Deep Learning

LightThinker: Thinking Step-by-Step Compression EMNLP 2025 Light Transport-aware Diffusion Posterior Sampling for Single-View Reconstruction of 3D Volumes CVPR 2025 Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables ICCV 2025 Lightweight and Robust Multi-Channel End-to-End Speech Recognition with Spherical Harmonic Transform Interspeech 2025 Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence NAACL 2025 Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval AAAI 2025 Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty ICML 2025 Lightweight Front-end Enhancement for Robust ASR via Frame Resampling and Sub-Band Pruning Interspeech 2025 Lightweight Gradient-Aware Upscaling of 3D Gaussian Splatting Images ICCV 2025 Lightweight Safety Guardrails Using Fine-tuned BERT Embeddings COLING 2025 Lightweight Speech Enhancement Model Based on Harmonic Attention and Phase Estimation with Skin-Attachable Accelerometer Interspeech 2025 Lightweight Yet Fine-Grained: A Graph Capsule Convolutional Network with Subspace Alignment for Shared-Account Sequential Recommendation AAAI 2025 Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading AAAI 2025 LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval EMNLP 2025 LimaCost: Data Valuation for Instruction Tuning of Large Language Models EMNLP 2025 LIME: Localized Image Editing via Attention Regularization in Diffusion Models WACV 2025 Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition - And Ways to Overcome Them AAAI 2025 Limitations of Religious Data and the Importance of the Target Domain: Towards Machine Translation for Guinea-Bissau Creole NAACL 2025 Limited-Resource Adapters Are Regularizers, Not Linguists ACL 2025 Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory ICLR 2025 LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes CVPR 2025 LimRank: Less is More for Reasoning-Intensive Information Reranking EMNLP 2025 Linear Attention Modeling for Learned Image Compression CVPR 2025 Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better ICLR 2025 Linear combinations of latents in generative models: subspaces and beyond ICLR 2025