ICLR 2025PastSafety & alignment
Second Workshop on Representational Alignment at ICLR 2025
ICLR 2025 Re-Align Workshop
- Submission deadline
- Feb 6, 2025, 12:30 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (38)
Fetched from OpenReview (v2) on 2026-06-10.
Aligning LLMs with Domain Invariant Reward Models
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Augmenting X-ray Astronomical Representations with Scientific Knowledge through Contrastive Learning
Beyond Adversarial Robustness: Breaking the Robustness-Alignment Trade-off in Object Recognition
Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
Brain-like slot representation for sequence working memory in recurrent neural networks
Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments
Closing The Modality Gap Enables Novel Multimodal Learning Applications
Cognitive Neural Architecture Search Reveals Hierarchical Entailment
Complexity in Complexity: Understanding Visual Complexity Through Structure, Color, and Surprise
Computer Graphics from a Neuroscientist's perspective
Conjuring Semantic Similarity
Contrastive Representations for Combinatorial Reasoning
Cross-Modal Alignment Regularization: Enhancing Language Models with Vision Model Representations
Do Large Language Models Perceive Orderly Number Concepts as Humans?
Dual-Pathway Neural Networks: Harnessing Scene and Object Pathways for Enhanced Visual Understanding
Exploring Geometric Representational Alignment through Ollivier Ricci curvature and Ricci Flow
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
Investigating the Role of Representation Switching Costs in Goal Persistence Bias
Kernel Alignment using Manifold Approximation
Linking Neural Representations To Adaptive Behavior With Cognitive Modeling
Model Alignment Search
Model alignment using inter-modal bridges
Model Connectomes: A Generational Approach to Data-Efficient Language Models
Modularity is the Bedrock of Natural and Artificial Intelligence
Partial Alignment of Representations via Interventional Consistency
Place Field Representation Learning During Policy Learning
Representation-alignment in Theory-of-Mind tasks across Language Models and Agents
REPRESENTATIONAL ALIGNMENT OF GLOMERULI ACTIVATION IN MURINE OLFACTORY BULB
Revisiting the Relation Between Robustness and Universality
Shared Global and Local Geometry of Language Model Embeddings
The Effect of Representational Compression on Flexibility Across Learning in Humans and Artificial Neural Networks
The in-context inductive biases of vision-language models differ across modalities
The Spotlight Resonance Method: Resolving The Alignment of Embedded Activations
Traveling Waves Integrate Spatial Information Into Spectral Representations
Understanding task representations in neural networks via Bayesian ablation
Understanding the Emergence of Multimodal Representation Alignment
Unsupervised Neuronal Matching with Spontaneous Neuronal Activity