ICML 2025 Workshop R2-FM Submissions

A Statistical Physics of Language Model Reasoning
Jack David Carson
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
BiasGUARRD: Enhancing Fairness and Reliability in LLM Conflict Resolution Through Agentic Debiasing
Erica Wang, Shrujana S Kunnam, Sreeyutha Ratala
- Published: 01 Jul 2025, Last Modified: 10 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Persuade Me If You Can: Evaluating AI Agent Influence on Safety Monitors
Jennifer Za, Julija Bainiaksina, Tanush Chopra, Nikita Ostrovsky, Victoria Krakovna
- Published: 01 Jul 2025, Last Modified: 10 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Model Organisms for Emergent Misalignment
Edward Turner, Anna Soligo, Mia Taylor, Senthooran Rajamanoharan, Neel Nanda
- Published: 01 Jul 2025, Last Modified: 10 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Adversarial Manipulation of Reasoning Models using Internal Representations
Kureha Yamaguchi, Benjamin Etheridge, Andy Arditi
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
GPT, But Backwards: Exactly Inverting Language Model Outputs
Adrians Skapars, Edoardo Manino, Youcheng Sun, Lucas Carvalho Cordeiro
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
On the Scoring Functions for RAG-based Conformal Factuality
Yi Chen, Caitlyn Heqi Yin, Sukrut Madhav Chikodikar, Ramya Korlakai Vinayak
- Published: 01 Jul 2025, Last Modified: 07 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
Miles Turpin, Andy Arditi, Marvin Li, Joe Benton, Julian Michael
- Published: 01 Jul 2025, Last Modified: 10 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
The Geometries of Truth Are Orthogonal Across Tasks
Waïss Azizian, Michael Kirchhof, Eugene Ndiaye, Louis Béthune, Michal Klein, Pierre Ablin, marco cuturi
- Published: 01 Jul 2025, Last Modified: 04 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
On Learning Verifiers for Chain-of-Thought Reasoning
Maria Florina Balcan, Avrim Blum, Zhiyuan Li, Dravyansh Sharma
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?
Kai Yan, Yufei Xu, Zhengyin Du, Xuesong Yao, Zheyu Wang, Xiaowen Guo, Jiecao Chen
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Do Sparse Autoencoders Generalize? A Case Study of Answerability
Lovis Heindrich, Philip Torr, Fazl Barez, Veronika Thost
- Published: 01 Jul 2025, Last Modified: 07 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Advancing LLM Safe Alignment with Safety Representation Ranking
Tianqi Du, Zeming Wei, Quan Chen, Chenheng Zhang, Yisen Wang
- Published: 01 Jul 2025, Last Modified: 07 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Conformal Prediciton Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models
Sima Noorani, Shayan Kiyani, George J. Pappas, Hamed Hassani
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
When Meaning Doesn’t Matter: Exposing Guard Model Fragility via Paraphrasing
Cristina Pinneri, Christos Louizos
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
Yingsha Xie, Rui Min, Zeyu Qin, Fei Ma, Li Shen, Fei Yu, Xiaochun Cao
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Learning on LLM Output Signatures for Gray-Box Behavior Analysis
Guy Bar-Shalom, Fabrizio Frasca, Derek Lim, Yoav Gelberg, Yftah Ziser, Ran El-Yaniv, Gal Chechik, Haggai Maron
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Visual Language Models as Zero-Shot Deepfake Detectors
Viacheslav Pirogov
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification
Yuhao Sun, Jiacheng Zhang, Zesheng Ye, Chaowei Xiao, Feng Liu
- Published: 01 Jul 2025, Last Modified: 06 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
Polina Kirichenko, Mark Ibrahim, Kamalika Chaudhuri, Samuel J. Bell
- Published: 01 Jul 2025, Last Modified: 09 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Semi-Nonnegative GPT: Towards Monosemantic representations
Junyi Li, Jinqi Liu, Qi Zhang, Yisen Wang
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Evaluating Adversarial Protections for Diffusion Personalization: A Comprehensive Study
Kai Ye, Tianyi Chen, Zhen Wang
- Published: 01 Jul 2025, Last Modified: 05 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models
Zhanke Zhou, Zhaocheng Zhu, Xuan Li, Mikhail Galkin, Xiao Feng, Sanmi Koyejo, Jian Tang, Bo Han
- Published: 01 Jul 2025, Last Modified: 10 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Conformal Risk Minimization with Variance Reduction
Sima Noorani, Orlando Romero, Nicolo Dal Fabbro, Hamed Hassani, George J. Pappas
- Published: 01 Jul 2025, Last Modified: 01 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
Distilling Safe LLM Systems via Soft Prompts
Motasem Alfarra, Dana Kianfar, Cristina Pinneri, Christos Louizos
- Published: 01 Jul 2025, Last Modified: 07 Jul 2025
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone