CWM shows that reasoning can benefit from step-by-step simulation of code execution.
🔹 Our latest evaluation results show that CWM achieves 47% accuracy on LogicIFEval, ranking #1 among all tested public models!
📄 LogicIF Paper: arxiv.org/pdf/2508.09125
This result suggests…
CWM shows that reasoning can benefit from step-by-step simulation of code execution.
🔹 Our latest evaluation results show that CWM achieves 47% accuracy on LogicIFEval, ranking #1 among all tested public models!
📄 LogicIF Paper: arxiv.org/pdf/2508.09125
This result suggests…
(1/6) A pathway for an LLM to become a great scientist like Isaac Newton!✨
🚨 New survey out! We explore how LLMs can be used for hypothesis discovery—uncovering new knowledge via reasoning. This is the first survey to present a unified framework connecting Abduction, Induction,…
Check out our new work investigating how RAG deals with retrieved info vs. parametric knowledge under different user instructions. We conduct systematic analysis to showcase LLM performances under a spectrum of real world use cases.
📄preprint: arxiv.org/abs/2502.19779…
Check out our new work investigating how RAG deals with retrieved info vs. parametric knowledge under different user instructions. We conduct systematic analysis to showcase LLM performances under a spectrum of real world use cases.
📄preprint: arxiv.org/abs/2502.19779…
We find suboptimal agentic searches are often caused by LLMs’ limited awareness of their own knowledge boundaries and propose an uncertainty-aware variant of GRPO to help mitigate suboptimal searches. Check out the paper for more analysis and results!
We find suboptimal agentic searches are often caused by LLMs’ limited awareness of their own knowledge boundaries and propose an uncertainty-aware variant of GRPO to help mitigate suboptimal searches. Check out the paper for more analysis and results!
103 Followers 524 FollowingCS PhD @OSUNLP with @ysu_nlp. Prev @AIatMeta @MSFTResearch @GoogleDeepMind. my former account @DrogoKhal4 was wrongly suspended...
45 Followers 81 Following🔬 Senior Research Scientist at Tencent AI Lab 🤖
📚 Passionate about LLM, NLP, & Summarization 📝
🤝 Building AI Assistants to Boost Productivity 🚀
#AI #NLP
554 Followers 381 FollowingClinical Psychologist, Founder of The Brightly Project • school-based mental health, computational psychiatry, statistics and machine learning for mental health
25 Followers 247 FollowingExpecting a better society with AI assistants.
PhD Student @ Soochow University.
Information Extraction & Mixture-of-Experts.
103 Followers 524 FollowingCS PhD @OSUNLP with @ysu_nlp. Prev @AIatMeta @MSFTResearch @GoogleDeepMind. my former account @DrogoKhal4 was wrongly suspended...
6K Followers 373 FollowingSafety and alignment at Meta Superintelligence. Prev: VP of Research at Scale AI, research at Google DeepMind / Brain (Gemini, LaMDA, RL / TFAgents, AlphaChip).
19K Followers 20 FollowingA high-throughput and memory-efficient inference and serving engine for LLMs. Join https://t.co/lxJ0SfX5pJ to discuss together with the community!
45 Followers 81 Following🔬 Senior Research Scientist at Tencent AI Lab 🤖
📚 Passionate about LLM, NLP, & Summarization 📝
🤝 Building AI Assistants to Boost Productivity 🚀
#AI #NLP
1.2M Followers 279 FollowingWe’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.