Trending Research
Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis.
YOLOE: Real-Time Seeing Anything
THU-MIG/yoloe
•
•
Object detection and segmentation are widely employed in computer vision applications, yet conventional models like YOLO series, while efficient and accurate, are limited by predefined categories, hindering adaptability in open scenarios.
Neural Fields with Thermal Activations for Arbitrary-Scale Super-Resolution
prs-eth/thera
•
•
We present a novel way to design neural fields such that points can be queried with an adaptive Gaussian PSF, so as to guarantee correct anti-aliasing at any desired output resolution.
Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Diffusion language models offer unique benefits over autoregressive models due to their potential for parallelized generation and controllability, yet they lag in likelihood modeling and are limited to fixed-length generation.
Agent S: An Open Agentic Framework that Uses Computers Like a Human
We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks.
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
gojasper/lbm
•
•
In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image translation.
FoundationStereo: Zero-Shot Stereo Matching
However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks - remains challenging for stereo matching.
Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k
With this model, we demonstrate that the cost of training a top-performing video generation model is highly controllable.
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
osilly/vision-r1
•
•
However, direct training with RL struggles to activate complex reasoning capabilities such as questioning and reflection in MLLMs, due to the absence of substantial high-quality multimodal reasoning data.
Slim attention: cut your context memory in half without loss of accuracy -- K-cache is all you need for MHA
openmachine-ai/transformer-tricks
•
•
For encoder-decoder transformers, the context memory size can be reduced even further: For the Whisper models for example, slim attention reduces the context memory by 8x, which can speed up token generation by 5x for batch size 64 for example.
