Publications

32 results at ICML 2026

ProbeLLM: Automating Principled Diagnosis of LLM Failures
- - Yue Huang
  - Zhengzhe Jiang
  - et al.
- 2026
- ICML 2026
Conference paper
How Can Mamba Learn In Context with Outliers and Generalize Provably?
- - Hongkang Li
  - Songtao Lu
  - et al.
- 2026
- ICML 2026
Conference paper
FlowState: Sampling-Rate-Equivariant Time-Series Forecasting
- - Lars Graf
  - Thomas Bohnstingl
  - et al.
- 2026
- ICML 2026
Conference paper
Transformer Circuits Can Realize Clustering Algorithms
- - Kenneth Clarkson
  - Lior Horesh
  - et al.
- 2026
- ICML 2026
Conference paper
Static Benchmarks Are Broken: The Case for Dynamic Evaluation of LLMs
- - Farhan Ahmed
  - Chad Deluca
- 2026
- ICML 2026
Workshop paper
HGR-TabE: Universal Tabular Embeddings via Maximal Correlation Alignment
- - Niharika DSouza
  - Liane Vogel
  - et al.
- 2026
- ICML 2026
Workshop paper
Computational Safety for Generative AI: A Hypothesis Testing Perspective
- - Pin-Yu Chen
- 2026
- ICML 2026
Workshop paper
Local Causal Attribution of Chain-of-Thought Reasoning
- - Dennis Wei
  - Yannis Belkhiter
  - et al.
- 2026
- ICML 2026
Workshop paper
Step-Tagging Early-Stopping: Toward controlling the generation of Language Reasoning Models through black-box step monitoring
- - Yannis Belkhiter
  - Seshu Tirupathi
  - et al.
- 2026
- ICML 2026
Workshop paper
Scalable Circuit Learning for Interpreting Large Language Models
- - Naiyu Yin
  - Dennis Wei
  - et al.
- 2026
- ICML 2026
Workshop paper