ICLR 2025 Workshop SSI-FM Submissions

Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-Translation
Tianyu Zheng, Shuyue Guo, Xingwei Qu, Jiawei Guo, Xeron Du, Chenghua Lin, Stephen Huang, Jie Fu, Ge Zhang
- Published: 08 Mar 2025, Last Modified: 08 Mar 2025
- SSI-FM Poster
- Readers: Everyone
NNetNav: Unsupervised Learning of Browser Agents Through Environment Interaction in the Wild
Shikhar Murty, Hao Zhu, Dzmitry Bahdanau, Christopher D Manning
- Published: 08 Mar 2025, Last Modified: 08 Mar 2025
- SSI-FM Poster
- Readers: Everyone
Assessing Diversity Collapse in Reasoning
Xingyu Dang, Christina Baek, J Zico Kolter, Aditi Raghunathan
- Published: 08 Mar 2025, Last Modified: 08 Mar 2025
- SSI-FM Poster
- Readers: Everyone
MPAW: Multi-Preference Alignment through Weak Model Collaboration for Efficient and Flexible LLM Decoding
Nuo Chen, GUOJUN XIONG, Bingsheng He
- Published: 08 Mar 2025, Last Modified: 23 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Understanding the Capabilities and Limitations of Weak-to-Strong Generalization
Wei Yao, Wenkai Yang, Ziqiao Wang, Yankai Lin, Yong Liu
- Published: 08 Mar 2025, Last Modified: 14 Mar 2025
- SSI-FM Poster
- Readers: Everyone
Can Language Models Falsify? The Need for Inverse Benchmarking
Shiven Sinha, Shashwat Goel, Ponnurangam Kumaraguru, Jonas Geiping, Matthias Bethge, Ameya Prabhu
- Published: 08 Mar 2025, Last Modified: 11 Apr 2025
- SSI-FM Oral
- Readers: Everyone
SCOPE: Improving LLM Conversations with Efficient Semantic Space Planning
Zhiliang Chen, Xinyuan Niu, Chuan-Sheng Foo, Bryan Kian Hsiang Low
- Published: 08 Mar 2025, Last Modified: 04 Apr 2025
- SSI-FM Poster
- Readers: Everyone
InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context
Bryan Lincoln Marques de Oliveira, Luana Guedes Barros Martins, Bruno Brandão, Luckeciano Carvalho Melo
- Published: 08 Mar 2025, Last Modified: 12 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Adaptively-Labeled Vision Datasets Via Instance-Level Retrieval
Brandon Trabucco, Rishav Mukherji, Yutong Bai, Ruslan Salakhutdinov
- Published: 08 Mar 2025, Last Modified: 07 Apr 2025
- SSI-FM Poster
- Readers: Everyone
DISC: Dynamic Decomposition Improves LLM Inference Scaling
Jonathan Light, Wei Cheng, Yue Wu, Masafumi Oyamada, Mengdi Wang, Santiago Paternain, Haifeng Chen
- Published: 08 Mar 2025, Last Modified: 04 Apr 2025
- SSI-FM Poster
- Readers: Everyone
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and Treefinement
Pranjal Aggarwal, Bryan Parno, Sean Welleck
- Published: 08 Mar 2025, Last Modified: 20 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Self-correction for OOD generalization
Vanya Bannihatti Kumar, Abhinav Sukumar Rao, Aditi Raghunathan
- Published: 08 Mar 2025, Last Modified: 13 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Exploring the Pre-conditions for Memory-Learning Agents
Vishwa Shah, Vishruth Veerendranath, Graham Neubig, Daniel Fried, Zora Zhiruo Wang
- Published: 08 Mar 2025, Last Modified: 12 Apr 2025
- SSI-FM Poster
- Readers: Everyone
DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks
Amin Karimi Monsefi, Kishore Prakash Sailaja, Ali Alilooee, Ser-Nam Lim, Rajiv Ramnath
- Published: 08 Mar 2025, Last Modified: 31 Mar 2025
- SSI-FM Poster
- Readers: Everyone
LaMsS: When Large Language Models Meet Self-Skepticism
Yetao Wu, Yihong Wang, Teng Chen, Ningyuan Xi, Qingqing Gu, Hongyang Lei, Luo Ji
- Published: 08 Mar 2025, Last Modified: 10 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Think, Prune, Train, Improve: Scaling Reasoning Without Scaling Models
Caia Costello
- Published: 08 Mar 2025, Last Modified: 12 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
Nayoung Lee, Ziyang Cai, Avi Schwarzschild, Kangwook Lee, Dimitris Papailiopoulos
- Published: 08 Mar 2025, Last Modified: 08 Mar 2025
- SSI-FM Oral
- Readers: Everyone
Aviary: Training Language Agents on Challenging Scientific Tasks
Siddharth Narayanan, James D. Braza, Ryan-Rhys Griffiths, Manvitha Ponnapati, Albert Bou, Jon M Laurent, Ori Kabeli, Geemi Wellawatte, Sam Cox, Samuel G Rodriques, Andrew White
- Published: 08 Mar 2025, Last Modified: 08 Mar 2025
- SSI-FM Poster
- Readers: Everyone
KernelBench: Can LLMs Write Efficient GPU Kernels?
Anne Ouyang, Simon Guo, Simran Arora, Alex L Zhang, William Hu, Christopher Re, Azalia Mirhoseini
- Published: 08 Mar 2025, Last Modified: 12 Apr 2025
- SSI-FM Poster
- Readers: Everyone
A Self-Improving Coding Agent
Maxime Robeyns, Martin Szummer, Laurence Aitchison
- Published: 08 Mar 2025, Last Modified: 12 Apr 2025
- SSI-FM Oral
- Readers: Everyone
Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers (Abridged)
Shalev Lifshitz, Sheila A. McIlraith, Yilun Du
- Published: 08 Mar 2025, Last Modified: 22 Mar 2025
- SSI-FM Poster
- Readers: Everyone
Great Models Think Alike and this Undermines AI Oversight
Shashwat Goel, Joschka Strüber, Ilze Amanda Auzina, Karuna K Chandra, Ponnurangam Kumaraguru, Douwe Kiela, Ameya Prabhu, Matthias Bethge, Jonas Geiping
- Published: 08 Mar 2025, Last Modified: 12 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Moral Intrinsic Rewards for Automated Alignment of LLM Agents
Elizaveta Tennant, Stephen Hailes, Mirco Musolesi
- Published: 08 Mar 2025, Last Modified: 11 Apr 2025
- SSI-FM Poster
- Readers: Everyone
Training a Generally Curious Agent
Fahim Tajwar, Yiding Jiang, Abitha Thankaraj, Sumaita Sadia Rahman, J Zico Kolter, Jeff Schneider, Ruslan Salakhutdinov
- Published: 08 Mar 2025, Last Modified: 14 Apr 2025
- SSI-FM Poster
- Readers: Everyone
How to Mitigate Overfitting in Weak-to-strong Generalization?
Junhao Shi, Qingyuan Chen, Zhaoye Fei, Yining Zheng, Qipeng Guo, Xuanjing Huang, Xipeng Qiu
- Published: 08 Mar 2025, Last Modified: 08 Mar 2025
- SSI-FM Poster
- Readers: Everyone