Pretraining

PanFoMa: A Lightweight Foundation Model and Benchmark for Pan-Cancer AAAI 2026 Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models AAAI 2026 PEFT-BoA: Parameter-Efficient Fine-Tuning with Bag-of-Adapters for Multi-Modal Object Re-identification AAAI 2026 Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training ACL 2026 PharmaQA: Prompt-Based Molecular Representation Learning via Pharmacophore-Oriented Question Answering AAAI 2026 PlantTraitNet: An Uncertainty-Aware Multimodal Framework for Global-Scale Plant Trait Inference from Citizen Science Data AAAI 2026 Practical Guidelines for Model Merging in LLMs Pre-Training ACL 2026 Promptus: Can Prompt Streaming Replace Video Streaming AAAI 2026 QueryCraft: Transformer-Guided Query Initialization for Enhanced Human-Object Interaction Detection AAAI 2026 ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models AAAI 2026 RegionMarker: A Region-Triggered Semantic Watermarking Framework for Embedding-as-a-Service Copyright Protection AAAI 2026 Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training CVPR 2026 Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction AAAI 2026 RiverScope: High-Resolution River Masking Dataset AAAI 2026 RobustFormer: Noise-Robust Pre-training for Images and Videos WACV 2026 Robust Pseudo-Labeling via Decoupled Class-Aware Filtering and Dynamic Category Correction AAAI 2026 SAFE: Semantic- and Frequency-Enhanced Curriculum for Cross-Domain Deepfake Detection AAAI 2026 Scalable Vision-Guided Crop Yield Estimation AAAI 2026 Scale Is All You Need: Analyzing Modality Interaction and Speaker Intent Without Fine-Tuning EACL 2026 Scaling-up Perceptual Video Quality Assessment AAAI 2026 SciPedia: Unlocking the Value of Scientific Data for Pre-training ACL 2026 SCORE: Semantic Collage by Optimizing Rendered Elements AAAI 2026 Semantic Embedding and Synthetic Augmentation for Longitudinal Survey Prediction (Student Abstract) AAAI 2026 Sequence-Free for Compound Protein Interaction Prediction AAAI 2026 SGPFeat: Semantic and Geometric Priors for Multi-modal Image Matching AAAI 2026