Fei Wang @fwang_nlp

Research Scientist @Google. PhD @USC. LLM post-training. feiwang96.github.io Los Angeles Joined May 2019

Tweets

285
Followers

2K
Following

2K
Likes

623

Tianyi Lorena Yan @LorenaYannnnn

6 days ago

[Belated update] Excited to share I’ll be starting my PhD with @johnhewtt at Columbia! I’m deeply grateful to my advisors Prof. @robinomial and Prof. @muhao_chen, my mentor @fwang_nlp, Prof. @_jessethomason_, Prof. Hao Zhou at TsinghuaAIR, and all my peers @USC. 🧵

10 5 159 14K 13

Ben Zhou @BenZhou96

2 weeks ago

In addition, we show a rubric-based reward can help steering models’ thinking/reflection process, potentially key to future directions on infusing constraints in reasoning.

jakedineenasu @jakedineenasu

2 weeks ago

In addition, we show a rubric-based reward can help steering models’ thinking/reflection process, potentially key to future directions on infusing constraints in reasoning.

0 3 9 2K 0

0 2 12 1K 1

Tianqing Fang @TFang229

a month ago

🚀 We are thrilled to release a new open-source Deep Research Agent, Cognitive Kernel-Pro, from Tencent AI Lab! We focus on building a fully open-source agent with (to the maximum extent) free tools, showcasing impressive performance on GAIA with Claude-3.7-sonnet and surpass the…

0 25 84 8K 40

Download Image

Qinyuan Ye @qinyuan_ye

a month ago

1+1=3 2+2=5 3+3=? Many language models (e.g., Llama 3 8B, Mistral v0.1 7B) will answer 7. But why? We dig into the model internals, uncover a function induction mechanism, and find that it’s broadly reused when models encounter surprises during in-context learning. 🧵

4 18 115 9K 42

Download Image

Anshuman Chhabra @nshuman_chhabra

2 months ago

A little late but nevertheless happy to share that our paper “Outlier Gradient Analysis: Efficiently Identifying Detrimental Training Samples for Deep Learning Models” was accepted as an oral presentation at #ICML2025 (top 1%). More details here: arxiv.org/pdf/2405.03869!

1 1 14 701 3

Tianqing Fang @TFang229

3 months ago

🚀 Check out our paper: WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model, from Tencent AI Lab!. We present a world model-driven framework for self-improving web agents, addressing critical challenges in self-training—such as limited exploration and…

1 16 53 9K 20

Download Image

Qin Liu @QinLiu_NLP

3 months ago

🚨 New paper accepted to #ACL2025! We propose SudoLM, a framework that lets LLMs learn access control over parametric knowledge. Rather than blocking everyone from sensitive knowledge, SudoLM grants access to authorized users only. Paper: arxiv.org/abs/2410.14676… 🧵[1/6]👇

1 8 11 2K 5

Download Image

Xiaofei Wen @Xiaofei_Wen_Mk

3 months ago

Can LLM guardrails think twice before deciding? ✨ Check out our #ACL2025 paper: THINKGUARD — a critique-augmented safety guardrail! ✅ Structured critiques ✅ Interpretable decisions ✅ Robust against adversarial prompts 📑 arxiv.org/abs/2502.13458 🧵[1/n]

1 10 12 1K 4

Download Image

ComputerUseAgents Workshop @workshopcua

4 months ago

🔦 Speaker Spotlight: Sercan Ö. Arık (@sercanarik) We're thrilled to welcome Sercan, Senior Staff Research Scientist at Google Cloud AI, as an invited speaker at the ICML 2025 Workshop on Computer Use Agents! Sercan's focuses on democratizing AI and applying it to impactful use…

1 1 3 317 1

Download Image

Wenjie Jacky Mo @Wenjie_Jacky_Mo

5 months ago

Worried about backdoors in LLMs? 🌟 Check out our #NAACL2025 work on test-time backdoor mitigation! ✅ Black-box 📦 ✅ Plug-and-play 🛡️ We explore: → Defensive Demonstrations 🧪 → Self-generated Prefixes 🧩 → Self-refinement ✍️ 📄 arxiv.org/abs/2311.09763 🧵[1/n]

