Controllable generation with text-to-image diffusion models: A survey
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the
landscape, marking a significant shift in capabilities with their impressive text-guided …
landscape, marking a significant shift in capabilities with their impressive text-guided …
Reslora: Identity residual mapping in low-rank adaption
As one of the most popular parameter-efficient fine-tuning (PEFT) methods, low-rank
adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs) …
adaptation (LoRA) is commonly applied to fine-tune large language models (LLMs) …
DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model
Abstract Text-to-image (T2I) generative models have attracted significant attention and found
extensive applications within and beyond academic research. For example the Civitai …
extensive applications within and beyond academic research. For example the Civitai …
Mixlora: Enhancing large language models fine-tuning with lora based mixture of experts
Large Language Models (LLMs) have showcased exceptional performance across a wide
array of Natural Language Processing (NLP) tasks. Fine-tuning techniques are commonly …
array of Natural Language Processing (NLP) tasks. Fine-tuning techniques are commonly …
Diffusion illusions: Hiding images in plain sight
We explore the problem of computationally generating specialprime'images that produce
optical illusions when physically arranged and viewed in a certain way. First, we propose a …
optical illusions when physically arranged and viewed in a certain way. First, we propose a …
Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic Forgetting
H Chen, PN Garner - arXiv preprint arXiv:2402.12220, 2024 - arxiv.org
Although motivated by the adaptation of text-to-speech synthesis models, we argue that
more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such …
more generic parameter-efficient fine-tuning (PEFT) is an appropriate framework to do such …
Balanced Orthogonal Subspace Separation Detector for Few-Shot Object Detection in Aerial Imagery
H Jiang, Q Wang, J Feng, G Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Few-shot object detection (FSOD) in remote sensing images (RSIs) aims to achieve object
location and classification with only few training samples. Currently, mainstream transfer …
location and classification with only few training samples. Currently, mainstream transfer …
A Survey on Personalized Content Synthesis with Diffusion Models
Recent advancements in generative models have significantly impacted content creation,
leading to the emergence of Personalized Content Synthesis (PCS). With a small set of user …
leading to the emergence of Personalized Content Synthesis (PCS). With a small set of user …
LoRA Training in the NTK Regime has No Spurious Local Minima
Low-rank adaptation (LoRA) has become the standard approach for parameter-efficient fine-
tuning of large language models (LLM), but our theoretical understanding of LoRA has been …
tuning of large language models (LLM), but our theoretical understanding of LoRA has been …
SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules
Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large
models, including large language models for natural language processing and diffusion …
models, including large language models for natural language processing and diffusion …