Trending Research
QA-MDT: Quality-aware Masked Diffusion Transformer for Enhanced Music Generation
ivcylc/qa-mdt
•
•
In recent years, diffusion-based text-to-music (TTM) generation has gained prominence, offering an innovative approach to synthesizing musical content from textual descriptions.
Ranked #1 on
Music Generation
on Song Describer Dataset
Revisit Anything: Visual Place Recognition via Image Segment Retrieval
This poses a fundamental challenge in matching two images of the same place captured from different camera viewpoints: "the similarity of what overlaps can be dominated by the dissimilarity of what does not overlap".
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
The fusion of both visual and LiDAR measurements is based on a single unified voxel map where the LiDAR module constructs the geometric structure for registering new LiDAR scans and the visual module attaches image patches to the LiDAR points.
YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
It can be used to obtain complete information, so that train-from-scratch models can achieve better results than state-of-the-art models pre-trained using large datasets, the comparison results are shown in Figure 1.
Ranked #7 on
Real-Time Object Detection
on MS COCO
LLaMA-Omni: Seamless Speech Interaction with Large Language Models
We build our model based on the latest Llama-3. 1-8B-Instruct model.
OverFlow: Putting flows on top of neural transducers for better TTS
coqui-ai/TTS
•
•
Neural HMMs are a type of neural transducer recently proposed for sequence-to-sequence modelling in text-to-speech.
Ranked #11 on
Text-To-Speech Synthesis
on LJSpeech
(using extra training data)
CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility
zibojia/COCOCO
•
•
To this end, this paper proposes a novel text-guided video inpainting model that achieves better consistency, controllability and compatibility.
StyleBooth: Image Style Editing with Multimodal Instruction
We integrate encoded textual instruction and image exemplar as a unified condition for diffusion model, enabling the editing of original image following multimodal instructions.
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction
salesforceairesearch/gemfilter
•
•
Our research introduces a novel approach for the long context bottleneck to accelerate LLM inference and reduce GPU memory consumption.
SoundStorm: Efficient Parallel Audio Generation
lucidrains/soundstorm-pytorch
•
•
We present SoundStorm, a model for efficient, non-autoregressive audio generation.
