Submitted by akhaliq 28 DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data · 9 authors 3
Submitted by akhaliq 15 LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models · 5 authors 9
Submitted by akhaliq 11 Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation · 7 authors 1
Submitted by akhaliq 10 Improved Distribution Matching Distillation for Fast Image Synthesis · 7 authors
Submitted by akhaliq 9 AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability · 7 authors
Submitted by akhaliq 8 RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance · 12 authors
Submitted by akhaliq 8 DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis · 8 authors
Submitted by akhaliq 8 CamViG: Camera Aware Image-to-Video Generation with Multimodal Transformers · 6 authors 1
Submitted by akhaliq 7 NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections · 7 authors
Submitted by akhaliq 6 Neural Directional Encoding for Efficient and Accurate View-Dependent Appearance Modeling · 8 authors
Submitted by akhaliq 5 Tele-Aloha: A Low-budget and High-authenticity Telepresence System Using Sparse RGB Cameras · 12 authors