Chris Manning: "WebDS: An End-to-End Benchmark for Web-based Data Science"
• Moussa Koulako Bala Doumbouya, Dan Jurafsky, Chris Manning: "Tversky Neural Networks: Psychologically Plausible Deep Learning with Differentiable Tversky Similarity" (poster)
• Chen Shani, Liron Soffer, Dan Jurafsky, Yann LeCun, Ravid Shwartz-Ziv: "From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning" (poster)