82 95 200

Andres Marafioti

andito

AI & ML interests

Multimodal models, VLM and TTS

Recent Activity

upvoted a paper about 12 hours ago

Qwen3 Technical Report

liked a Space about 13 hours ago

huggingface-projects/repo_duplicator

liked a dataset 1 day ago

Zhiqiang007/MathV360K

View all activity

Organizations

upvoted a paper about 12 hours ago

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14 • 243

liked a Space about 13 hours ago

297

Repo duplicator

😻

Duplicate Hugging Face repositories

liked a dataset 1 day ago

Zhiqiang007/MathV360K

Viewer • Updated Jun 27, 2024 • 339k • 370 • 30

updated a model 1 day ago

andito/nanoVLM

Image-Text-to-Text • 0.5B • Updated 1 day ago • 46 • 1

posted an update 2 days ago

Post

2517

Many VLMs claim to process hours of video. But can they follow the story?🤔
Today, we introduce TimeScope: The benchmark that separates true temporal understanding from marketing hype. Let's see how much VLMs really understand!⏳

We test three skills that matter for real-world use:
🔎 Localized Retrieval: Find a specific action.
🧩 Information Synthesis: Piece together scattered clues.
🏃 Fine-Grained Perception: Analyze detailed motion (e.g., count how many times a person swings an axe).

The results are in, and they're revealing. Only Gemini 2.5 pro handles 1-hour-long videos.
Performance drops sharply with duration, proving that long video understanding is still challenging. We've found the breaking points—now the community can start fixing them.📈

Want to learn more? TimeScope is 100% open-source. Benchmark your model and help us build the next generation of video AI.

📖 Blog:
https://huggingface.co/blog/timescope-video-lmm-benchmark
👩‍💻 Leaderboard & Demo: Apollo-LMMs/TimeScope
📊 Dataset: Apollo-LMMs/TimeScope
⚙️ Eval Code: https://github.com/EvolvingLMMs-Lab/lmms-eval