Simeng Sun
@simeng_ssun
Followers
452
Following
1K
Statuses
173
Research Scientist @nvidia. ex: PhD @UMassCS; Intern @MSFTResearch, @MetaAI, @AdobeResearch.
Joined June 2019
RT @xiangyue96: Demystifying Long CoT Reasoning in LLMs Reasoning models like R1 / O1 / O3 have gained massive atte…
0
193
0
RT @JaechulRoh: 🧠💸 "We made reasoning models overthink — and it's costing them big time." Meet 🤯 #OVERTHINK 🤯 — our new attack that forces…
0
33
0
RT @zied_houidi: 1/12 We just found something unsettling: Today's most advanced AI models - including the latest powerhouse reasoning model…
0
118
0
RT @kuchaev: Our team put together a unified mathematical framework to analyze popular model alignment algorithms. “Reward-aware Preference…
0
19
0
RT @DimitrisPapail: Transformers can overcome easy-to-hard and length generalization challenges through recursive self-improvement. Paper…
0
150
0
RT @jennajrussell: People often claim they know when ChatGPT wrote something, but are they as accurate as they think? Turns out that while…
0
148
0
RT @DanHendrycks: We’re releasing Humanity’s Last Exam, a dataset with 3,000 questions developed with hundreds of subject matter experts to…
0
802
0
RT @SonglinYang4: I've created slides for those curious about the recent rapid progress in linear attention: from linear attention to Light…
0
173
0
RT @drjingjing2026: 1/3 Today, an anecdote shared by an invited speaker at #NeurIPS2024 left many Chinese scholars, myself included, feelin…
0
631
0
RT @lilianweng: 🦃 At the end of Thanksgiving holidays, I finally finished the piece on reward hacking. Not an easy one to write, phew. Rew…
0
225
0
RT @PavloMolchanov: 🚀 Introducing Hymba-1.5B: a new hybrid architecture for efficient small language models! ✅ Outperforms Llama, Qwen, an…
0
56
0
RT @PavloMolchanov: Sharing our team’s latest work on Hymba - an efficient small language model with hybrid architecture. Tech report: htt…
0
94
0
RT @mat_jacob1002: It's time to revisit common assumptions in IR! Embeddings have improved drastically, but mainstream IR evals have stagna…
0
43
0
RT @brendan642: We're hiring new #nlproc faculty this year! Asst or Assoc Professors in NLP at UMass CICS --
0
4
0
RT @AkariAsai: 1/ Introducing ᴏᴘᴇɴꜱᴄʜᴏʟᴀʀ: a retrieval-augmented LM to help scientists synthesize knowledge 📚 @uwnlp @allen_ai With open m…
0
267
0
RT @MohitIyyer: Underspecified queries (e.g. "tell me about birds") are rife in benchmarks like Chatbot Arena. How do we eval responses wit…
0
8
0
RT @yixiao_song: Are you at EMNLP '24, and looking for an accurate metric for factuality evaluation? ✨ Check out our poster presentation o…
0
12
0
RT @mar_kar_: Will be presenting #nocha at #EMNLP2024 (Tue 16:00-17:30 (Riverfront Hall). Also happy to share that we have updated the data…
0
5
0
RT @chautmpham: TopicGPT is now available as a Python package! You can use it to generate, refine, and assign topics with LLMs (we suppor…
0
21
0