ICML 2025 Workshop TAIG Submissions

Measuring What Matters: A Framework for Evaluating Safety Risks in Real-World LLM Applications
Jia Yi Goh, Shaun Khoo, Nyx Iskandar, Gabriel Chua, Leanne Tan, Jessica Foo
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
Acceleration potential in the GPU design-to-manufacturing pipeline
Maximilian Negele
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Scaling Limits to AI Chip Production
Maximilian Negele, Lennart Heim, Peter Ruschhaupt
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Access Controls Will Solve the Dual-Use Dilemma
Evžen Wybitul
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Exploring an Agenda on Memorization-based Copyright Verification
Harry H. Jiang, Aster Plotnik, Carlee Joe-Wong
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
CALMA: Context‑Aligned Axes for Language Model Alignment
Prajna Soni, Deepika Raman, Dylan Hadfield-Menell
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
Marginal Risk Relative to What? Distinguishing Baselines in AI Risk Management
Jide Alaga, Michael Chen
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Societal Capacity Assessment Framework: Measuring Advanced AI Implications for Vulnerability, Resilience, and Transformation
Milan M. Gandhi, Peter Cihon, Owen C. Larter, Rebecca Anselmetti
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Meek Models Shall Inherit The Earth
Hans Gundlach, Jayson Lynch, Neil Thompson
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Relative Bias: A Comparative Approach for Quantifying Bias in LLMs
Alireza Arbabi, Florian Kerschbaum
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
A Conceptual Framework for AI Capability Evaluations
María Victoria Carro, Denise Alejandra Mester, Francisca Gauna Selasco, Luca Nicolás Forziati Gangi, Matheo Sandleris Musa, Lola Ramos Pereyra, Mario Leiva, Juan Gustavo Corvalan, Maria Vanina Martinez, Gerardo Simari
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Watermarking Without Standards Is Not AI Governance
Alexander Nemecek, Yuzhou Jiang, Erman Ayday
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
From Individual Experience to Collective Evidence: A Reporting-Based Framework for Identifying Systemic Harms
Jessica Dai, Paula Gradu, Inioluwa Deborah Raji, Benjamin Recht
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Position: Generative AI Regulation Can Learn from Social Media Regulation
Ruth Elisabeth Appel
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI
Shayne Longpre, Kevin Klyman, Ruth E. Appel, Sayash Kapoor, Rishi Bommasani, Michelle Sahar, Sean McGregor, Avijit Ghosh, Borhane Blili-Hamelin, Nathan Butters, Alondra Nelson, Dr. Amit Elazari, Andrew Sellars, Casey John Ellis, Dane Sherrets, Dawn Song, Harley Geiger, Ilona Cohen, Lauren McIlvenny, Madhulika Srikumar et al. (14 additional authors not shown)
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Expert Survey: Technical AI Safety & Security Research Priorities
Joe O'Brien, Jeremy Dolan, Jeba Sania, Jay Kim, Rocio Cara Labrador, Jonah Dykhuizen, Sebastian Becker, Jam Kraprayoon
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Deprecating Benchmarks: Criteria and Framework
Ayrton San Joaquin, Rokas Gipiškis, Leon Staufer, Ariel Gil
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
LLMs Can Covertly Sandbag On Capability Evaluations Against Chain-of-Thought Monitoring
Chloe Li, Mary Phuong, Noah Y. Siegel
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
Trends in Frontier AI Model Count: A Forecast to 2028
Iyngkarran Kumar, Sam Manning
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Distributed and Decentralised Training: Technical Governance Challenges in a Shifting AI Landscape
Jakub Kryś, Yashvardhan Sharma, Janet Egan
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
Exploring Functional Similarities of Backdoored Models
Yufan Feng, Benjamin Tan, Yani Ioannou
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Fragile by Design: Formalizing Watermarking Tradeoffs via Paraphrasing
Ali Falahati, Lukasz Golab
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
A Taxonomy for Design and Evaluation of Prompt-Based Natural Language Explanations
Isar Nejadgholi, Mona Omidyeganeh, Marc-Antoine Drouin, Jonathan Boisvert
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone
Evaluating LLM Agent Adherence to Hierarchical Principles: A Lightweight Benchmark for Verifying AI Safety Plan Components
Ram Potham
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Oral
- Readers: Everyone
Position: Formal Methods are the Principled Foundation of Safe AI
Gagandeep Singh, Deepika Chawla
- Published: 05 Jun 2025, Last Modified: 15 Jul 2025
- ICML 2025 Workshop TAIG Poster
- Readers: Everyone