kepeng/PRSIMVL-LoRA-V1

Model

11

stars

3

commits

1

linked in READMEs

May 27, 2026

updated

benchmark

camera-raw

hdr

low-light

measurement-grounding

meas-xyz

multimodal

prsimvl

raw-image

safetensors

vision-language

visual-question-answering

Browse cluster: Vision-Language Pre-training and Retrieval →

README

Released PRSIMVL Weights

This folder stores the released PRSIMVL LoRA adapter layout used by inference and evaluation.

Expected Checkpoints

Size	Base Model	Local LoRA Checkpoint
2B	`Qwen/Qwen3-VL-2B-Instruct`	`BANALCED_150K_META_VIT_PROXY/output-Qwen3-VL-2B-Instruct/v8-20260421-133546/checkpoint-95000`
4B	`Qwen/Qwen3-VL-4B-Instruct`	`BANALCED_150K_META_VIT_PROXY/output-Qwen3-VL-4B-Instruct/v12-20260425-113029/checkpoint-85000`
8B	`Qwen/Qwen3-VL-8B-Instruct`	`BANALCED_150K_META_VIT_PROXY/output-Qwen3-VL-8B-Instruct/v2-20260423-205317/checkpoint-95000`

@misc{xu2026allegory,
  title         = {Allegory of the Cave: Measurement-Grounded Vision-Language Learning},
  author        = {Xu, Kepeng and Xu, Li and He, Gang and Yu, Wenxin},
  year          = {2026},
  eprint        = {2605.11727},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2605.11727}
}

Contributors

3 commits

Similar repos

kepeng/MeasL-Bench-V1

13

kepeng/MeasL-150K-V1

2

kepengxu/PRISM-VL

PRISM-VL studies measurement-grounded VLM learning with RAW-derived Meas.-XYZ inputs,…

912

Kun-Xiang/SeePhysPro

1

ForeverBlue/Qwen3-VL-2B-GRACE-W4G128

1

ForeverBlue/Qwen3-VL-2B-GRACE-W8G128

1

ForeverBlue/Qwen3-VL-2B-GRACE-BF16

1

Heinz217/PreMidTrainVL-Qwen3Dense

0

Linked in READMEs

kepengxu/PRISM-VL

PRISM-VL studies measurement-grounded VLM learning with RAW-derived Meas.-XYZ inputs,…

912

kepeng/PRSIMVL-LoRA-V1

Model

11

stars

3

commits

1

linked in READMEs

May 27, 2026

updated

benchmark

camera-raw

hdr

low-light

measurement-grounding

meas-xyz

multimodal

prsimvl

raw-image

safetensors

vision-language

visual-question-answering

Browse cluster: Vision-Language Pre-training and Retrieval →

README

Released PRSIMVL Weights

This folder stores the released PRSIMVL LoRA adapter layout used by inference and evaluation.

Expected Checkpoints

Size	Base Model	Local LoRA Checkpoint
2B	`Qwen/Qwen3-VL-2B-Instruct`	`BANALCED_150K_META_VIT_PROXY/output-Qwen3-VL-2B-Instruct/v8-20260421-133546/checkpoint-95000`
4B	`Qwen/Qwen3-VL-4B-Instruct`	`BANALCED_150K_META_VIT_PROXY/output-Qwen3-VL-4B-Instruct/v12-20260425-113029/checkpoint-85000`
8B	`Qwen/Qwen3-VL-8B-Instruct`	`BANALCED_150K_META_VIT_PROXY/output-Qwen3-VL-8B-Instruct/v2-20260423-205317/checkpoint-95000`

@misc{xu2026allegory,
  title         = {Allegory of the Cave: Measurement-Grounded Vision-Language Learning},
  author        = {Xu, Kepeng and Xu, Li and He, Gang and Yu, Wenxin},
  year          = {2026},
  eprint        = {2605.11727},
  archivePrefix = {arXiv},
  url           = {https://arxiv.org/abs/2605.11727}
}

Similar repos

kepeng/MeasL-Bench-V1

13

kepeng/MeasL-150K-V1

2

kepengxu/PRISM-VL

PRISM-VL studies measurement-grounded VLM learning with RAW-derived Meas.-XYZ inputs,…

912

Kun-Xiang/SeePhysPro

1

ForeverBlue/Qwen3-VL-2B-GRACE-W4G128

1

ForeverBlue/Qwen3-VL-2B-GRACE-W8G128

1

ForeverBlue/Qwen3-VL-2B-GRACE-BF16

1

Heinz217/PreMidTrainVL-Qwen3Dense

0

Linked in READMEs

kepengxu/PRISM-VL

PRISM-VL studies measurement-grounded VLM learning with RAW-derived Meas.-XYZ inputs,…

912

Contributors

3 commits