Trending Research
ChatDoctor: A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge
Recent large language models (LLMs) in the general domain, such as ChatGPT, have shown remarkable success in following instructions and producing human-like responses.
PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters
shuhongchen/panic3d-anime-reconstruction
•
•
We propose PAniC-3D, a system to reconstruct stylized 3D character heads directly from illustrated (p)ortraits of (ani)me (c)haracters.
Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators
Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets.
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
In this work, we investigate the problem of creating high-fidelity 3D content from only a single image.
Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator.
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
BlinkDL/RWKV-LM
•
•
We propose SmoothQuant, a training-free, accuracy-preserving, and general-purpose post-training quantization (PTQ) solution to enable 8-bit weight, 8-bit activation (W8A8) quantization for LLMs.
Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation
Key to Fantasia3D is the disentangled modeling and learning of geometry and appearance.
Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases
However current research rarely studies the impact of different amounts of instruction data on model performance, especially in the real-world use cases.
LoRA: Low-Rank Adaptation of Large Language Models
We propose Low-Rank Adaptation, or LoRA, which freezes the pre-trained model weights and injects trainable rank decomposition matrices into each layer of the Transformer architecture, greatly reducing the number of trainable parameters for downstream tasks.
More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models
In such attacks, an adversary can prompt the LLM to produce malicious content or override the original instructions and the employed filtering schemes.
