ICLR 2025 Workshop SCSL Submissions

Unveiling and Mitigating Shortcuts in Multimodal In-Context Learning
Yanshu Li
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Mitigating Simplicity Bias in Neural Networks: A Feature Sieve Modification, Regularization, and Self-Supervised Augmentation Approach
Gaurav Joshi, Parth Narendra Shah, Rachit Verma
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Object-Centric Representations Generalize Better Compositionally with Less Compute
Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Max Horn, Carsten Marr, Stefan Bauer, Andrea Dittadi
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
BEYOND DECODABILITY: LINEAR FEATURE SPACES ENABLE VISUAL COMPOSITIONAL GENERALIZATION
Arnas Uselis, Andrea Dittadi, Seong Joon Oh
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
LACER: Loss-Aware Clustering for Effective Reweighting
Saksham Rastogi, Polina Kirichenko
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Cross-Instance Contrastive Masking in Vision Transformers for Self-Supervised Hyperspectral Image Classification
Abhiroop Chatterjee, Susmita Ghosh, Ashish Ghosh
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Are We Done with Object-Centric Learning?
Alexander Rubinstein, Ameya Prabhu, Matthias Bethge, Seong Joon Oh
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Diagnosing the Effects of Pre-training Data on Fine-tuning and Subgroup Robustness for Occupational NER in Clinical Notes
Dana Moukheiber, Saurabh Mahindre, Mingchen Gao
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
GradTune: Last-layer Fine-tuning for Group Robustness Without Group Annotation
Patrik Kenfack, Ulrich Aïvodji, Samira Ebrahimi Kahou
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Structured Robustness for Distribution Shifts
Erfan Darzi, Alexander Marx
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Assessing Robustness to Spurious Correlations in Post-Training Language Models
Julia Shuieh, Prasann Singhal, Apaar Shanker, John Heyer, George Pu, Samuel Marc Denton
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Can Transformers Learn Tasks of Varying Complexity In-context?
Puneesh Deora, Bhavya Vasudeva, Tina Behnia, Christos Thrampoulidis
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
A Guide to Misinformation Detection Data and Evaluation
Camille Thibault, Jacob-Junqi Tian, Gabrielle Péloquin-Skulski, Taylor Lynn Curtis, James Zhou, Florence Laflamme, Yuxiang Guan, Reihaneh Rabbany, Jean-François Godbout, Kellin Pelrine
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Towards personalized healthcare without harm via bias modulation
Frank Ngaha, Patrik Kenfack, Ulrich Aïvodji, Samira Ebrahimi Kahou
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Exploiting What Trained Models Learn for Making Them Robust to Spurious Correlations without Group Annotations
Mahdi Ghaznavi, Hesam Asadollahzadeh, Fahimeh Hosseini Noohdani, Soroush Vafaie Tabar, Hosein Hasani, Taha Akbari Alvanagh, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Mitigating Spurious Correlations in Image Recognition Models using Performance-Based Feature Sampling
Aarav Monga, Rajakrishnan Somou, Sonia Zhang, Antonio Ortega
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Bayesian Invariance Modeling of Multi-Environment Data
Luhuan Wu, Mingzhang Yin, Yixin Wang, John Patrick Cunningham, David Blei
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Evaluating Multi-modal Language Models Through Concept Hacking
Yijiang Li, Bingyang Wang, Tianwei Zhao, Qingying Gao, Hokin Deng, Dezhi Luo
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
SpurLens: Finding Spurious Correlations in Multimodal LLMs
Parsa Hosseini, Sumit Nawathe, Mazda Moayeri, Sriram Balasubramanian, Soheil Feizi
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Meta Learning not to Learn: Robustly Informing Meta-Learning under Nuisance-Varying Families
Louis McConnell
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Spawrious: A Benchmark for Fine Control of Spurious Correlation Biases
Aengus Lynch, Gbetondji Jean-Sebastien Dovonon, Jean Kaddour, Ricardo Silva
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Towards Brain Inspired Design for Addressing the Shortcomings of ANNs
Fahad Sarfraz, Bahram Zonooz, Elahe Arani
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Excessive Supervision and Shortcuts Prevent In-domain Learning of Trivial Graph Search
Arvid Frydenlund
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
VACT: A Video Automatic Causal Testing System and a Benchmark
Haotong Yang, Qingyuan Zheng, Yunjian Gao, Yongkun Yang, Yangbo He, Zhouchen Lin, Muhan Zhang
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone
Spurious Equilibrium in Segmentation Models and Recurrent Processing in Human Vision
Kailas D, Brejesh Lall
- Published: 06 Mar 2025, Last Modified: 01 May 2025
- SCSL @ ICLR 2025
- Readers: Everyone