Model Architecture

The Unreasonable Ineffectiveness of the Deeper Layers ICLR 2025 Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation CVPR 2025 ThunderKittens: Simple, Fast, and Adorable Kernels ICLR 2025 Till the Layers Collapse: Compressing a Deep Neural Network Through the Lenses of Batch Normalization Layers. AAAI 2025 TinyFoA: Memory Efficient Forward-Only Algorithm for On-Device Learning AAAI 2025 TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Research EMNLP 2025 TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba ICCV 2025 TKG-DM: Training-free Chroma Key Content Generation Diffusion Model CVPR 2025 ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge ICLR 2025 TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters ICLR 2025 TokensGen: Harnessing Condensed Tokens for Long Video Generation ICCV 2025 Top-Down Guidance for Learning Object-Centric Representations IJCAI 2025 Top-I2P: Explore Open-Domain Image-to-Point Cloud Registration Using Topology Relationship IJCAI 2025 Toward Robust Non-Transferable Learning: A Survey and Benchmark IJCAI 2025 Towards Accurate Binary Spiking Neural Networks: Learning with Adaptive Gradient Modulation Mechanism AAAI 2025 Towards a Unified Paradigm of Concept Editing in Large Language Models EMNLP 2025 Towards a Universal Image Degradation Model via Content-Degradation Disentanglement ICCV 2025 Towards Calibrated Deep Clustering Network ICLR 2025 Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather CVPR 2025 Towards Higher Effective Rank in Parameter-Efficient Fine-tuning using Khatri-Rao Product ICCV 2025 Towards Loss-Resilient Image Coding for Unstable Satellite Networks AAAI 2025 Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling ICLR 2025 Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning ICLR 2025 Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings ACL 2025 Towards Utilising a Range of Neural Activations for Comprehending Representational Associations WACV 2025