↓Skip to main content

Vision-Language Models

Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding
·4505 words·22 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Tsinghua University
Parameter-Inverted Image Pyramid Networks (PIIP) drastically cut visual model computing costs without sacrificing accuracy by using smaller models for higher-resolution images and larger models for lo…
Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
·22812 words·108 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 University of Würzburg
Centurio: a 100-language LVLMs achieves state-of-the-art multilingual performance by strategically incorporating non-English data in training, proving that multilingualism doesn’t hinder English profi…
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
·2599 words·13 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Zhejiang University
InfiGUIAgent, a novel multimodal GUI agent, leverages a two-stage training pipeline to achieve advanced reasoning and GUI interaction capabilities, outperforming existing models in benchmarks.
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
·4541 words·22 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Peking University
Sa2VA marries SAM2 and LLaVA for dense grounded image and video understanding, achieving state-of-the-art results on multiple benchmarks.
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token
·5398 words·26 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Key Laboratory of Intelligent Information Processing
LLaVA-Mini achieves comparable performance to state-of-the-art LMMs using only one vision token, drastically reducing computational cost and latency.
Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
·2565 words·13 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Chinese University of Hong Kong
Dispider: A novel system enabling real-time interaction with video LLMs via disentangled perception, decision, and reaction modules for efficient, accurate responses to streaming video.
VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction
·2577 words·13 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Tencent Youtu Lab
VITA-1.5 achieves near real-time vision and speech interaction by using a novel three-stage training method that progressively integrates speech data into an LLM, enabling fluent conversations.
2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
·4036 words·19 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 College of Computer Science and Technology, Zhejiang University
New multimodal textbook dataset boosts Vision-Language Model (VLM) performance!
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
·3571 words·17 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 DAMO Academy, Alibaba Group
VideoRefer Suite boosts video LLM understanding by introducing a large-scale, high-quality object-level video instruction dataset, a versatile spatial-temporal object encoder model, and a comprehensiv…
On the Compositional Generalization of Multimodal LLMs for Medical Imaging
·5637 words·27 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Chinese University of Hong Kong, Shenzhen
Multimodal LLMs for medical imaging now generalize better via compositional generalization, leveraging relationships between image features (modality, anatomy, task) to understand unseen images and im…
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
·3641 words·18 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 University of Oxford
OS-Genesis: Reverse task synthesis revolutionizes GUI agent training by generating high-quality trajectory data without human supervision, drastically boosting performance on challenging benchmarks.
From Elements to Design: A Layered Approach for Automatic Graphic Design Composition
·3329 words·16 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Xi'an Jiaotong University
LaDeCo: a layered approach to automatic graphic design composition, generating high-quality designs by sequentially composing elements into semantic layers.
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
·3509 words·17 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Shanghai AI Laboratory
Task Preference Optimization (TPO) significantly boosts multimodal large language models’ visual understanding by aligning them with fine-grained visual tasks via learnable task tokens, achieving 14.6…
MMFactory: A Universal Solution Search Engine for Vision-Language Tasks
·2929 words·14 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 University of Toronto
MMFactory: A universal framework for vision-language tasks, offering diverse programmatic solutions based on user needs and constraints, outperforming existing methods.
3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding
·3344 words·16 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 AIRI
3DGraphLLM boosts 3D scene understanding by cleverly merging semantic graphs and LLMs, enabling more accurate scene descriptions and outperforming existing methods.
MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval
·2604 words·13 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Hong Kong University of Science and Technology
MegaPairs synthesizes 26M+ high-quality multimodal retrieval training examples, enabling state-of-the-art zero-shot performance and surpassing existing methods trained on 70x more data.
Flowing from Words to Pixels: A Framework for Cross-Modality Evolution
·3592 words·17 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Meta GenAI
CrossFlow: Directly evolve any modality to another using flow matching, achieving state-of-the-art results across various tasks!
LLaVA-UHD v2: an MLLM Integrating High-Resolution Feature Pyramid via Hierarchical Window Transformer
·3553 words·17 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Tsinghua University
LLaVA-UHD v2 enhances MLLMs by integrating high-resolution visual details using a hierarchical window transformer.
Descriptive Caption Enhancement with Visual Specialists for Multimodal Perception
·2901 words·14 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Hong Kong University of Science and Technology
Enhance image captions significantly with DCE, a novel engine leveraging visual specialists to generate comprehensive, detailed descriptions surpassing LMM and human-annotated captions.
Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models
·5510 words·26 mins· loading · loading
AI Generated 🤗 Daily Papers Multimodal Learning Vision-Language Models 🏢 Beijing University of Posts and Telecommunications
New benchmark reveals how well AI understands and meets real-world human needs.