Peixuan Han (韩沛煊) (@peixuanhakhan) 's Twitter Profile
Peixuan Han (韩沛煊)

@peixuanhakhan

1st year Ph.D. student at UIUC @IllinoisCS
LLM researcher

ID: 1839016452311130112

linkhttps://hanpx20.github.io/ calendar_today25-09-2024 18:57:51

26 Tweet

49 Followers

59 Following

Zijia Liu (@xwzliuzijia) 's Twitter Profile Photo

💥Time-R1 is here! Can a 3B LLM truly grasp time? 🤔 YES! Excited to share our new work, Time-R1: Towards Comprehensive Temporal Reasoning in LLMs 🚀 Check it out: 📖 Paper: arxiv.org/abs/2505.13508 💻 Code: github.com/ulab-uiuc/Time… #TemporalReasoning #RL #LLMs

💥Time-R1 is here! Can a 3B LLM truly grasp time? 🤔 YES! 

Excited to share our new work, Time-R1: Towards Comprehensive Temporal Reasoning in LLMs 🚀

Check it out:
📖 Paper: arxiv.org/abs/2505.13508
💻 Code: github.com/ulab-uiuc/Time…

#TemporalReasoning #RL #LLMs
Cheng Qian (@qiancheng1231) 's Twitter Profile Photo

📢 New Paper Drop: From Solving to Modeling! LLMs can solve math problems — but can they model the real world? 🌍 📄 arXiv: arxiv.org/pdf/2505.15068 💻 Code: github.com/qiancheng0/Mod… Introducing ModelingAgent, a breakthrough system for real-world mathematical modeling with LLMs.

📢 New Paper Drop: From Solving to Modeling!
LLMs can solve math problems — but can they model the real world? 🌍

📄 arXiv: arxiv.org/pdf/2505.15068
💻 Code: github.com/qiancheng0/Mod…

Introducing ModelingAgent, a breakthrough system for real-world mathematical modeling with LLMs.
Jiaxun Zhang (@jiaxunzhang6) 's Twitter Profile Photo

⚠️ Rogue AI scientists? 🛡️ SafeScientist rejects unsafe prompts for ethical discoveries. Check out paper ➡️ (arxiv.org/pdf/2505.23559) #AISafety #LLM #SafeAI #AI

Xiusi Chen (@xiusi_chen) 's Twitter Profile Photo

Can LLMs make rational decisions like human experts? 📖Introducing DecisionFlow: Advancing Large Language Model as Principled Decision Maker We introduce a novel framework that constructs a semantically grounded decision space to evaluate trade-offs in hard decision-making

Can LLMs make rational decisions like human experts?

📖Introducing DecisionFlow: Advancing Large Language Model as Principled Decision Maker

We introduce a novel framework that constructs a semantically grounded decision space to evaluate trade-offs in hard decision-making
Peixuan Han (韩沛煊) (@peixuanhakhan) 's Twitter Profile Photo

Super excited to begin my Applied Scientist Internship at Amazon, which is my first internship in the industry. I'm looking forward to conducting interesting and insightful research on the efficient reasoning of LLMs!

Super excited to begin my Applied Scientist Internship at <a href="/amazon/">Amazon</a>, which is my first internship in the industry.

I'm looking forward to conducting interesting and insightful research on the efficient reasoning of LLMs!
Alexi Gladstone (@alexiglad) 's Twitter Profile Photo

How can we unlock generalized reasoning? ⚡️Introducing Energy-Based Transformers (EBTs), an approach that out-scales (feed-forward) transformers and unlocks generalized reasoning/thinking on any modality/problem without rewards. TLDR: - EBTs are the first model to outscale the

How can we unlock generalized reasoning?

⚡️Introducing Energy-Based Transformers (EBTs), an approach that out-scales (feed-forward) transformers and unlocks generalized reasoning/thinking on any modality/problem without rewards.
TLDR:
- EBTs are the first model to outscale the
Peixuan Han (韩沛煊) (@peixuanhakhan) 's Twitter Profile Photo

We're pleased to announce that SafeSwitch has been accepted to EMNLP 2025! Many thanks to the collaborators for their help with this amazing project! Cheng Qian Xiusi Chen Yuji Zhang Denghui Zhang Heng Ji Paper: arxiv.org/pdf/2502.01042

Denghui Zhang (@denghui_zhang) 's Twitter Profile Photo

Interpretability: Understanding how AI models think youtu.be/fGKNUvivvnc?si… via YouTube Anthropic Anthropic’s new video dives into AI interpretability—how models think & why it matters 🧠✨ Our EMNLP paper SafeSwitch takes a similar path: leveraging internal activations

Kunlun Zhu (@kunlun_zhu) 's Twitter Profile Photo

🚨 New from UIUC x Stanford x AMD: AgentDebug: Where LLM Agents Fail and How They Can Learn From Failures 🔍🤖 LLM agents fail due to early errors that snowball—yet lack tools to trace & fix them. ✅ AgentDebug Debugger 📄 arxiv.org/abs/2509.25370 🛠️ github.com/ulab-uiuc/Agen…

🚨 New from UIUC x Stanford x AMD:

AgentDebug: Where LLM Agents Fail and How They Can Learn From Failures 🔍🤖
LLM agents fail due to early errors that snowball—yet lack tools to trace &amp; fix them.
✅ AgentDebug Debugger
📄 arxiv.org/abs/2509.25370
🛠️ github.com/ulab-uiuc/Agen…
Jiaxuan You (@youjiaxuan) 's Twitter Profile Photo

Introducing Multi-Agent Evolve 🧠 A new paradigm beyond RLHF and RLVR: More compute → closer to AGI No need for expensive data or handcrafted rewards We show that an LLM can self-evolve — improving itself through co-evolution among roles (Proposer, Solver, Judge) via RL — all

Introducing Multi-Agent Evolve 🧠

A new paradigm beyond RLHF and RLVR:
More compute → closer to AGI
No need for expensive data or handcrafted rewards

We show that an LLM can self-evolve — improving itself through co-evolution among roles (Proposer, Solver, Judge) via RL — all