ChaoHuangCS/qwen2_5_vl_3b_internvl3_qwenvl25_videomme_loose_1frame__v3prompt_grpo_multiply_raw 4B • Updated Nov 27, 2025 • 3
ChaoHuangCS/qwen2_5_vl_3b_internvl3_qwenvl25_videomme_loose_1frame__v3prompt_grpo_multiply_raw 4B • Updated Nov 27, 2025 • 3
ChaoHuangCS/qwen2_5_vl_3b_internvl3_qwenvl25_videomme_loose_1frame__v3prompt_grpo_add_raw 4B • Updated Nov 27, 2025 • 2
ChaoHuangCS/qwen2_5_vl_3b_internvl3_qwenvl25_videomme_loose_1frame__v3prompt_grpo_add_raw 4B • Updated Nov 27, 2025 • 2
Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination Paper • 2511.17490 • Published Nov 21, 2025 • 21
ZeroSep: Separate Anything in Audio with Zero Training Paper • 2505.23625 • Published May 29, 2025 • 6
Directional Reasoning Injection for Fine-Tuning MLLMs Paper • 2510.15050 • Published Oct 16, 2025 • 11 • 4
Directional Reasoning Injection for Fine-Tuning MLLMs Paper • 2510.15050 • Published Oct 16, 2025 • 11
Directional Reasoning Injection for Fine-Tuning MLLMs Paper • 2510.15050 • Published Oct 16, 2025 • 11 • 4
Directional Reasoning Injection for Fine-Tuning MLLMs Paper • 2510.15050 • Published Oct 16, 2025 • 11