Trending Research
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
Furthermore, we adopt a simple concatenation operation to integrate the reference appearance into the model and incorporate the pose information of the reference image for enhanced pose alignment.
PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters
Emergency of DeepSeek R1 and QwQ 32B have broken through performance barriers for running frontier large language models (LLMs) on home devices.
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
We show that while diffusion loss is ineffective, end-to-end training can be unlocked through the representation-alignment (REPA) loss -- allowing both VAE and diffusion model to be jointly tuned during the training process.
Liquid: Language Models are Scalable Multi-modal Generators
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared feature space for both vision and language.
Advanced Video Inpainting Using Optical Flow-Guided Efficient Diffusion
nevsnev/fgdvi
•
•
Specifically, FloED employs a dual-branch architecture, where a flow branch first restores corrupted flow and a multi-scale flow adapter provides motion guidance to the main inpainting branch.
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
microsoft/bitnet
•
•
The advent of 1-bit large language models (LLMs), led by BitNet b1. 58, has spurred interest in ternary LLMs.
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
AI is increasingly playing a pivotal role in transforming how scientific discoveries are made.
UniK3D: Universal Camera Monocular 3D Estimation
Monocular 3D estimation is crucial for visual perception.
Ranked #2 on
Monocular Depth Estimation
on KITTI Eigen split
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e. g., keyboard and mouse operations).
BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence
In embodied intelligence systems, a key component is 3D perception algorithm, which enables agents to understand their surrounding environments.
