representation learning

6174 papers

Explore in graph

Also known as

WAV2VEC2.0 RL NRMS NDFS

Co-occurring keywords

contrastive learning (3979) self-supervised learning (3751) transfer learning (5442) neural network (6616) unsupervised learning (3255) graph neural network (3945) multimodal learning (4622) domain adaptation (4578) feature learning (1309) language model (4573)

Papers

Detecting Subtle Sense Shift with Polysemy-Aware Trends EACL 2026

On the Additive Compositionality of Task Vectors in Vision–Language Models EACL 2026

Suppressing Final Layer Hidden State Jumps in Transformer Pretraining EACL 2026

Subspace-Guided Knowledge Distillation for Efficient Model Transfer WACV 2026

Exploiting Label-Independent Regularization from Spatial Patterns for Whole Slide Image Analysis WACV 2026

Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space WACV 2026

LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance EACL 2026

Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer EACL 2026

MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning EACL 2026

Zero-Shot Coreset Selection via Iterative Subspace Sampling WACV 2026

A Dataset and Framework for Learning State-invariant Object Representations WACV 2026

CoreCaption: Core Caption based Text-to-Video Retrieval WACV 2026

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story EACL 2026

Cosine Similarity is Almost All You Need (for Prototypical-Part Models) WACV 2026

SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition WACV 2026

Ordinal-Aware Multimodal Engagement Recognition for Collaborative Learning WACV 2026

LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization WACV 2026

Feature Inversion as a Lens on Vision Encoders WACV 2026

Countering Multi-modal Representation Collapse through Rank-targeted Fusion WACV 2026

Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction WACV 2026

Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis WACV 2026

DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning WACV 2026

Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models WACV 2026

Beyond Tokens: Concept-Level Training Objectives for LLMs EACL 2026

Discovering Hybrid World Representations with Co-Evolving Foundation Models AAAI 2026