Trending Research
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
However, existing methods are limited to challenging image-based forecasting, which suffers from redundant information and lacks comprehensive and critical world knowledge, including dynamic, spatial and semantic information.
Ranked #1 on
Robot Manipulation
on CALVIN
PresentAgent: Multimodal Agent for Presentation Video Generation
We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos.
Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts
lileyang1210/ant
•
•
Anchor-free methods risk disrupting sampling trajectories, leading to visual artifacts, while anchor-based methods rely on the heuristic selection of anchor concepts.
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
aidc-ai/awesome-unified-multimodal-models
•
•
Despite their respective successes, these two domains have evolved independently, leading to distinct architectural paradigms: While autoregressive-based architectures have dominated multimodal understanding, diffusion-based models have become the cornerstone of image generation.
From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
Supported by benchmark results and the rise of open-source implementations, we demonstrate that Agentic Deep Research not only significantly outperforms existing approaches, but is also poised to become the dominant paradigm for future information seeking.
ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization
The field of Fake Image Detection and Localization (FIDL) is highly fragmented, encompassing four domains: deepfake detection (Deepfake), image manipulation detection and localization (IMDL), artificial intelligence-generated image detection (AIGC), and document image manipulation localization (Doc).
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
alibaba/roll
•
•
First, a single-controller architecture combined with an abstraction of the parallel worker simplifies the development of the training pipeline.
Aligning Anime Video Generation with Human Feedback
Existing reward models, designed primarily for real-world videos, fail to capture the unique appearance and consistency requirements of anime.
Kinetics: Rethinking Test-Time Scaling Laws
We rethink test-time scaling laws from a practical efficiency perspective, revealing that the effectiveness of smaller models is significantly overestimated.
Cradle: Empowering Foundation Agents Towards General Computer Control
To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i. e., using screenshots as input and keyboard and mouse actions as output.
