When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought Paper ⢠2511.02779 ⢠Published 22 days ago ⢠55 ⢠2
view post Post 1804 Bee-8B đ open 8B Multimodal LLM built on high quality data, released by TencentHunyuan Paper: Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs (2510.13795)Model: https://huggingface.co/collections/Open-Bee/bee-8b-68ecbf10417810d90fbd9995⨠Trained on Honey-Data-15M, a 15M-sample SFT corpus with dual-level CoT reasoning⨠Backed by HoneyPipe, a transparent & reproducible open data curation suite See translation đĽ 4 4 đ 1 1 â¤ď¸ 1 1 + Reply
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs Paper ⢠2510.13795 ⢠Published Oct 15 ⢠56 ⢠2
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs Paper ⢠2510.13795 ⢠Published Oct 15 ⢠56
R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation Paper ⢠2505.02018 ⢠Published May 4 ⢠3
R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation Paper ⢠2505.02018 ⢠Published May 4 ⢠3
RBench-V: A Primary Assessment for Visual Reasoning Models with Multi-modal Outputs Paper ⢠2505.16770 ⢠Published May 22 ⢠12
CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation Paper ⢠2502.08639 ⢠Published Feb 12 ⢠43
Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling Paper ⢠2401.15977 ⢠Published Jan 29, 2024 ⢠39