Shengyu Feng

PhD student @LTIatCMU

[Shengyu Feng @ShawnSYFeng]

@lltjuatja Congrats🚀!

[Lindia Tjuatja ✈️ ACL @lltjuatja]

In case you’ve been wondering what I’ve been up to these days…

So excited to (re)join an amazing community of linguists and NLP researchers at UT :)

[Frank Xu @frankxu2004]

Excited to share as many details on what we @MicrosoftAI have been working on. Building a LLM from scratch is an awesome journey with pain and suffering battling unknowns but also many cool moments to see it (somehow) works out every stage! https://t.co/WTRRRRwUGu

[Shengyu Feng @ShawnSYFeng]

Thanks for the question!

We didn’t try masked diffusion in our work, as this is not standard for combinatorial optimization, but would be meaningful to try for diffusion language model in the future.

The mode collapse did happen a lot, but also quite dependent on the neural architecture (like normalization helps alleviate it a lot). One of the techniques, as in my prior work, is Regularized Langevin Dynamics, https://t.co/qoPZWSraT4, where forcing a certain level of exploration could help model to escape a local optimum.

[Shengyu Feng @ShawnSYFeng]

Introducing Combinatorial Adjoint Matching (CAM)🚀, a paradigm shift from Reinforcement Learning to Adjoint-Method for unsupervised discrete diffusion models!

Highlight🌟: training signals from

- a single trajectory
- the terminal gradient

No labels, no RL, no dense rewards.

[Seungone Kim @seungonekim]

🇰🇷Despite rapid progress in AI agent research, Korean agentic benchmarks remain largely absent!

To narrow this gap, we release K-BrowseComp, a benchmark that requires searching across Korean websites and Korean-language content.

https://t.co/kuHby48uif

[Shengyu Feng @ShawnSYFeng]

Thanks for the question!

In fact, our original objective has already been defined as an integral. Here c_t is a cost measuring the instant KL divergence to a reference process. The objective I showed before is for practical implementation only.

For the navigation task, I would replace the second line as the direction to reduce the geodesic distance to the locally improved state at the terminal. The key spirit should be exactly the same!

[Shengyu Feng @ShawnSYFeng]

CAM is accepted to ICML26, see you in Seoul!

[Shengyu Feng @ShawnSYFeng]

Paper: https://t.co/x7LufQVFyL
Code: https://t.co/ytm8qE6yHT

[Yizhe Zhang @YizheZhangNLP]

Looped Transformers, Diffusion Models, and Latent Reasoning all share a powerful core mechanism: global iterative refinement.
But how do we make LTs lightweight to achieve performance AND high efficiency? Enter Linear Attention.
Check out our latest work led by @ChunyuanDeng!

[Martin Ziqiao Ma @ziqiao_ma]

PhDone :)

[Weiwei Sun @sunweiwei12]

🪭Excited to share that Context Folding has been accepted to #ICML2026! Congrats to all collaborators!
https://t.co/ohVoMQQ0el

[Weihua Du @StigLidu]

Excited to introduce AdaExplore 🚀✨

AdaExplore teaches LLM agents to improve GPU kernel generation by learning from past execution failures (Adapt Stage) and searching over diverse optimization paths (Explore Stage).

With GPT-5-mini as the base model, AdaExplore achieves 3.12×/1.72× speedups on KernelBench Level-2/Level-3 within 100 evaluation steps ⚡ and outperforms existing baselines such as OpenEvolve.

Project Page & Demo: https://t.co/cGoUkg5JnV
Arxiv: https://t.co/CpyvPgFBC8
Code: https://t.co/dZFayAk3EY

More in the thread 👇

[Shanda Li 黎善达 @Shanda_Li_2000]

New paper: Spend Less, Fit Better

Fitting scaling laws for LLMs can cost millions💰-but what if you can get the same insights with just ~10% of the budget?

We frame scaling-law fitting as budget-aware experimental design and propose a method to pick the most valuable runs.#LLM

[Xuhui Zhou @nlpxuhui]

Creating user simulators is a key to evaluating and training models for user-facing agentic applications. But are stronger LLMs better user simulators?

TL;DR: not really.

We ran the largest sim2real study for AI agents to date: 31 LLM simulators vs. 451 real humans across 165 tasks.

Here's what we found (co-lead with @sunweiwei12).

[Sean Welleck @wellecks]

Excited to announce our workshop on flow-based generative models at CMU:

Frontiers of Flows for Generative AI
March 26-27, Pittsburgh PA

https://t.co/U52Mx5vIYf

We have an amazing lineup of featured talks, panel discussions, and lightning talks. Registration is now open!