YM Qin's picture

YM Qin

Wakals

·

https://wakals.github.io/

AI & ML interests

Computer Vision, Vision-language Model, Generative Model

Recent Activity

liked a dataset 3 days ago

VisGym/inference-dataset

upvoted a paper 8 days ago

Emu3.5: Native Multimodal Models are World Learners

upvoted a paper 9 days ago

dLLM: Simple Diffusion Language Modeling

View all activity

Organizations

None yet

liked a dataset 3 days ago

VisGym/inference-dataset

Updated Jan 26 • 3.48k • 3

upvoted a paper 8 days ago

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30, 2025 • 112

upvoted a paper 9 days ago

dLLM: Simple Diffusion Language Modeling

Paper • 2602.22661 • Published 15 days ago • 127

liked a dataset 10 days ago

DietCoke4671/BlenderBench

Viewer • Updated 13 days ago • 27 • 563 • 28

upvoted a collection about 1 month ago

MMFineReason

High-quality STEM reasoning dataset for Multimodal LLM post-training. • 8 items • Updated 11 days ago • 22

upvoted a paper about 2 months ago

VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents

Paper • 2601.16973 • Published Jan 23 • 40

liked a dataset 2 months ago

DietCoke4671/ToolVQA

Preview • Updated Aug 16, 2025 • 501 • 4

upvoted 2 papers 3 months ago

DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI

Paper • 2512.16676 • Published Dec 18, 2025 • 220

COOPER: A Unified Model for Cooperative Perception and Reasoning in Spatial Intelligence

Paper • 2512.04563 • Published Dec 4, 2025 • 16

updated 5 models 3 months ago

Wakals/CoVT-LLaVA-13B-depth

13B • Updated Dec 5, 2025 • 156 • 2

Wakals/CoVT-7B-seg

8B • Updated Dec 5, 2025 • 81 • 1

Wakals/CoVT-7B-depth

8B • Updated Dec 5, 2025 • 92 • 2

Wakals/CoVT-7B-seg_depth_dino_edge

8B • Updated Dec 5, 2025 • 501 • 2

Wakals/CoVT-7B-seg_depth_dino

8B • Updated Dec 5, 2025 • 1.02k • 2

updated a dataset 3 months ago

Wakals/CoVT-Dataset

Viewer • Updated Dec 5, 2025 • 1.17M • 1.74k • 11

authored a paper 3 months ago

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Paper • 2511.19418 • Published Nov 24, 2025 • 29

reacted to sanaka87's post with 🔥 4 months ago

Post

3431

Excited to share our Unified Multimodal Models new work Reconstruction Alignment (RecA)! 🚀 Just 6 × 80GB A100s × 4.5 hours to boost BAGEL performance across all tasks! Outperforms FLUX-Kontext in image editing capabilities!

📄 Paper: https://alphaxiv.org/abs/2509.07295
💻 Code: https://github.com/HorizonWind2004/reconstruction-alignment
🤗 HF Models: sanaka87/reca-68ad2176380355a3dcedc068
✍️ DEMO: sanaka87/BAGEL-RecA
🌐 Project Page: https://reconstruction-alignment.github.io
🔥 X: https://x.com/XDWang101/status/1965908302581420204
📰 Zhihu: https://zhuanlan.zhihu.com/p/1947584568187159814
🤗 HF Daily Paper: Reconstruction Alignment Improves Unified Multimodal Models (2509.07295)

⚡ <10k images & 27 GPU hours (no-arch-changes) → SOTA, surpassing much larger open-source & private models:

📊 GenEval: 0.73 → 0.90 | 📊 DPGBench: 80.93 → 88.15
🖼️ ImgEdit: 3.38 → 3.75 | 🖌️ GEdit: 6.94 → 7.25

✅ RecA trains UMMs to reconstruct images from their own visual understanding encoder embeddings → big gains in image generation 🎨 & editing ✂️.

updated a collection 4 months ago

CoVT: Chain-of-Visual-Thought

Enrich VLMs’ vision-centric reasoning capabilities via Chain-of-Visual-Thought! • 7 items • Updated Nov 25, 2025 • 6

upvoted a paper 4 months ago

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Paper • 2511.19418 • Published Nov 24, 2025 • 29

updated a collection 4 months ago

CoVT: Chain-of-Visual-Thought

Enrich VLMs’ vision-centric reasoning capabilities via Chain-of-Visual-Thought! • 7 items • Updated Nov 25, 2025 • 6