Representation Learning

Improving Quotation Attribution with Fictional Character Embeddings EMNLP 2024 Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective NeurIPS 2024 Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures ECCV 2024 Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective AISTATS 2024 Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders NeurIPS 2024 Improving Spectral Snapshot Reconstruction with Spectral-Spatial Rectification CVPR 2024 Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer Interspeech 2024 Improving Subgroup Robustness via Data Selection NeurIPS 2024 Improving Unsupervised Hierarchical Representation with Reinforcement Learning CVPR 2024 Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping CVPR 2024 In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging CVPR 2024 Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation EMNLP 2024 Inconsistency of Cross-Validation for Structure Learning in Gaussian Graphical Models AISTATS 2024 In-context Autoencoder for Context Compression in a Large Language Model ICLR 2024 In-Context Language Learning: Architectures and Algorithms ICML 2024 In-Context Symmetries: Self-Supervised Learning through Contextual World Models NeurIPS 2024 In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering ICML 2024 Incorporating Precedents for Legal Judgement Prediction on European Court of Human Rights Cases EMNLP 2024 Incorporating Word Count Information into Depression Risk Summary Generation: INF@UoS CLPsych 2024 Submission EACL 2024 Increasing Biases Can Be More Efficient Than Increasing Weights WACV 2024 Incremental Residual Concept Bottleneck Models CVPR 2024 Indirectly Parameterized Concrete Autoencoders ICML 2024 Individuation in Neural Models with and without Visual Grounding EMNLP 2024 Inducing Systematicity in Transformers by Attending to Structurally Quantized Embeddings ACL 2024 Inductive biases of multi-task learning and finetuning: multiple regimes of feature reuse NeurIPS 2024