Jiaqi-hkust (Jiaqi Tang)

reacted to their post with ❤️➕😎 about 23 hours ago

Post

60

We reshaped how VLMs connect vision to language!

One simple architectural change → dramatically better visual information injection into the LLM.

Accepted at NeurIPS. Check it out 👇

📄 https://arxiv.org/abs/2611.06844
💻 https://github.com/YingyingYan1/DGP

#NeurIPS #VLM #MLLM #ViT

reacted to their post with 👀🔥 1 day ago

Post

60

We reshaped how VLMs connect vision to language!

One simple architectural change → dramatically better visual information injection into the LLM.

Accepted at NeurIPS. Check it out 👇

📄 https://arxiv.org/abs/2611.06844
💻 https://github.com/YingyingYan1/DGP

#NeurIPS #VLM #MLLM #ViT

posted an update 1 day ago

Post

60

We reshaped how VLMs connect vision to language!

One simple architectural change → dramatically better visual information injection into the LLM.

Accepted at NeurIPS. Check it out 👇

📄 https://arxiv.org/abs/2611.06844
💻 https://github.com/YingyingYan1/DGP

#NeurIPS #VLM #MLLM #ViT

upvoted a paper 3 days ago

Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers

Paper • 2611.06844 • Published 8 days ago • 2

submitted a paper to Daily Papers 3 days ago

Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers

Paper • 2611.06844 • Published 8 days ago • 2

reacted to their post with ❤️👀🔥 29 days ago

Post

3,202

We open-sourced Game-Creation-Agents — an agentic system that turns a one-line game idea into a playable browser game. 🎮

Why it matters:
- It lowers the barrier: you don’t need a full studio or deep engine skills to start.
- It compresses prototyping from weeks to hours.
- It lets creators test more ideas, faster, and focus on what’s actually fun.
- It brings game creation closer to a conversation — and makes it accessible to more people.

This isn’t just about generating code. It’s about giving more people the power to bring their ideas to life.

Try it:
https://github.com/Tencent/Game-Creation-Agents

#AI #GameDev #OpenSource

posted an update 29 days ago

Post

3,202

We open-sourced Game-Creation-Agents — an agentic system that turns a one-line game idea into a playable browser game. 🎮

Why it matters:
- It lowers the barrier: you don’t need a full studio or deep engine skills to start.
- It compresses prototyping from weeks to hours.
- It lets creators test more ideas, faster, and focus on what’s actually fun.
- It brings game creation closer to a conversation — and makes it accessible to more people.

This isn’t just about generating code. It’s about giving more people the power to bring their ideas to life.

Try it:
https://github.com/Tencent/Game-Creation-Agents

#AI #GameDev #OpenSource

liked a model 3 months ago

tencent/Hy4-preview

Text Generation • 780B • Updated Aug 28 • 11.4k • • 555

reacted to their post with 🤗➕👀🚀🔥 3 months ago

Post

2,429

🧠 Remember-R1: Our fix for MLLMs forgetting the image during long reasoning

We noticed a frustrating problem: when multimodal models reason over long chains, they gradually stop looking at the image—and start hallucinating based on their own text.

So we built Remember‑R1, a simple RL framework that directly supervises visual attention on the original reasoning trajectory—no inference overhead, no proxy tasks.

We use three complementary rewards: coverage, persistence, and focus. They encourage the model to keep attending to relevant visual evidence even in later reasoning steps.

Results across 7 benchmarks and 2 model sizes: better reasoning, and—more importantly—visual attention decays much more slowly during generation.

No extra cost at inference, just cleaner supervision where it counts.

📄 Paper: https://arxiv.org/abs/2608.01314
💻 Code: https://github.com/Ch921-cell/Remember-R1

Happy to answer any questions and receive feedback!

#MultimodalAI #RL #MLLM #CoT #VisualReasoning

posted an update 3 months ago

Post

2,429

🧠 Remember-R1: Our fix for MLLMs forgetting the image during long reasoning

We noticed a frustrating problem: when multimodal models reason over long chains, they gradually stop looking at the image—and start hallucinating based on their own text.

So we built Remember‑R1, a simple RL framework that directly supervises visual attention on the original reasoning trajectory—no inference overhead, no proxy tasks.

We use three complementary rewards: coverage, persistence, and focus. They encourage the model to keep attending to relevant visual evidence even in later reasoning steps.

Results across 7 benchmarks and 2 model sizes: better reasoning, and—more importantly—visual attention decays much more slowly during generation.

No extra cost at inference, just cleaner supervision where it counts.

📄 Paper: https://arxiv.org/abs/2608.01314
💻 Code: https://github.com/Ch921-cell/Remember-R1

Happy to answer any questions and receive feedback!

#MultimodalAI #RL #MLLM #CoT #VisualReasoning

liked a dataset 3 months ago

futurex-ai/Futurex-Online

Viewer • Updated 3 days ago • 80 • 587 • 27

Jiaqi Tang PRO

AI & ML interests

Recent Activity

Organizations

Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers

Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers

tencent/Hy4-preview

futurex-ai/Futurex-Online

Jiaqi Tang PRO

AI & ML interests

Recent Activity

Organizations

Jiaqi-hkust's activity