👋 Open to Work

XiaofengShi

XiaofengAlg

·

https://xiaofengshi.com/

AI & ML interests

Multimodal LLMs for engineering & medical domains | RL post-training (DAPO/GRPO) | Open benchmarks MechVQA (ICML 2026) — MechVL-4B-RL scores 84.85, beating GPT-5 & GLM-4.6V huggingface.co/XiaofengAlg/XiaofengAlg

Recent Activity

reacted to theirpost with 🔥 30 days ago

📐 MechVQA: a 4B open VLM that beats GPT-5 on mechanical engineering drawings (ICML 2026) We release MechVQA — the first comprehensive benchmark and training resource for multimodal LLMs on mechanical engineering drawings — plus MechVL, a 4B domain-specialized VLM trained with SFT → DAPO RL self-play. 📊 The benchmark: 13,515 bilingual (中/EN) QA pairs over 3,371 unique drawings, covering 10 subcategories — dimension & annotation, assembly relationship, geometric calculation, anomaly detection, consistency judgment, projection & multi-view, structure understanding, identification & counting, item localization, text & table. Train/validation splits are image-hash disjoint and decontaminated against the public eval benchmark. 🚀 The model: MechVL-4B-RL (Qwen3-VL-4B-Instruct → full-param SFT → two-stage DAPO self-play) reaches 84.85 total on MechVQA — ahead of every closed-source model we evaluated: GLM-4.6V 78.91 · Gemini-3-Pro-Preview 77.28 · MechVL-4B-SFT 76.36 · GPT-5 75.44. Reward = accuracy (LLM-as-a-judge) + format + quality; ablations show DAPO > GRPO > GSPO. 🎁 All open (Apache-2.0), with full curation lineage, SHA-256 manifests and a LLaMA-Factory-ready dataset_info.json: • Dataset: https://huggingface.co/datasets/XiaofengAlg/MechVQA • RL checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-RL • SFT checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-SFT • Demo: https://huggingface.co/spaces/XiaofengAlg/mechvqa-project • Paper: https://arxiv.org/abs/2605.30794 We hope MechVQA helps the community move beyond natural-image VQA into real industrial document understanding — feedback and contributions welcome!

reacted to theirpost with 🔥 30 days ago

📐 MechVQA: a 4B open VLM that beats GPT-5 on mechanical engineering drawings (ICML 2026) We release MechVQA — the first comprehensive benchmark and training resource for multimodal LLMs on mechanical engineering drawings — plus MechVL, a 4B domain-specialized VLM trained with SFT → DAPO RL self-play. 📊 The benchmark: 13,515 bilingual (中/EN) QA pairs over 3,371 unique drawings, covering 10 subcategories — dimension & annotation, assembly relationship, geometric calculation, anomaly detection, consistency judgment, projection & multi-view, structure understanding, identification & counting, item localization, text & table. Train/validation splits are image-hash disjoint and decontaminated against the public eval benchmark. 🚀 The model: MechVL-4B-RL (Qwen3-VL-4B-Instruct → full-param SFT → two-stage DAPO self-play) reaches 84.85 total on MechVQA — ahead of every closed-source model we evaluated: GLM-4.6V 78.91 · Gemini-3-Pro-Preview 77.28 · MechVL-4B-SFT 76.36 · GPT-5 75.44. Reward = accuracy (LLM-as-a-judge) + format + quality; ablations show DAPO > GRPO > GSPO. 🎁 All open (Apache-2.0), with full curation lineage, SHA-256 manifests and a LLaMA-Factory-ready dataset_info.json: • Dataset: https://huggingface.co/datasets/XiaofengAlg/MechVQA • RL checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-RL • SFT checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-SFT • Demo: https://huggingface.co/spaces/XiaofengAlg/mechvqa-project • Paper: https://arxiv.org/abs/2605.30794 We hope MechVQA helps the community move beyond natural-image VQA into real industrial document understanding — feedback and contributions welcome!

updated a model 30 days ago

XiaofengAlg/XiaofengAlg

View all activity

Organizations

XiaofengAlg 's collections 3