Trending Research
Zero-Shot Tokenizer Transfer
bminixhofer/zett
•
•
Finally, we show that a ZeTT hypernetwork trained for a base (L)LM can also be applied to fine-tuned variants without extra training.
LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks
We explore the intersection of LLMs and penetration testing to gain insight into their capabilities and challenges in the context of privilege escalation.
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation.
From NeRFs to Gaussian Splats, and Back
grasp-lyrl/nerftogsandback
•
•
For robotics applications where there is a limited number of (typically ego-centric) views, parametric representations such as neural radiance fields (NeRFs) generalize better than non-parametric ones such as Gaussian splatting (GS) to views that are very different from those in the training data; GS however can render much faster than NeRFs.
Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
lllyasviel/fooocus
•
•
ICCV 2023
Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity.
RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment
weixiongust/rlhf-reward-modeling
•
•
Utilizing a reward model and a sufficient number of samples, our approach selects the high-quality samples, discarding those that exhibit undesired behavior, and subsequently enhancing the model by fine-tuning on these filtered samples.
depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers
thuml/depyf
•
•
PyTorch \texttt{2. x} introduces a compiler designed to accelerate deep learning programs.
Libra: Building Decoupled Vision System on Large Language Models
yifanxu74/libra
•
•
Specifically, we incorporate a routed visual expert with a cross-modal bridge module into a pretrained LLM to route the vision and language flows during attention computing to enable different attention patterns in inner-modal modeling and cross-modal interaction scenarios.
Unified Training of Universal Time Series Forecasting Transformers
SalesforceAIResearch/uni2ts
•
•
Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models.
A Survey on Vision Mamba: Models, Applications and Challenges
ruixxxx/awesome-vision-mamba-models
•
•
To help keep pace with the rapid advancements in computer vision, this paper aims to provide a comprehensive review of visual Mamba approaches.
