Dazhen

Assistant Professor @ Zhejiang University, LLM x Vis

[Dazhen @Dakzen4]

Our code and data are also available:
https://t.co/Cpnqbq98CW

[Yuchen He @y_he02]

Chart data extraction is still tedious or unreliable.
We study MLLMs and find a key gap: they get the structure right but miss the numbers.
We introduce a benchmark + human-inspired training approach, and explore mixed-initiative workflows.
Come talk to us at #CHI2026!

[九原客 @9hills]

如果对 DeepResearch 这类复杂的 Agent 感兴趣，我建议学一下LangGraph的免费课程 Deep Research with LangGraph。

课程比较循序渐进，先做一个单Agent系统，然后进化为多 Agent。

最主要是架构简单，外部依赖非常少，一个大模型一个搜索API就完了。

https://t.co/2yz5oHUBTO

[Pedro Lopes @plopesresearch]

#CHI2026 6700 * 4 reviews can be benefit from this wonderful advice from @MillerLabMIT on reviewing. I highly stress these points too when discussing peer review in my lab.

[Dazhen @Dakzen4]

Just presented our paper ReSpark at #UIST2025! ✨

ReSpark leverages previous data reports to help LLMs generate new analysis code, charts, and narratives—making data report authoring more efficient and logical.

Code is open source 👉 https://t.co/KqHF9hNzS9

@zjuidg @bebincaa

[johann.GPT @ProgramerJohann]

又看到个牛逼的文章。

一文带你看懂主流 LLM 技术演进全览。

超多图，讲解易懂、图示直观。包括 DeepSeek、Gemma、Llama、Qwen、OLMo、Mistral、Kimi 等代表性开源模型的架构变迁和技术细节。

链接放下面了：

[ZJUIDG @zjuidg]

@sig_chi Want to create a highlight collection for your favorite player? Or want to collect sports data for professional analysis? HCI empowered by computer vision models can help! @Dakzen4 Check out the paper at https://t.co/ur1XlMKfuc to learn more.

[ZJUIDG @zjuidg]

Welcome to the session, Animation and Sports, on October 23 (10:50AM-12:20PM). I'll show you the secrets behind the top table tennis players.

[IEEE VIS @ieeevis]

What is the secret behind the top table tennis players around the world? Tac-Simur will answer you! Available at https://t.co/VKRaS7sPwL @ZJUIDG #ieeevis

[IEEE VIS @ieeevis]

Where are the air pollutants coming from? AirVis will answer you! Available at https://t.co/VKRaS7sPwL @ZJUIDG #ieeevis