Ax Srivatsa Kundurthy, Clara Na, Colton Moraine, Anoushka Mohta, Case Winter, George Fang, John Ling, Emma Strubell, Zach Kirshner 6/1/2026

BlueFin: Benchmarking LLM Agents on Financial Spreadsheets

Benchmark evaluating LLM agents on financial spreadsheet tasks including synthesis, manipulation, and comprehension in professional finance domain.

Ax Sina Alemohammad, Li Chen, Richard G. Baraniuk, Zhangyang Wang 6/1/2026

Not All Synthetic Data Is Yours to Learn From

Research on self-training language models with synthetic data, identifying when models can improve from self-generated text through latent capability resurfacing.

Ax Matthew Dowling, Hyungju Jeon, Cristina Savin, Il Memming Park 6/1/2026

Memory by Design: Probabilistic Sequence Layers

Probabilistic sequence layer design using Bayesian filtering for efficient recurrent neural networks with uncertainty tracking.

Ax Zheyu Zhang, Shuo Yang, Gjergji Kasneci 6/1/2026

Consolidating Rewarded Perturbations for LLM Post-Training

Proposes consolidating rewarded perturbations for LLM post-training by sampling Gaussian perturbations and ensembling top-K specialists as alternative to gradient descent methods.

Ax Arnas Uselis, Darina Koishigarina, Seong Joon Oh 6/1/2026

How can embedding models bind concepts?

Studies how vision-language embedding models like CLIP represent concept binding in multi-object scenes, showing limitations in cross-modal retrieval.

Ax Anna Vettoruzzo, Mohamed-Rafik Bouguelia, Joaquin Vanschoren, Thorsteinn R\"ognvaldsson, KC Santosh 6/1/2026

Advances and Challenges in Meta-Learning: A Technical Review

Technical review of meta-learning methods enabling systems to adapt quickly to new tasks with limited data, covering state-of-the-art approaches and applications.

Ax Shijie Wang, Jiani Huang, Zhikai Chen, Yu Song, Wenzhuo Tang, Haitao Mao, Wenqi Fan, Hui Liu, Xiaorui Liu, Dawei Yin, Qing Li 6/1/2026

Graph Machine Learning in the Era of Large Language Models (LLMs)

Survey of graph machine learning integration with LLMs, covering GNN architectures, applications in knowledge graphs, molecules, and emerging LLM-GNN combinations.

Ax Ferhat Erata, Orr Paradise, Thanos Typaldos, Timos Antonopoulos, ThanhVu Nguyen, Shafi Goldwasser, Ruzica Piskac 6/1/2026

Learning Randomized Reductions

Bitween: Automated learning system for discovering randomized self-reductions that previously required expert manual derivation.