🖼️ Multimodal AI - hop1.ng.1357 · Scour

Can Multimodal Large Language Models Truly Understand Small Objects? ✨Gemini

CinemaCLIP — A hybrid CLIP model for the visual language of cinema ✨Gemini

ozu.ai·6d·Hacker News

Mm – Unix tools (find/cat/grep) rebuilt for the multimodal era 🕷️Web Crawling

vlm.run·8h·Hacker News

SketchVLM: Vision-Language Models Can Annotate Images to Explain Thoughts and Guide Users ✨Gemini

sketchvlm.github.io·1d·Hacker News

TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment 🎖Text Quality Models

gdm-tipsv2.github.io·6d·Hacker News

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents ✨Gemini

huggingface.co·2d·Hacker News

Delineating Knowledge Boundaries for Honest Large Vision-Language Models ✨Gemini

Zorq AI – Multimodal workspace for video, image, and voice generation ✨Gemini

zorq-ai.io·1d·Hacker News

typomonster/parlor-jarvis: On-device, real-time multimodal AI. Multilingual voice + vision (en/ko/es/pt/fr) with camera, screen, PDF, and video — runs entirely locally. ✨Gemini

github.com·4d·Hacker News

Benchmarking Complex Multimodal Document Processing Pipelines: A Unified Evaluation Framework for Enterprise AI 🔍Information Extraction

NVIDIA Nemotron 3 Nano Omni Powers Multimodal Agent Reasoning in a Single Efficient Open Model ✨Gemini

developer.nvidia.com·2d·Hacker News

Three-Step Nav: A Hierarchical Global-Local Planner for Zero-Shot Vision-and-Language Navigation 🤝Human-AI Collaboration

SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations ✨Gemini

World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning ✨Gemini

$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills ✨Gemini

Source-Modality Monitoring in Vision-Language Models ✨Gemini

Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning 🎯Alignment Research

EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs ✨Gemini

FASH-iCNN: Making Editorial Fashion Identity Inspectable Through Multimodal CNN Probing ✨Gemini

A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration 🤝Human-AI Collaboration

Log in to enable infinite scrolling