embedding space

Q-Probe: A Lightweight Approach to Reward Maximization for Language Models ICML 2024 Relational Proxy Loss for Audio-Text based Keyword Spotting Interspeech 2024 Representation Degeneration Problem in Prompt-based Models for Natural Language Understanding COLING 2024 Robust AI-Generated Text Detection by Restricted Embeddings EMNLP 2024 RulE: Knowledge Graph Reasoning with Rule Embedding ACL 2024 Scaling Retrieval-Based Language Models with a Trillion-Token Datastore NeurIPS 2024 Simulation-Free Training of Neural ODEs on Paired Data NeurIPS 2024 Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space NeurIPS 2024 Sparse Enhanced Network: An Adversarial Generation Method for Robust Augmentation in Sequential Recommendation AAAI 2024 Spectral Filters, Dark Signals, and Attention Sinks ACL 2024 Speech Formants Integration for Generalized Detection of Synthetic Speech Spoofing Attacks Interspeech 2024 Stable Anisotropic Regularization ICLR 2024 Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning ICLR 2024 Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval CVPR 2024 Text-to-Code Generation with Modality-relative Pre-training EACL 2024 The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models EACL 2024 The Shape of Word Embeddings: Quantifying Non-Isometry with Topological Data Analysis EMNLP 2024 The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric ICLR 2024 Towards Improved Proxy-Based Deep Metric Learning via Data-Augmented Domain Adaptation AAAI 2024 Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis EACL 2024 Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization EMNLP 2024 Unpacking Bias: An Empirical Study of Bias Measurement Metrics, Mitigation Algorithms, and Their Interactions COLING 2024 Unsupervised Order Learning ICLR 2024 When Cohesion Lies in the Embedding Space: Embedding-Based Reference-Free Metrics for Topic Segmentation COLING 2024 AdaMS: Deep Metric Learning with Adaptive Margin and Adaptive Scale for Acoustic Word Discrimination Interspeech 2023