Trending Research
3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
In this paper, we fully utilize the facial part segmentation geometry by introducing Part Re-projection Distance Loss (PRDL).
Ranked #3 on
3D Face Reconstruction
on REALY (side-view)
SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing
modelscope/swift
•
•
Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis.
Grokfast: Accelerated Grokking by Amplifying Slow Gradients
ironjr/grokfast
•
•
One puzzling artifact in machine learning dubbed grokking is where delayed generalization is achieved tenfolds of iterations after near perfect overfitting to the training data.
Scalable MatMul-free Language Modeling
Our experiments show that our proposed MatMul-free models achieve performance on-par with state-of-the-art Transformers that require far more memory during inference at a scale up to at least 2. 7B parameters.
GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning
cmavro/gnn-rag
•
•
In our GNN-RAG framework, the GNN acts as a dense subgraph reasoner to extract useful graph information, while the LLM leverages its natural language processing ability for ultimate KGQA.
U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
Diffusion Transformers (DiTs) introduce the transformer architecture to diffusion tasks for latent-space image generation.
CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
We present a novel generative 3D modeling system, coined CraftsMan, which can generate high-fidelity 3D geometries with highly varied shapes, regular mesh topologies, and detailed surfaces, and, notably, allows for refining the geometry in an interactive manner.
Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis
zhangzc21/dyntet
•
•
Recent works in implicit representations, such as Neural Radiance Fields (NeRF), have advanced the generation of realistic and animatable head avatars from video sequences.
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
openbmb/minicpm
•
•
For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation.
Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images.
