AI Research Papers Daily

DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures

Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

SweRank: Software Issue Localization with Code Ranking

VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models

CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image

Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?

DetReIDX: A Stress-Test Dataset for Real-World UAV-Based Person Recognition

Visually Interpretable Subtask Reasoning for Visual Question Answering