encoder-decoder architecture

Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction WACV 2026 BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification CVPR 2026 Complex Mathematical Expression Recognition: Benchmark, Large-Scale Dataset and Strong Baseline AAAI 2026 DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization CVPR 2026 Digitizing Nepal’s Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts ACL 2026 DREAM: Document Recognition with Explicit Adaptive Memory CVPR 2026 FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolution CVPR 2026 Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction AAAI 2026 RMAE-ProGRess: Advancing Semantic Segmentation in Unstructured Environments CVPR 2026 SAM 3D Body: Robust Full-Body Human Mesh Recovery CVPR 2026 Scaling View Synthesis Transformers CVPR 2026 SEAM: Bridging the Temporal-Semantic Granularity Gap for LLM-based Speech Recognition EACL 2026 VGent: Visual Grounding via Modular Design for Disentangling Reasoning and Prediction CVPR 2026 AEHRC at BioLaySumm 2025: Leveraging T5 for Lay Summarisation of Radiology Reports ACL 2025 BARTABSA++: Revisiting BARTABSA with Decoder LLMs ACL 2025 Beyond Attacks: Advancing Fake Speech Detection with Attack-Agnostic Methods Interspeech 2025 Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation ACL 2025 Blood Flow Speed Estimation with Optical Coherence Tomography Angiography Images CVPR 2025 CiteBART: Learning to Generate Citations for Local Citation Recommendation EMNLP 2025 DeDisCo at the DISRPT 2025 Shared Task: A System for Discourse Relation Classification EMNLP 2025 Degradation-Aware Feature Perturbation for All-in-One Image Restoration CVPR 2025 DeNC: Unleash Neural Codecs in Video Streaming with Diffusion Enhancement AAAI 2025 EduCSW: Building a Mandarin-English Code-Switched Generation Pipeline for Computer Science Learning ACL 2025 Exploiting Bispectral Features for Single-Channel Speech Enhancement Interspeech 2025 GarFast: Realistic and Fast Garment Transfer with a Simplified Parser-Free Approach AAAI 2025