1 6 9 897 0

Download Image

Hadi Askari @hadiaskari67

4 months ago

🧵1/ Excited to share our #NAACL2025 work! 🎉 "Assessing LLMs for Zero-Shot Abstractive Summarization Through the Lens of Relevance Paraphrasing" We study how robust LLM summarization is to our relevance paraphrasing method? 🧠📝 More details below:👇 arxiv.org/abs/2406.03993

1 7 15 853 1

Nan Xu @xunannancy

4 months ago

Should multimodal in-context learning demonstrations mirror the visual or textual patterns of test instances? I'll present paper “From Introspection to Best Practices: Principled Analysis of Demonstrations in Multimodal In-Context Learning” on April 30th at NAACL. See you there!

1 5 6 487 1

Download Image

Tu Vu @tuvllms

5 months ago

🚨 New paper 🚨 Excited to share my first paper w/ my PhD students!! We find that advanced LLM capabilities conferred by instruction or alignment tuning (e.g., SFT, RLHF, DPO, GRPO) can be encoded into model diff vectors (à la task vectors) and transferred across model…

13 92 445 47K 278

Download Image

Xiaogeng Liu @XiaogengLiu

4 months ago

Thrilled to be featured in the #ICLR2025 Spotlight! 🎉 Come see our poster in Hall 3 + Hall 2B #602, April 25, 10:00–12:30 PM SGT

Xiaogeng Liu @XiaogengLiu

11 months ago

Thrilled to be featured in the #ICLR2025 Spotlight! 🎉 Come see our poster in Hall 3 + Hall 2B #602, April 25, 10:00–12:30 PM SGT

1 4 15 4K 1

Download Image

1 1 4 1K 0

Cognitive Computation Group @cogcomp

4 months ago

Excited to share our papers at #ICLR2025 in Singapore! Check out the summaries on our blog (ccgblog.seas.upenn.edu/2025/04/ccg-pa…), and then check out the papers at oral session 1B (BIRD) and poster session 2 (for all three)! @AnnieFeng6, @XingyuFu2, @BenZhou96, @muhao_chen, @DanRothNLP

0 4 8 1K 1

Download Image

Fei Wang @fwang_nlp

4 months ago

🎉 Excited to share that our paper, "MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding", will be presented at #ICLR2025! 📅 Date: April 24 🕒 Time: 3:00 PM 📍 Location: Hall 3 + Hall 2B #11 MuirBench challenges multimodal LLMs with diverse multi-image…

0 18 54 3K 5

Download Image

Yu Feng @AnnieFeng6

5 months ago

#ICLR2025 Oral LLMs often struggle with reliable and consistent decisions under uncertainty 😵‍💫 — largely because they can't reliably estimate the probability of each choice. We propose BIRD 🐦, a framework that significantly enhances LLM decision making under uncertainty. BIRD…

2 39 259 28K 184

Download Image

Fei Liu @feiliu_nlp

5 months ago

Curious how LLMs tackle planning tasks, such as travel and computer use? Our new survey #PlanGenLLMs (arxiv.org/abs/2502.11221) builds on classic work by Kartam and Wilkins (1990) and examines 6 key metrics to compare today's top planning systems. Your next agentic workflow…

0 4 33 4K 5

Download Image

Tu Vu @tuvllms

5 months ago

📢 Research internship @Google📢 I am looking for a PhD student researcher to work with me and my colleagues on advanced reasoning and/or RAG factuality this summer @Google Mountain View, CA. We will focus on open-source models and benchmarks, and aim to publish our findings.…

3 38 345 37K 208

Fei Liu @feiliu_nlp

5 months ago

🤖 Imagine a world where everyone has a personalized LLM agent by their side! Our latest research (arxiv.org/abs/2502.12149) explores how persona dynamics influence multi-agent competitive auctions. 🏆 Discover who wins, who loses, and the impact of personas on competitiveness!