Trending Research
Matching Anything by Segmenting Anything
The robust association of the same objects across video frames in complex scenes is crucial for many applications, especially Multiple Object Tracking (MOT).
LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images
openbmb/omnilmm
•
•
To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution.
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
We introduce Buffer of Thoughts (BoT), a novel and versatile thought-augmented reasoning approach for enhancing accuracy, efficiency and robustness of large language models (LLMs).
Vision-LSTM: xLSTM as Generic Vision Backbone
Transformers are widely used as generic backbones in computer vision, despite initially introduced for natural language processing.
Fast Timing-Conditioned Latent Audio Diffusion
stability-ai/stable-audio-tools
•
•
Generating long-form 44. 1kHz stereo audio from text prompts can be computationally demanding.
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Simultaneous speech-to-speech translation (Simul-S2ST, a. k. a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication.
Ranked #1 on
de-en
on CVSS
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Creating high-quality scientific figures can be time-consuming and challenging, even though sketching ideas on paper is relatively easy.
Scalable MatMul-free Language Modeling
Our experiments show that our proposed MatMul-free models achieve performance on-par with state-of-the-art Transformers that require far more memory during inference at a scale up to at least 2. 7B parameters.
AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
Building generalist agents that can handle diverse tasks and evolve themselves across different environments is a long-term goal in the AI community.
Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
In this paper, we propose an efficient, fast, and versatile distillation method to accelerate the generation of pre-trained diffusion models: Flash Diffusion.
