Trending Research
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
We present InstantMesh, a feed-forward framework for instant 3D mesh generation from a single image, featuring state-of-the-art generation quality and significant training scalability.
OLAPH: Improving Factuality in Biomedical Long-form Question Answering
dmis-lab/olaph
•
•
We highlight that, even on evaluation metrics not used during training, LLMs trained with our OLAPH framework demonstrate significant performance improvement in factuality.
UFO: A UI-Focused Agent for Windows OS Interaction
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision.
FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets
ai4finance-foundation/fingpt
•
•
This paper introduces a distinctive approach anchored in the Instruction Tuning paradigm for open-source large language models, specifically adapted for financial contexts.
Speaker Embedding-aware Neural Diarization for Flexible Number of Speakers with Textual Information
alibaba-damo-academy/FunASR
•
•
In this paper, we reformulate this task as a single-label prediction problem by encoding the multi-speaker labels with power set.
GPQA: A Graduate-Level Google-Proof Q&A Benchmark
We present GPQA, a challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry.
emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation
alibaba-damo-academy/FunASR
•
•
To the best of our knowledge, emotion2vec is the first universal representation model in various emotion-related tasks, filling a gap in the field.
QLoRA: Efficient Finetuning of Quantized LLMs
internlm/xtuner
•
•
NeurIPS 2023
Our best model family, which we name Guanaco, outperforms all previous openly released models on the Vicuna benchmark, reaching 99. 3% of the performance level of ChatGPT while only requiring 24 hours of finetuning on a single GPU.
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.
Improving Diffusion Models for Virtual Try-on
yisol/IDM-VTON
•
•
Finally, we present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity.
Ranked #1 on
Virtual Try-on
on VITON-HD
