imesh7/sinhala-tts
Updated
Imesh Madushanka
imesh7
AI & ML interests
TTS (Text-to-Speech) , Computer vision
Recent Activity
liked a model 2 days ago
google/diffusiongemma-26B-A4B-it reacted to XiaofengAlg's post with π₯ 4 days ago
π MechVQA: a 4B open VLM that beats GPT-5 on mechanical engineering drawings (ICML 2026)
We release MechVQA β the first comprehensive benchmark and training resource for multimodal LLMs on mechanical engineering drawings β plus MechVL, a 4B domain-specialized VLM trained with SFT β DAPO RL self-play.
π The benchmark: 13,515 bilingual (δΈ/EN) QA pairs over 3,371 unique drawings, covering 10 subcategories β 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.
π The model: MechVL-4B-RL (Qwen3-VL-4B-Instruct β full-param SFT β two-stage DAPO self-play) reaches 84.85 total on MechVQA β ahead of every closed-source model we evaluated: GLM-4.6V 78.91 Β· Gemini-3-Pro-Preview 77.28 Β· MechVL-4B-SFT 76.36 Β· GPT-5 75.44. Reward = accuracy (LLM-as-a-judge) + format + quality; ablations show DAPO > GRPO > GSPO.
π All open (Apache-2.0), with full curation lineage, SHA-256 manifests and a LLaMA-Factory-ready dataset_info.json:
β’ Dataset: https://huggingface.co/datasets/XiaofengAlg/MechVQA
β’ RL checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-RL
β’ SFT checkpoint: https://huggingface.co/XiaofengAlg/MechVL-4B-SFT
β’ Demo: https://huggingface.co/spaces/XiaofengAlg/mechvqa-project
β’ Paper: https://arxiv.org/abs/2605.30794
We hope MechVQA helps the community move beyond natural-image VQA into real industrial document understanding β feedback and contributions welcome! liked a model 9 days ago
canberkkkkkk/ema-lightningOrganizations
None yet