Skip to content Skip to sidebar Skip to footer

VL-Cogito: Advancing Multimodal Reasoning with Progressive Curriculum Reinforcement Learning

Multimodal reasoning, where models integrate and interpret information from multiple sources such as text, images, and diagrams, is a frontier challenge in AI. VL-Cogito is a state-of-the-art Multimodal Large Language Model (MLLM) proposed by DAMO Academy (Alibaba Group) and partners, introducing a robust reinforcement learning pipeline that fundamentally upgrades the reasoning skills of large models…

Read More

NASA Releases Galileo: The Open-Source Multimodal Model Advancing Earth Observation and Remote Sensing

Introduction Galileo is an open-source, highly multimodal foundation model developed to process, analyze, and understand diverse Earth observation (EO) data streams—including optical, radar, elevation, climate, and auxiliary maps—at scale. Galileo is developed with the support from researchers from McGill University, NASA Harvest Ai2, Carleton University, University of British Columbia, Vector Institute, and Arizona State University.…

Read More

NVIDIA AI Presents ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

Estimated reading time: 5 minutes Introduction Embodied AI agents are increasingly being called upon to interpret complex, multimodal instructions and act robustly in dynamic environments. ThinkAct, presented by researchers from Nvidia and National Taiwan University, offers a breakthrough for vision-language-action (VLA) reasoning, introducing reinforced visual latent planning to bridge high-level multimodal reasoning…

Read More

VLM2Vec-V2: A Unified Computer Vision Framework for Multimodal Embedding Learning Across Images, Videos, and Visual Documents

Embedding models act as bridges between different data modalities by encoding diverse multimodal information into a shared dense representation space. There have been advancements in embedding models in recent years, driven by progress in large foundation models. However, existing multimodal embedding models are trained on datasets such as MMEB and M-BEIR, with most focus only…

Read More

How Radial Attention Cuts Costs in Video Diffusion by 4.4× Without Sacrificing Quality

Introduction to Video Diffusion Models and Computational Challenges Diffusion models have made impressive progress in generating high-quality, coherent videos, building on their success in image synthesis. However, handling the extra temporal dimension in videos significantly increases computational demands, especially since self-attention scales poorly with sequence length. This makes it difficult to train or run these…

Read More

ByteDance Researchers Introduce VGR: A Novel Reasoning Multimodal Large Language Model (MLLM) with Enhanced Fine-Grained Visual Perception Capabilities

Why Multimodal Reasoning Matters for Vision-Language Tasks Multimodal reasoning enables models to make informed decisions and answer questions by combining both visual and textual information. This type of reasoning plays a central role in interpreting charts, answering image-based questions, and understanding complex visual documents. The goal is to make machines capable of using vision as…

Read More

Multimodal LLMs Without Compromise: Researchers from UCLA, UW–Madison, and Adobe Introduce X-Fusion to Add Vision to Frozen Language Models Without Losing Language Capabilities

LLMs have made significant strides in language-related tasks such as conversational AI, reasoning, and code generation. However, human communication extends beyond text, often incorporating visual elements to enhance understanding. To create a truly versatile AI, models need the ability to process and generate text and visual information simultaneously. Training such unified vision-language models from scratch…

Read More

Subject-Driven Image Evaluation Gets Simpler: Google Researchers Introduce REFVNLI to Jointly Score Textual Alignment and Subject Consistency Without Costly APIs

Text-to-image (T2I) generation has evolved to include subject-driven approaches, which enhance standard T2I models by incorporating reference images alongside text prompts. This advancement allows for more precise subject representation in generated images. Despite the promising applications, subject-driven T2I generation faces a significant challenge of lacking reliable automatic evaluation methods. Current metrics focus either on text-prompt…

Read More

ViSMaP: Unsupervised Summarization of Hour-Long Videos Using Meta-Prompting and Short-Form Datasets

Video captioning models are typically trained on datasets consisting of short videos, usually under three minutes in length, paired with corresponding captions. While this enables them to describe basic actions like walking or talking, these models struggle with the complexity of long-form videos, such as vlogs, sports events, and movies that can last over an…

Read More