Deep Learning

PlaNet: Learning to Mitigate Atmospheric Turbulence in Planetary Images AAAI 2025 Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding ICCV 2025 PriFold: Biological Priors Improve RNA Secondary Structure Predictions AAAI 2025 Probing Neural Network Generalization using Default Patterns NAACL 2025 Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss ICCV 2025 Psych-Occlusion: using Visual Psychophysics for Aerial Detection of Occluded Persons during Search and Rescue WACV 2025 PwnGPT: Automatic Exploit Generation Based on Large Language Models ACL 2025 Quad-Pixel Image Defocus Deblurring: A New Benchmark and Model CVPR 2025 R-DTI: Drug Target Interaction Prediction Based on Second-Order Relevance Exploration AAAI 2025 Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling NAACL 2025 ReDiffDet: Rotation-equivariant Diffusion Model for Oriented Object Detection CVPR 2025 Re-Evaluating Group Robustness via Adaptive Class-Specific Scaling WACV 2025 REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research? ACL 2025 ReTracker: Exploring Image Matching for Robust Online Any Point Tracking ICCV 2025 Revisiting Pruning vs Quantization for Small Language Models EMNLP 2025 Rust-doctor: Enhanced Feature for Rust Ownership and Lifetime Repair with Balanced Training Data Generation EMNLP 2025 SADSLyC: A Corpus for Saudi Arabian Multi-dialect Identification through Song Lyrics COLING 2025 sDPO: Don’t Use Your Data All at Once COLING 2025 SEP: A General Lossless Compression Framework with Semantics Enhancement and Multi-Stream Pipelines IJCAI 2025 SET: Spectral Enhancement for Tiny Object Detection CVPR 2025 SIC: Similarity-Based Interpretable Image Classification with Neural Networks ICCV 2025 SIDL: A Real-World Dataset for Restoring Smartphone Images with Dirty Lenses AAAI 2025 Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion AAAI 2025 Snakes and Ladders: Two Steps Up for VideoMamba ICCV 2025 SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal CVPR 2025