Pretraining

TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings AAAI 2025 TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras ICCV 2025 TESS 2: A Large-Scale Generalist Diffusion Language Model ACL 2025 Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP AAAI 2025 TFG-Flow: Training-free Guidance in Multimodal Generative Flow ICLR 2025 The 3D-PC: a benchmark for visual perspective taking in humans and machines ICLR 2025 The Double-Ellipsoid Geometry of CLIP ICML 2025 The Dynamic Duo of Collaborative Masking and Target for Advanced Masked Autoencoder Learning AAAI 2025 The FineView Dataset:A 3D Scanned Multi-View Object Dataset of Fine-Grained Category Instances WACV 2025 The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence ACL 2025 Time-to-Event Pretraining for 3D Medical Imaging ICLR 2025 TLLC: Transfer Learning-based Label Completion for Crowdsourcing ICML 2025 TokenUnify: Scaling Up Autoregressive Pretraining for Neuron Segmentation ICCV 2025 Towards Addressing Frontiers in Graph Generation AAAI 2025 Towards Foundation Models for Mixed Integer Linear Programming ICLR 2025 Towards General Visual-Linguistic Face Forgery Detection CVPR 2025 Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model CVPR 2025 Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language ACL 2025 Towards Pre-training an Effective Respiratory Audio Foundation Model Interspeech 2025 Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning ICCV 2025 Towards Universal Dataset Distillation via Task-Driven Diffusion CVPR 2025 TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes ICCV 2025 Transferable Post-training via Inverse Value Learning NAACL 2025 Transferable Relativistic Predictor: Mitigating Cross-Task Cold-Start Issue in NAS IJCAI 2025 TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning ICCV 2025