Article
Shipping huggingface_hub every week with AI, open tools, and a human in the loop
Wauplin, celinah
• • 18Jorge Munoz Laredo
jorgemunozl
AI & ML interests
I like Vision Language Action Models, AI4Science, Diffusion based architectures (flow matching) and I love physics.
Recent Activity
upvoted an article 3 days ago
Shipping huggingface_hub every week with AI, open tools, and a human in the loop updated a dataset 5 days ago
jorgemunozl/first_mace_test updated a model 5 days ago
jorgemunozl/mace_omat_mediumOrganizations
upvoted an article 3 days ago
updated a
dataset 5 days ago
updated a
model 5 days ago
liked a
model 5 days ago
updated a
model 6 days ago
published a
model 6 days ago
liked a
model 6 days ago
updated a
model 6 days ago
published a
model 6 days ago
liked a
model 6 days ago
published a
model 6 days ago
reacted to Anran-MLLM's post with 🔥 7 days ago
Post
3550
🚀 Introducing PerceptionDLM — the first multimodal diffusion LLM for parallel region perception!
Most MLLMs are autoregressive, so captioning N regions costs N sequential passes. PerceptionDLM instead describes ALL masked regions in a single denoising process. 🧩
✨ Highlights
• ⚡ Up to 3.4× faster on dense multi-region captioning, with stable per-image latency
• 🏆 PerceptionDLM-Base beats LLaDA-V on 15/16 multimodal benchmarks (new SOTA among open diffusion VLMs)
• 📊 New benchmark: ParaDLC-Bench — jointly evaluates caption quality AND inference efficiency
• 🔓 Code, models & benchmark all open-sourced
🤖 Models
MSALab/PerceptionDLM-Base
MSALab/PerceptionDLM
📊 Benchmark
MSALab/ParaDLC-Bench
📄 Paper: PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models (2606.19534)
💻 Code: https://github.com/MSALab-PKU/PerceptionDLM
Diffusion LLMs aren't just for text — they unlock efficient, parallel visual perception. 👁️✨
#multimodal #diffusion #VLM #perception
Most MLLMs are autoregressive, so captioning N regions costs N sequential passes. PerceptionDLM instead describes ALL masked regions in a single denoising process. 🧩
✨ Highlights
• ⚡ Up to 3.4× faster on dense multi-region captioning, with stable per-image latency
• 🏆 PerceptionDLM-Base beats LLaDA-V on 15/16 multimodal benchmarks (new SOTA among open diffusion VLMs)
• 📊 New benchmark: ParaDLC-Bench — jointly evaluates caption quality AND inference efficiency
• 🔓 Code, models & benchmark all open-sourced
🤖 Models
MSALab/PerceptionDLM-Base
MSALab/PerceptionDLM
📊 Benchmark
MSALab/ParaDLC-Bench
📄 Paper: PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models (2606.19534)
💻 Code: https://github.com/MSALab-PKU/PerceptionDLM
Diffusion LLMs aren't just for text — they unlock efficient, parallel visual perception. 👁️✨
#multimodal #diffusion #VLM #perception
liked a
model 7 days ago
updated a
model 7 days ago
published a
model 7 days ago
awesome, tough I ask a double pendulum and it failed, but pretty awesome to be honest
reacted to ovi054's post with ❤️ 11 days ago
Post
3608
Qwen3-14B Manim Expert LoRA
For "Build Small Hackathon", I built a Gradio app that turns any concept into a Manim explainer video.
This is powered by Qwen3-14B + Manim LoRA I trained on a synthetic 10k dataset I generated.
👉 Try it now: build-small-hackathon/anim-vid-ai
For "Build Small Hackathon", I built a Gradio app that turns any concept into a Manim explainer video.
This is powered by Qwen3-14B + Manim LoRA I trained on a synthetic 10k dataset I generated.
👉 Try it now: build-small-hackathon/anim-vid-ai
- 2 replies
liked a
Space 11 days ago
liked a
dataset 11 days ago
published a
dataset 11 days ago