Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
Paper
• 2508.09834 • Published
• 53
LVLM
-
-
RadGenome-Chest CT: A Grounded Vision-Language Dataset for Chest CT Analysis
Paper • 2404.16754 • Published -
LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery
Paper • 2505.02829 • Published -
MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMs
Paper • 2510.01691 • Published • 4 -
A Survey of Vibe Coding with Large Language Models
Paper • 2510.12399 • Published • 50 -
Large Language Models Do NOT Really Know What They Don't Know
Paper • 2510.09033 • Published • 17 -
AnyUp: Universal Feature Upsampling
Paper • 2510.12764 • Published • 12 -
ReXGroundingCT: A 3D Chest CT Dataset for Segmentation of Findings from Free-Text Reports
Paper • 2507.22030 • Published • 3 -
Phrase-grounded Fact-checking for Automatically Generated Chest X-ray Reports
Paper • 2509.21356 • Published -
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
Paper • 2601.10527 • Published • 25 -
LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning
Paper • 2601.10129 • Published • 12 -
Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
Paper • 2602.05393 • Published • 8 -
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper • 2603.06569 • Published • 86