Skip to yearly menu bar Skip to main content


Workshop Sun, Dec 7, 2025 • 8:00 AM – 5:00 PM PST Upper Level Room 1AB

Regulatable ML: Towards Bridging the Gaps between Machine Learning Research and Regulations

Chirag Agarwal · Jiaqi Ma · Sarah Tan · Himabindu Lakkaraju · Junwei Deng · Pingbang Hu · Eileanor LaRocco · Karolina Naranjo · Shichang (Ray) Zhang
Project Page [ OpenReview] 

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
8:45 AM
Opening Remarks
9:00 AM
Contributed Talk Session 1
Yi Huang · Gauri Kholkar · Wei May Chen · Luxi He
9:40 AM
Coffee Break
12:15 PM
Lunch
2:00 PM
Contributed Talk Session 2
Chung Peng Lee · Kevin Feng · Ahmed Ahmed · Hamidah Oderinwale
3:50 PM
Panel: The AI Wars: Regulation, Open Science, and the Race for Global Power
Rich Caruana · Jiahao Chen · Avijit Ghosh · melissa g fabros · Ian Eisenberg · Chirag Agarwal
Regulating the Agency of LLM-based Agents
Seán Boddy · Joshua Joseph
AI, Climate, and Transparency: Operationalizing and Improving the AI Act
Nicolas Alder · Kai Ebert · Ralf Herbrich · Philipp Hacker
AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
Harish Karthikeyan · Yue Guo · Udari Sehwag · Leo de Castro · Antigoni Polychroniadou · Leo Ardon · Sumitra Ganesh
Differentially Private Adaptation of Diffusion Models via Noisy Aggregated Embeddings
Pura Peetathawatchai · Wei-Ning Chen · Berivan Isik · Sanmi Koyejo · Albert No
A Framework for the Categorisation of General-Purpose AI Models under the EU AI Act
Lorenzo Pacchiardi · John Burden · Fernando Martínez-Plumed · José Hernández-Orallo · Emilia Gomez · David Fernández-Llorca
Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
Will Cai · Tianneng Shi · Xuandong Zhao · Dawn Song
Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders
Xuansheng Wu · Jiayi Yuan · Wenlin Yao · Xiaoming Zhai · Ninghao Liu
ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models
Xiaomin Li · Xupeng Chen · Jingxuan Fan · Eric Hanchen Jiang · Mingye Gao
Scratchpad Thinking: Alternation Between Storage and Computation in Latent Reasoning Models
Sayam Goyal · Brad Peters · Maria Emilia Granda · Akshath Narmadha · Dharunish Yugeswardeenoo · Callum McDougall · Sean O'Brien · Ashwinee Panda · Kevin Zhu · Cole Blondin
PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming
Wesley Deng · Sunnie S. Y. Kim · Akshita Jha · Kenneth Holstein · Motahhare Eslami · Lauren Wilcox · Leon Gatys
How do data owners say no? A case study of data consent mechanisms in web-scraped vision-language AI training datasets
Chung Peng Lee · Rachel Hong · Harry H. Jiang · Aster Plotnik · William Agnew · Jamie Morgenstern
Data Forging Attacks on Cryptographic Model Certification
Carter Luck · Olive Franzese · Elisaweta Masserova · Akira Takahashi · Antigoni Polychroniadou
SPEAR++: Scaling Gradient Inversion via Sparsely-Used Dictionary Learning
Alexander Bakarsky · Dimitar I. Dimitrov · Maximilian Baader · Martin Vechev
Statutory Construction and Interpretation for Artificial Intelligence
Luxi He · Nimra Nadeem · Michel Liao · Howard Chen · Danqi Chen · Peter Henderson
Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Face
Hamidah Oderinwale · Benjamin Laufer · Jon Kleinberg
EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law
Ilija Lichkovski · Alexander Müller · Mariam Ibrahim · Tiwai Mhundwa
SpecEval: Evaluating Model Adherence to Behavior Specifications
Ahmed Ahmed · Kevin Klyman · Yi Zeng · Sanmi Koyejo · Percy Liang
The Contribution of XAI for the Safe Development and Certification of AI: An Expert-Based Analysis
Benjamin Fresz · Vincent Philipp Göbels · Safa Omri · Danilo Brajovic · Andreas Aichele · Janika Kutz · Jens Neuhüttler · Marco Huber
From Proposals to Enactment: The Procedural Bottleneck in AI Safety Regulation
Mansur Khan · Mehmet Efe Akengin · Ahmad Rushdi
The Hidden Cost of Modeling $P(X)$: Membership Inference Attacks in Generative Text Classifiers
Owais Makroo · Karan Gupta · Siva Rajesh Kasa · Sumegh Roychowdhury · Pattisapu Priyatam · SANTHOSH KASA · Sumit Negi
Position: Bridge the Gaps between Machine Unlearning and AI Regulation
Bill Marino · Meghdad Kurmanji · Nicholas Lane
MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
Sepideh Abedini · Shubhankar Mohapatra · David B. Emerson · Masoumeh Shafieinejad · Jesse Cresswell · Xi He
The Backfiring Effect of Weak AI Safety Regulation
Benjamin Laufer · Jon Kleinberg · Hoda Heidari
Inducing Uncertainty on Open-Weight Models for Test-Time Privacy in Image Recognition
Muhammad Ashiq · Peter Triantafillou · Hung Tseng · Grigorios Chrysos
Cost Efficient Fairness Audit Under Partial Feedback
Nirjhar Das · mohit sharma · Praharsh Nanavati · Kirankumar Shiragur · Amit Deshpande
On the Regulatory Potential of User Interfaces for AI Agent Governance
Kevin Feng · Tae Soo Kim · Rock Yuren Pang · Faria Huq · Tal August · Amy Zhang
Emergency Response Measures for Catastrophic Risk
James Zhang · Miles Kodama · Zongze Wu · Michael Chen · Yue Zhu · Geng Hong
StealthEval: A Probe-Rewrite-Evaluate Workflow for Reliable Benchmarks
Lang Xiong · Nishant Bhargava · Jeremy Chang · Jianhang Hong · Haihao Liu · Kevin Zhu
Check Yourself Before You Wreck Yourself: Selectively Quitting Improves LLM Agent Safety
Vamshi Krishna Bonagiri · Ponnurangam Kumaraguru · Khanh Nguyen · Benjamin Plaut
Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning
Benjamin Liu · Dillon Mehta · Rishi Malhotra · Adam Zobian · Yong Tan · Samir Chopra · Daniella Rand · Natalie Pang · Abhiram Gudimella · Raghav Thallapragada · Derek Jiu · Kevin Zhu
Do AI Companies Make Good on Voluntary Commitments to the White House?
Jennifer Wang · Kayla Huang · Kevin Klyman · Rishi Bommasani
The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models
Yang Xiao · Gen Li · Jie Ji · Ruimeng Ye · Xiaolong Ma · Bo Hui