UniG2U-Bench: Do Unified Models Advance Multimodal Understanding? Paper • 2603.03241 • Published 4 days ago • 79
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence Paper • 2602.08683 • Published 26 days ago • 50
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence Paper • 2602.08683 • Published 26 days ago • 50
lmms-lab-encoder/wd_temporal_grounding_frames_max_64_max_448x448_pixels_with_fps Updated 21 days ago • 154
lmms-lab-encoder/wd_temporal_grounding_frames_max_64_max_448x448_pixels_with_fps Updated 21 days ago • 154
ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder Paper • 2510.18795 • Published Oct 21, 2025 • 11
DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset Paper • 2601.10305 • Published Jan 15 • 36