AI News Google DeepMind Researchers Propose Human-Centric Alignment for Vision Models to Boost AI Generalization and Interpretation Sep 17, 20243 min read
AI News Enhancing Sparse-view 3D Reconstruction with LM-Gaussian: Leveraging Large Model Priors for High-Quality Scene Synthesis from Limited Images Sep 12, 20244 min read
AI News DriveGenVLM: Advancing Autonomous Driving with Generated Videos and Vision Language Models VLMs Sep 7, 20243 min read
AI News GaussianOcc: A Self-Supervised Approach for Efficient 3D Occupancy Estimation Using Advanced Gaussian Splatting Techniques Sep 2, 20243 min read
AI News Show-o: A Unified AI Model that Unifies Multimodal Understanding and Generation Using One Single Transformer Aug 28, 20243 min read
AI News Processing 2-Hour Videos Seamlessly: This AI Paper Unveils LONGVILA, Advancing Long-Context Visual Language Models for Long Videos Aug 23, 20243 min read
AI News UniBench: A Python Library to Evaluate Vision-Language Models VLMs Robustness Across Diverse Benchmarks Aug 18, 20244 min read
AI News Data-Augmented Contrastive Tuning: A Breakthrough in Object Hallucination Mitigation Aug 13, 20243 min read
AI News AI in Medical Imaging: Balancing Performance and Fairness Across Populations Aug 8, 20243 min read
AI News VEnhancer: A Generative Space-Time Enhancement Method for Video Generation Aug 3, 20243 min read
AI News Revolutionising Visual-Language Understanding: VILA 2’s Self-Augmentation and Specialist Knowledge Integration Jul 29, 20243 min read
AI News Visual Haystacks Benchmark: The First “Visual-Centric” Needle-In-A-Haystack (NIAH) Benchmark to Assess LMMs’ Capability in Long-Context Visual Retrieval and Reasoning Jul 24, 20243 min read
AI News From Diagrams to Solutions: MAVIS’s Three-Stage Framework for Mathematical AI Jul 19, 20244 min read
