Trending Research
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.
Equivariant Similarity for Vision-Language Foundation Models
wangt-cn/eqben
•
•
Unlike the existing image-text similarity objective which only categorizes matched pairs as similar and unmatched pairs as dissimilar, equivariance also requires similarity to vary faithfully according to the semantic changes.
LLaMA: Open and Efficient Foundation Language Models
tatsu-lab/stanford_alpaca
•
•
arXiv 2023
We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters.
Ranked #1 on
Question Answering
on PIQA
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.
Training language models to follow instructions with human feedback
In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback.
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.
Your Diffusion Model is Secretly a Zero-Shot Classifier
Finally, we use Diffusion Classifier to extract standard classifiers from class-conditional diffusion models trained on ImageNet.
Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
KU-CVLAB/3DFuse
•
•
Text-to-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neural radiance field (NeRF) in the zero-shot setting.
GLM-130B: An Open Bilingual Pre-trained Model
thudm/glm-130b
•
•
We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters.
Ranked #1 on
Language Modelling
on CLUE (CMRC2018)
Reflexion: an autonomous agent with dynamic memory and self-reflection
To achieve full automation, we introduce a straightforward yet effective heuristic that enables the agent to pinpoint hallucination instances, avoid repetition in action sequences, and, in some environments, construct an internal memory map of the given environment.
