| Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation | Apr 13, 2025 | Data AugmentationEmotion-Cause Pair Extraction | CodeCode Available | 0 |
| ContrastiveGaussian: High-Fidelity 3D Generation with Contrastive Learning and Gaussian Splatting | Apr 10, 2025 | 3D GenerationContrastive Learning | CodeCode Available | 0 |
| Multi-Task Learning with Multi-Annotation Triplet Loss for Improved Object Detection | Apr 10, 2025 | Multi-Task Learningobject-detection | CodeCode Available | 0 |
| Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments | Apr 10, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| ID-Booth: Identity-consistent Face Generation with Diffusion Models | Apr 10, 2025 | DenoisingDiversity | CodeCode Available | 1 |
| AsyReC: A Multimodal Graph-based Framework for Spatio-Temporal Asymmetric Dyadic Relationship Classification | Apr 7, 2025 | Graph Neural NetworkTriplet | CodeCode Available | 0 |
| Subjective Visual Quality Assessment for High-Fidelity Learning-Based Image Compression | Apr 7, 2025 | BenchmarkingImage Compression | CodeCode Available | 0 |
| Scaling Prompt Instructed Zero Shot Composed Image Retrieval with Image-Only Data | Apr 1, 2025 | Image RetrievalRetrieval | —Unverified | 0 |
| LANID: LLM-assisted New Intent Discovery | Mar 31, 2025 | Intent DiscoveryTask-Oriented Dialogue Systems | CodeCode Available | 0 |
| FreeSplat++: Generalizable 3D Gaussian Splatting for Efficient Indoor Scene Reconstruction | Mar 29, 2025 | 3DGSIndoor Scene Reconstruction | CodeCode Available | 2 |
