👋 Open to Work

Yanlong Chen PRO

ForeverBlue

2 8

ForeverBlue816

AI & ML interests

None yet

Recent Activity

liked a Space about 1 month ago

ForeverBlue/GRACE-VLM

updated a collection about 1 month ago

GRACE-VLM: Deployable INT4 Vision-Language Models

updated a model about 1 month ago

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

View all activity

Organizations

None yet

liked a Space about 1 month ago

GRACE-VLM

🦢

Try GRACE-VLM on an image, then deploy the INT4 build.

updated a collection about 1 month ago

GRACE-VLM: Deployable INT4 Vision-Language Models

Collection

ICML 2026 · Qwen3-VL-2B distilled from 8B. Start with the real AWQ-packed INT4 checkpoint, retaining 98% of GRACE BF16. • 9 items • Updated Aug 15 • 1

updated 4 models about 1 month ago

updated a Space about 1 month ago

GRACE-VLM

🦢

Try GRACE-VLM on an image, then deploy the INT4 build.

published a Space about 1 month ago

GRACE-VLM

🦢

Try GRACE-VLM on an image, then deploy the INT4 build.

updated a model about 1 month ago

ForeverBlue/LLaVA-1.5-7B-GRACE-W4G128-AWQ

Image-Text-to-Text • 1B • Updated Aug 14 • 15 • 1

upvoted a paper 3 months ago

Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs

Paper • 2601.22709 • Published Jan 30 • 1

liked a model 3 months ago

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

Image-Text-to-Text • 0.9B • Updated Aug 15 • 13 • 1

updated a collection 3 months ago

GRACE-VLM: Deployable INT4 Vision-Language Models

Collection

ICML 2026 · Qwen3-VL-2B distilled from 8B. Start with the real AWQ-packed INT4 checkpoint, retaining 98% of GRACE BF16. • 9 items • Updated Aug 15 • 1

published a model 3 months ago

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

Image-Text-to-Text • 0.9B • Updated Aug 15 • 13 • 1

liked a model 3 months ago

ForeverBlue/LLaVA-1.5-7B-GRACE-W4G128-AWQ

Image-Text-to-Text • 1B • Updated Aug 14 • 15 • 1

updated a model 4 months ago

ForeverBlue/LLaVA-1.5-7B-GRACE-W4G128

Image-Text-to-Text • 7B • Updated Jun 3 • 9 • 1

updated a collection 4 months ago

GRACE-VLM: Deployable INT4 Vision-Language Models

Collection

ICML 2026 · Qwen3-VL-2B distilled from 8B. Start with the real AWQ-packed INT4 checkpoint, retaining 98% of GRACE BF16. • 9 items • Updated Aug 15 • 1

published a model 4 months ago

ForeverBlue/LLaVA-1.5-7B-GRACE-W4G128-AWQ

Image-Text-to-Text • 1B • Updated Aug 14 • 15 • 1

authored a paper 4 months ago

Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs

Paper • 2601.22709 • Published Jan 30 • 1

updated a collection 4 months ago

GRACE-VLM: Deployable INT4 Vision-Language Models

Collection

ICML 2026 · Qwen3-VL-2B distilled from 8B. Start with the real AWQ-packed INT4 checkpoint, retaining 98% of GRACE BF16. • 9 items • Updated Aug 15 • 1

Yanlong Chen PRO

AI & ML interests

Recent Activity

Organizations

ForeverBlue's activity

GRACE-VLM

GRACE-VLM

GRACE-VLM