Tran Quang Long's picture

Tran Quang Long

tqlong84

AI & ML interests

None yet

Recent Activity

replied to merve's post about 9 hours ago

stop using VLMs blindly ✋🏻 compare different VLM outputs on a huge variety of inputs (from reasoning to OCR!) 🔥 https://huggingface.co/spaces/visionLMsftw/comparevlms > has support for multiple VLMs: https://huggingface.co/google/gemma-3-27b-it, https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct, https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct, https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct, https://huggingface.co/HuggingFaceTB/SmolVLM2-2.2B-Instruct > recommend us new models or inputs, we'll add 🫡 so far I figured out > for fact-checks, you need a relatively bigger size (7B is ok!) > Gemma 3 gets downgrade without pan and scan (especially for 📑) > Qwen2.5VL-32B is very talkative, great for reasoning but not good for simple tasks 🗣️

View all activity

Organizations

None yet

models 0

None public yet

datasets 0

None public yet