Search Results for author:
Found 15 papers, 8 papers with code
FiVL: A Framework for Improved Vision-Language Alignment
Large Vision Language Models (LVLMs) have achieved significant progress in integrating visual and textual inputs for multimodal reasoning.
A Noise is Worth Diffusion Guidance
Observing that noise obtained via diffusion inversion can reconstruct high-quality images without guidance, we focus on the initial noise of the denoising pipeline.
FastRM: An efficient and automatic explainability framework for multimodal generative models
While Large Vision Language Models (LVLMs) have become masterly capable in reasoning over human prompts and visual inputs, they are still prone to producing responses that contain misinformation.
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs
The widespread adoption of cloud-based proprietary large language models (LLMs) has introduced significant challenges, including operational dependencies, privacy concerns, and the necessity of continuous internet connectivity.
Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
In this paper, we focus on the alignment of recent text-to-image diffusion models, such as Stable Diffusion XL (SDXL), and find that this "reference mismatch" is indeed a significant problem in aligning these models due to the unstructured nature of visual modalities: e. g., a preference for a particular stylistic aspect can easily induce such a discrepancy.
Getting it Right: Improving Spatial Consistency in Text-to-Image Models
One of the key shortcomings in current text-to-image (T2I) models is their inability to consistently generate images which faithfully follow the spatial relationships specified in the text prompt.
DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models
In the realm of subject-driven text-to-image (T2I) generative models, recent developments like DreamBooth and BLIP-Diffusion have led to impressive results yet encounter limitations due to their intensive fine-tuning demands and substantial parameter requirements.
PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models
As a state-of-the-art, open-source image generation model, PIXART-{\delta} offers a promising alternative to the Stable Diffusion family of models, contributing significantly to text-to-image synthesis.
Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss
In this work, we introduce two scaled-down variants, Segmind Stable Diffusion (SSD-1B) and Segmind-Vega, with 1. 3B and 0. 74B parameter UNets, respectively, achieved through progressive removal using layer-level losses focusing on reducing the model size while preserving generative quality.
Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning
Floods wreak havoc throughout the world, causing billions of dollars in damages, and uprooting communities, ecosystems and economies.
Vision Transformers are Robust Learners
Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art (SOTA) standard accuracy.
Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report
To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms.
G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling
In this work, we propose that, with the normalized temperature-scaled cross-entropy (NT-Xent) loss function (as used in SimCLR), it is beneficial to not have images of the same category in the same batch.
G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling
In this work, we propose that, with the normalized temperature-scaled cross-entropy (NT-Xent) loss function (as used in SimCLR), it is beneficial to not have images of the same category in the same batch.
