OpenReview.net

Login

Back to ICLR

ICLR 2026 Workshop UCRL Submissions

Loading

About OpenReview
Hosting a Venue
All Venues

Contact
Sponsors
Donate

FAQ
Terms of Use / Privacy Policy
News

About OpenReview
Hosting a Venue
All Venues
Sponsors
News

FAQ
Contact
Donate
Terms of Use
Privacy Policy

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2026 OpenReview

Post-hoc Self-explanation of CNNs
Ahcene Boubekki, Line H Clemmensen
- Published: 01 Mar 2026, Last Modified: 28 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
One Language, Two Scripts: Probing Script-Invariance in LLM Concept Representations
Sripad Karne
- Published: 01 Mar 2026, Last Modified: 28 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Multi-shot AutoInterp: Agents Can Explain Complex Features By Refining Explanations
Kamal Maher, Simon Elias Schrader, Kola Ayonrinde
- Published: 01 Mar 2026, Last Modified: 11 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations
Bryce Grant, Peng Wang
- Published: 01 Mar 2026, Last Modified: 28 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Do Monolingual Language Models Learn Cross-Lingual Universal Conceptual Representations?
Suchir Salhan, Ej Zhou, Paula Buttery
- Published: 01 Mar 2026, Last Modified: 01 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
VLC Fusion: Vision-Language Conditioned Sensor Fusion for Robust Object Detection
Aditya Taparia, Noel Ngu, Mario Leiva, Joshua Shay Kricheli, John Corcoran, Nathaniel D. Bastian, Gerardo Simari, Paulo Shakarian, Ransalu Senanayake
- Published: 01 Mar 2026, Last Modified: 28 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Causality Guided Representation Learning for Cross-Style Hate Speech Detection
Chengshuai Zhao, Shu Wan, Paras Sheth, Karan Patwa, K. Selcuk Candan, huan liu
- Published: 01 Mar 2026, Last Modified: 27 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
SSCD: Sparse Semantic Concept Defense Against Semantic Adversarial Attacks to Image Classifiers
Nghia Nguyen, Darshan Thaker, Konstantinos Emmanouilidis, Tianjiao Ding, Rene Vidal
- Published: 01 Mar 2026, Last Modified: 01 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Self-Interpretable Concept Representations: Training Lightweight Adapters on Vector-Label Pairs
Keenan Pepper, Alex McKenzie, Florin Pop, Stijn Servaes, Martin Leitgab, Michael Vaiana, Judd Rosenblatt, Michael S. A. Graziano, Diogo S de Lucena
- Published: 01 Mar 2026, Last Modified: 01 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Diagnosing and Fixing Latent Recovery in Sparse Autoencoders
Zhenyu Zhu, Marco Fumero, Francesco Locatello, Volkan Cevher
- Published: 01 Mar 2026, Last Modified: 27 Mar 2026
- UCRL@ICLR2026 Oral
- Readers: Everyone
Identifiable Estimation of Causal Concept Effects under Visual Latent Confounding
Thomas Melistas, Damian Machlanski, Kurt Butler, Angelos Korakitis, Nikos Spyrou, Athanasios Vlontzos, Yannis Panagakis, Sotirios A. Tsaftaris, Giorgos Papanastasiou
- Published: 01 Mar 2026, Last Modified: 23 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Simulating Concept Bottlenecks with Vision-Language Models
Karim Galliamov, Ilya Pershin, Ivan Titov
- Published: 01 Mar 2026, Last Modified: 27 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Syntax-Preserving Hyperbolic Visual-Semantic Embeddings
Genji Ohara, Daiki Yoshikawa, Takashi Matsubara
- Published: 01 Mar 2026, Last Modified: 28 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Digging Deeper: Learning Multi-Level Concept Hierarchies
Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
- Published: 01 Mar 2026, Last Modified: 26 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Continual learning and refinement of causal models through dynamic predicate invention
Enrique Crespo-Fernandez, Oliver Ray, Telmo M Silva Filho, Peter Flach
- Published: 01 Mar 2026, Last Modified: 09 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Extracting Representations in LLMs Robust to Distribution Shifts
Sweta Karlekar, Claudia Shi, Aahlad Manas Puli, Carolina Zheng, Maggie Makar, John Bowlan, Michal Kucer, David Blei
- Published: 01 Mar 2026, Last Modified: 31 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
NEUROLOGIC: From Neural Representations to Interpretable Logic Rules
Chuqin Geng, Anqi Xing, Li Zhang, Ziyu Zhao, Jingkai Xu, Yuhe Jiang, Xujie Si
- Published: 01 Mar 2026, Last Modified: 01 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
Hoyeon Chang, Bálint Mucsányi, Seong Joon Oh
- Published: 01 Mar 2026, Last Modified: 01 Mar 2026
- UCRL@ICLR2026 Oral
- Readers: Everyone
Decomposing Representation Drift via Interventions
Thomas Y Chen, Daniel Xu
- Published: 01 Mar 2026, Last Modified: 07 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Automated Concept Discovery for LLM-as-a-Judge Preference Analysis
James Wedgwood, Chhavi Yadav, Virginia Smith
- Published: 01 Mar 2026, Last Modified: 27 Mar 2026
- UCRL@ICLR2026 Oral
- Readers: Everyone
Concept Bottleneck Diffusion for Steerable Generation
Eric Enouen, sainyam galhotra
- Published: 01 Mar 2026, Last Modified: 01 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
Automatic Interpretation of Visual Concepts
Felix Meissen, Kenza Bouzid, Tristan Lazard, Shruthi Bannur, Daniel C. Castro, Javier Alvarez-Valle, Stephanie Hyland
- Published: 01 Mar 2026, Last Modified: 08 Mar 2026
- UCRL@ICLR2026 Oral
- Readers: Everyone
Navigating the Concept Space of Language Models
Wilson Marcilio-Jr, Danilo Medeiros Eler
- Published: 01 Mar 2026, Last Modified: 06 Mar 2026
- UCRL@ICLR2026 Oral
- Readers: Everyone
On the Existence and Behavior of Secondary Attention Sinks
Jeffrey T. H. Wong, Cheng Zhang, Louis Mahon, Wayne Luk, Anton Isopoussu, Yiren Zhao
- Published: 01 Mar 2026, Last Modified: 14 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone
An Information-Theoretic Approach to Benign Leakage in Static Concept Embedding Models
Tianchao Li, Shujian Yu, Robert Jenssen
- Published: 01 Mar 2026, Last Modified: 26 Mar 2026
- UCRL@ICLR2026 Poster
- Readers: Everyone

«
‹
1
2
›
»