2025-01-22s

Video Depth Anything achieves consistent depth estimation for super-long videos by enhancing Depth Anything V2 with a spatial-temporal head and a novel temporal consistency loss, setting a new state-o…

UI-TARS, a novel native GUI agent, achieves state-of-the-art performance by solely using screenshots as input, eliminating the need for complex agent frameworks and expert-designed workflows.

TokenVerse: Extract & combine visual concepts from multiple images for creative image generation!

MMVU: a new benchmark pushes multimodal video understanding to expert level, revealing limitations of current models and paving the way for more advanced AI.

InternLM-XComposer2.5-Reward: A novel multi-modal reward model boosting Large Vision Language Model performance.

Hunyuan3D 2.0: A groundbreaking open-source system generating high-resolution, textured 3D assets using scalable diffusion models, exceeding state-of-the-art performance.

GPS-guided image generation is here! This paper leverages GPS data to create highly realistic images reflecting specific locations, even reconstructing 3D models from 2D photos.

Democratizing advanced reasoning in AI, this blueprint introduces a modular framework for building Reasoning Language Models (RLMs), simplifying development and enhancing accessibility.

Mobile-Agent-E: A self-evolving mobile assistant conquering complex tasks with hierarchical agents and a novel self-evolution module, significantly outperforming prior approaches.

Agent-R: A novel self-training framework enables language model agents to learn from errors by dynamically constructing training data that corrects erroneous actions, resulting in significantly improv…

EMO2 achieves realistic audio-driven avatar video generation by employing a two-stage framework: first generating hand poses directly from audio and then using a diffusion model to synthesize full-bod…

New multimodal safety test suite (MSTS) reveals vision-language models’ vulnerabilities and underscores the unique challenges of multimodal inputs.