Trending Research
NEFTune: Noisy Embeddings Improve Instruction Finetuning
openaccess-ai-collective/axolotl
•
•
We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation.
DeepSeek-VL: Towards Real-World Vision-Language Understanding
The DeepSeek-VL family (both 1. 3B and 7B models) showcases superior user experiences as a vision-language chatbot in real-world applications, achieving state-of-the-art or competitive performance across a wide range of visual-language benchmarks at the same model size while maintaining robust performance on language-centric benchmarks.
Ranked #31 on
Visual Question Answering
on MM-Vet
Imp: Highly Capable Large Multimodal Models for Mobile Devices
milvlg/imp
•
•
By harnessing the capabilities of large language models (LLMs), recent large multimodal models (LMMs) have shown remarkable versatility in open-world multimodal understanding.
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
We first construct the Feedback Collection, a new dataset that consists of 1K fine-grained score rubrics, 20K instructions, and 100K responses and language feedback generated by GPT-4.
AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One
nvlabs/radio
•
•
A handful of visual foundation models (VFMs) have recently emerged as the backbones for numerous downstream tasks.
VILA: On Pre-training for Visual Language Models
nvlabs/vila
•
•
Visual language models (VLMs) rapidly progressed with the recent success of large language models.
Ranked #24 on
Visual Question Answering
on MM-Vet
xFinder: Robust and Pinpoint Answer Extraction for Large Language Models
The continuous advancement of large language models (LLMs) has brought increasing attention to the critical issue of developing fair and reliable methods for evaluating their performance.
Outlier-robust Kalman Filtering through Generalised Bayes
gerdm/weighted-likelihood-filter
•
•
We derive a novel, provably robust, and closed-form Bayesian update rule for online filtering in state-space models in the presence of outliers and misspecified measurement models.
MMBench: Is Your Multi-modal Model an All-around Player?
In response to these challenges, we propose MMBench, a novel multi-modality benchmark.
MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise
Current fundus image analysis models are predominantly built for specific tasks relying on individual datasets.
