Taiming Lu

Ph.D student at @Princeton | Formerly @JohnsHopkins ’25, @HopkinsDSAI @JHUCompSci @jhuclsp @CCVLatJHU | AI/ML/NLP/CV

[Taiming Lu @TaimingLu]

@muhan_gao Nice work!

[Taiming Lu @TaimingLu]

@kentonmurray Congrats!!! 🎉

[Taiming Lu @TaimingLu]

Teacher–student compatibility matters more than raw teacher strength.

This changes how you pick a teacher: both for frontier training (where the best available teacher is often a prior generation) and for efficient small models, where "bigger teacher is better" isn't the right rule.

Thanks @liuzhuang1234 for the support!

arxiv: https://t.co/EWcX461JHS
code: https://t.co/efl747LsVd

[Taiming Lu @TaimingLu]

Knowledge doesn't always flow downhill.

We find that in LLM pretraining, a weaker teacher can improve a stronger student, and pushing the teacher further can actually hurt.

New paper: Strong Teacher Not Needed? On Distillation in LLM Pretraining.

[Taiming Lu @TaimingLu]

Distillation improves generalization more readily than in-domain fit.

Out-of-distribution perplexity and downstream accuracy improve more consistently than in-domain perplexity, where some configurations help OOD/downstream while doing nothing for in-domain.

[Taiming Lu @TaimingLu]

@DanielKhashabi Congrats Daniel!!! 🎉🎉🎉

[Zhuang Liu @liuzhuang1234]

Stronger Normalization-Free Transformers – new paper.

We introduce Derf (Dynamic erf), a simple point-wise layer that lets norm-free Transformers not only work, but actually outperform their normalized counterparts.

[Jieneng Chen @jieneng_chen]

🤯 Think better visuals mean better world models? Think again.
💥 Surprise: Agents don’t need eye candy— they need wins.

Meet World-in-World, the first open benchmark that ranks world models by closed-loop task success, not pixels.

We uncover 3 shocks:
1️⃣ Visuals ≠ utility
2️⃣ Action data > bigger models
3️⃣ Scaling test-time compute = more success

🤗 https://t.co/OXn4WfnuTU
🌍 https://t.co/AKRgXhSCJV
📄 https://t.co/izyjaKTHgO
https://t.co/hd6F9VPGQ2

[Zhuang Liu @liuzhuang1234]

Excited to share our lab’s first open-source release: LLM-Distillation-JAX

supports practical knowledge distillation configurations (distillation strength, temperature, top-k/top-p), built on MaxText

designed for reproducible JAX/Flax training on both TPUs and GPUs

[JHU Computer Science @JHUCompSci]

Meet the AI system that can envision an entire world from a single picture. @genex_world—developed by @jieneng_chen, @YuilleAlan, @TaiMingLu, @DanielKhashabi, & @tianminshu—imagines in-depth scenarios to make informed decisions. Learn more here: https://t.co/yXTaBBxH8K

[Jieneng Chen @jieneng_chen]

Thrilled to introduce GenEx: Generating an Explorable World. ✨

✨ GenEx takes a single image 🖼️ and create a 3D generative world 🌍 — you can dive in for interactive exploration, and so as embodied AI agent.

Follow our X for more demos: https://t.co/3pgBPvo2ap
Paper on huggingface: https://t.co/e6TLHKheHy
Tech details: https://t.co/3TRt9SpwJv
(1/n)

[GenEx @genex_world]

Introducing GenEx: Turn any image into a 3D world adventure!

1️⃣ Create a fully explorable 360° world in 3D from just a single image!
2️⃣ Explore interactively or with GPT assistance.
3️⃣ Advance embodied AI with this imagined world!

Check out our website: https://t.co/Kj4g3STesR

[Jieneng Chen @jieneng_chen]

Introducing Genex: Generative World Explorer.

🧠 Humans mentally explore unseen parts of the world, revising their beliefs with imagined observations. ✨ Genex replicates this human-like ability, advancing embodied AI in planning with partial observations. (1/6)

[Muhan Gao @muhan_gao]

🤖LLMs know more long-context information than they show!

🔍Probing reveals higher accuracy than generation output. #LLMs know but don't tell.🤐

The earlier relevant information is learned within the layers, the higher the final output accuracy! 📈

(https://t.co/1f4I65VAEy)