NeurIPS 2024PastOther
UniReps: 2nd Edition of the Workshop on Unifying Representations in Neural Models
UniReps
- Submission deadline
- Sep 24, 2024, 12:00 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (68)
Fetched from OpenReview (v2) on 2026-06-10.
A Cognitive Framework for Learning Debiased and Interpretable Representations via Debiasing Global Workspace
A Framework for Standardizing Similarity Measures in a Rapidly Evolving Field
Adapter to facilitate Foundation Model Communication for DLO Instance Segmentation
An Information Criterion for Controlled Disentanglement of Multimodal Data
Artificial Neural Networks Generate Human-like Continuous Speech Perception
Auxiliary objective improves generalization performance but reduces model specification for low-data neuroimaging-based brain age prediction
Challenges in Explaining Representational Similarity through Identifiability
Circular Learning Provides Biological Plausibility
Comparing Representations in Static and Dynamic Vision Models to the Human Brain
Comparing the local information geometry of image representations
Conic Activation Functions
Connecting Neural Models Latent Geometries with Relative Geodesic Representations
CopRA: A Progressive LoRA Training Strategy
Correlating Variational Autoencoders Natively For Multi-View Imputation
Decision-margin consistency: a principled metric for human and machine performance alignment
Delays in generalization match delayed changes in representational geometry
DFM: Interpolant-free Dual Flow Matching
DIETing: Self-Supervised Learning with Instance Discrimination Learns Identifiable Features
Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations
Emergence of Text Semantics in CLIP Image Encoders
Equivalence between representational similarity analysis, centered kernel alignment, and canonical correlations analysis
Evidence from fMRI Supports a Two-Phase Abstraction Process in Language Models
Fast Imagic: Solving Overfitting in Text-guided Image Editing via Disentangled UNet with Forgetting Mechanism and Unified Vision-Language Optimization
Federated GNNs for EEG-Based Stroke Assessment
Finding Symmetry in Neural Network Parameter Spaces
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
Hybrid Dynamic High-Order Functional Correlations and Divisive Normalization for Improved Classification of Schizophrenia and Bipolar Disorder
Hypernetworks for image recontextualization
Improving Model Merging with Natural Niches
Improving OOD Generalization of Pre-trained Encoders via Aligned Embedding-Space Ensembles
Inducing Human-like Biases in Moral Reasoning Language Models
Invariant Learning with Annotation-free Environments
Investigating the role of modality and training objective on representational alignment between transformers and the brain
It's All Relative: Relative Uncertainty in Latent Spaces using Relative Representations
Joint Learning for Visual Reconstruction from the Brain Activity: Hierarchical Representation of Image Perception with EEG-Vision Transformer
Language decoding from human brain activity via contrastive learning
Locality-aware Concept Bottleneck Model
Look-Ahead Selective Plasticity for Continual Learning of Visual Tasks
M3CoL: Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification
Modern Hopfield Networks meet Encoded Neural Representations - Addressing Practical Considerations
Monkey See, Model Knew: Large Language Models accurately Predict Human AND Macaque Visual Brain Activity
Multi-task Learning yields Disentangled World Models: Impact and Implications
Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities
On the cognitive alignment between humans and machines
Position: Maximizing Neural Regression Scores May Not Identify Good Models of the Brain
Random Propagations in GNNs
Relative Representations: Topological and Geometric Perspectives
Representation Learning of Structured Data for Medical Foundation Models
Representation with a capital 'R': measuring functional alignment with causal perturbation
Rethinking Fine-tuning Through Geometric Perspective
Revealing spatial-frequency channels in an ensemble encoding model of human fMRI
Self-Supervised Pre-training of Spiking Neural Networks by Contrasting Events and Frames
Shared Recurrent Memory Improves Multi-agent Pathfinding
Small-scale adversarial perturbations expose differences between predictive encoding models of human fMRI responses
Task-Relevant Covariance from Manifold Capacity Theory Improves Robustness in Deep Networks
Topology Preserving Regularization for Independent Training of Inter-operable Models
Understanding Memorization using Representation Similarity Analysis and Model Stitching
Understanding Permutation Based Model Merging with Feature Visualizations
Understanding Variational Autoencoders with Intrinsic Dimension and Information Imbalance
Unifying Causal Representation Learning with the Invariance Principle
Unsupervised Learning of Categorical Structure
Unsupervised Modality Adaptation in Human Action Recognition via Cross-modal Representation Learning
Video decoding from human fMRI data with a multi-stream sensory approach
Vision and language representations in multimodal AI models and human social brain regions during natural movie viewing
VISTA: A Panoramic View of Neural Representations
What Representational Similarity Measures Imply about Decodable Information
Winning Tickets from Random Initialization: Aligning Masks for Sparse Training
Workshop Submission: Towards Making Untrainable Networks Trainable