GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
aacudad
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
aacudad
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Keep-Correct-Revise (KCR) is the data recipe behind the model this run starts from. An SFT plus GRPO policy generates its own reasoning traces on Real-IAD images. Each trace is then kept when the verdict is correct, corrected by a teacher model when the verdict is wrong, and revised by a teacher model when the verdict is correct but the reasoning is only weakly grounded in the image. The base model is then fine-tuned from scratch on the curated 6,000-trace result. That fine-tune is the KCR model.
This model is one more GRPO stage stacked on top of that KCR model.
GRPO on the already-strong KCR init edges the SFT ceiling on average but the trajectory bounces across epoch 3 rather than climbing monotonically, so the gain is small and not yet clearly stable. The thesis therefore reports the KCR SFT model as the headline and holds this run as future work. Do not read these numbers as "GRPO beat SFT".
Balanced accuracy BA = 0.5 * (TP/(TP+FN) + TN/(TN+FP)), recomputed from the raw tp/tn/fp/fn of
each eval JSON (shipped in the code repo).
| Benchmark | BA | tp | tn | fp | fn | n |
|---|---|---|---|---|---|---|
| DS-MVTec | 82.95 | 1004 | 373 | 71 | 222 | 1670 |
| VisA | 72.62 | 719 | 804 | 140 | 478 | 2141 |
Average 77.78, versus the KCR init's 77.44 (82.80 / 72.07).
| Model | DS-MVTec | VisA | Note |
|---|---|---|---|
…-7B-KCR | 82.80 | 72.07 | thesis headline |
…-7B-SFT | 80.16 | 64.78 | plain SFT baseline |
python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom qwen_vl_utils import process_vision_info model_id = "aacudad/AnomalyThink-Qwen2.5-VL-7B-KCR-GRPO"model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_id, torch_dtype="auto", device_map="auto")processor = AutoProcessor.from_pretrained(model_id) messages = [{"role": "user", "content": [ {"type": "image", "image": "file:///path/to/part.png"}, {"type": "text", "text": "Is there a defect in this product? Analyze and answer yes or no."},]}]text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)imgs, vids = process_vision_info(messages)inputs = processor(text=[text], images=imgs, videos=vids, padding=True, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=512)print(processor.batch_decode(out[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0])checkpoint-954 eval JSONs: https://github.com/aacudad/IAD-VLMsbibtex
@mastersthesis{acudad2026reasoning, author = {Acudad, A.}, title = {Reasoning-Enhanced Vision-Language Models for Explainable Industrial Anomaly Detection}, school = {Delft University of Technology}, year = {2026}, type = {Master's thesis}, url = {https://resolver.tudelft.nl/uuid:65c62420-79c0-447f-b095-7fb11d4474fc}}Thesis: https://resolver.tudelft.nl/uuid:65c62420-79c0-447f-b095-7fb11d4474fc. Code and evaluation files: https://github.com/aacudad/IAD-VLMs.
Derived from Qwen2.5-VL-7B-Instruct (Apache-2.0). Evaluated on DS-MVTec and VisA (MMAD protocol), trained on AnomalyThink traces distilled from Gemini-2.5-Flash over Real-IAD.
…-7B-SFT-GRPO| 82.73 |
| 70.39 |
| released RL model, the policy KCR rolls out from |
| this model (GRPO on KCR, ckpt-954) | 82.95 | 72.62 | research preview / future work |