ICML 2025 Workshop R2-FM Submissions

Finetuning-Activated Backdoors in LLMs
Thibaud Gloaguen, Mark Vero, Robin Staab, Martin Vechev
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
SOSBENCH: Benchmarking Safety Alignment on Scientific Knowledge
Fengqing Jiang, Fengbo Ma, Zhangchen Xu, Yuetai Li, Bhaskar Ramasubramanian, Luyao Niu, Bo Li, Xianyan Chen, Zhen Xiang, Radha Poovendran
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Defending Against Prompt Injection with a Few DefensiveTokens
Sizhe Chen, Yizhu Wang, Nicholas Carlini, Chawin Sitawarin, David Wagner
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Lifelong Safety Alignment for Language Models
Haoyu Wang, Zeyu Qin, Yifei Zhao, Chao Du, Min Lin, Xueqian Wang, Tianyu Pang
- Published: 01 Jul 2025, Last Modified: 05 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Robust and Interpretable Relational Reasoning with Large Language Models and Symbolic Solvers
Ge Zhang, Mohammad Ali Alomrani, Hongjian Gu, Jiaming Zhou, Yaochen Hu, Bin Wang, Qun Liu, Mark Coates, Yingxue Zhang, Jianye HAO
- Published: 01 Jul 2025, Last Modified: 07 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
LoRA Merging with SVD: Understanding Interference and Preserving Performance
Dennis Tang, Prateek Yadav, Yi-Lin Sung, Jaehong Yoon, Mohit Bansal
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
Yukun Jiang, Mingjie Li, Michael Backes, Yang Zhang
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Thought calibration: Efficient and confident test-time scaling
Menghua Wu, Cai Zhou, Stephen Bates, Tommi Jaakkola
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Lookahead Bias in Pretrained Language Models
Suproteem K Sarkar, Keyon Vafa
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Steering Language Model Refusal with Sparse Autoencoders
Kyle O'Brien, David Majercak, Xavier Fernandes, Richard G. Edgar, Blake Bullwinkel, Jingya Chen, Harsha Nori, Dean Carignan, Eric Horvitz, Forough Poursabzi-Sangdeh
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
Aditya Kumar, Tom Blanchard, Adam Dziedzic, Franziska Boenisch
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
Kejia Zhang, Keda TAO, Jiasheng Tang, Huan Wang
- Published: 01 Jul 2025, Last Modified: 05 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization
Joschka Braun, Carsten Eickhoff, Seyed Ali Bahrainian
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Dynamic Risk Assessments for Offensive Cybersecurity Agents
Boyi Wei, Benedikt Stroebl, Jiacen Xu, Joie Zhang, Zhou Li, Peter Henderson
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Capability-Based Scaling Laws for LLM Red-Teaming
Alexander Panfilov, Paul Kassianik, Maksym Andriushchenko, Jonas Geiping
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Consistency in Language Models: Current Landscape, Challenges, and Future Directions
Jekaterina Novikova, Carol Myrick Anderson, Borhane Blili-Hamelin, Domenic Rosati, Subhabrata Majumdar
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
The Geometry of Forgetting: Analyzing Machine Unlearning through Local Learning Coefficients
Aashiq Muhamed, Virginia Smith
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
Aashiq Muhamed, Jacopo Bonato, Mona T. Diab, Virginia Smith
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
Jianyu Wang, Zhiqiang Hu, Lidong Bing
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
State Space Models: A Naturally Robust Alternative to Transformers in Computer Vision
Chengbin Du, Yanxi Li, Chang Xu
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone