LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL Paper • 2503.07536 • Published 4 days ago • 73 • 3
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL Paper • 2503.07536 • Published 4 days ago • 73
Negative Token Merging: Image-based Adversarial Feature Guidance Paper • 2412.01339 • Published Dec 2, 2024 • 23
Zero-Shot Long-Form Video Understanding through Screenplay Paper • 2406.17309 • Published Jun 25, 2024 • 1
Exploring Diverse In-Context Configurations for Image Captioning Paper • 2305.14800 • Published May 24, 2023
Number it: Temporal Grounding Videos like Flipping Manga Paper • 2411.10332 • Published Nov 15, 2024 • 14
Number it: Temporal Grounding Videos like Flipping Manga Paper • 2411.10332 • Published Nov 15, 2024 • 14
Number it: Temporal Grounding Videos like Flipping Manga Paper • 2411.10332 • Published Nov 15, 2024 • 14 • 2
LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Paper • 2409.18125 • Published Sep 26, 2024 • 34