Jie He (@Jiehenlp) / X

Jie He

42 posts

Jie He

@Jiehenlp

PhD student in #NLProc @EdinburghNLP & @InfAtEd, @Apple AI/ML PhD Fellow

Joined February 2016

Jie He
@Jiehenlp
Jul 9
Excited to share that our work has been accepted to #COLM! Huge thanks to my amazing collaborators @richard_baihe, @sineadwilliamso , Jeff Z. Pan, Navdeep Jaitly, and @YizheZhangNLP !! I’ll likely be in San Francisco from Oct. 6–9 for the conference. Feel free to reach out!🤝
Jie He
@Jiehenlp
Nov 25, 2025
Happy to introduce my internship work at @Apple . We introduce CLaRa: Continuous Latent Reasoning, an end-to-end training framework that jointly trains retrieval and generation ! 🧠📦 🔗 arxiv.org/pdf/2511.18659… #RAG #LLMs #Retrieval #Reasoning #AI
Jie He
@Jiehenlp
Nov 27, 2025
Thanks to @_akhaliq for introducing our work on building a continuous-representation bridge for retrieval and generation. For more details, please check out our code: github.com/apple/ml-clara and our model: huggingface.co/collections/pr…
AK
@_akhaliq
Nov 27, 2025
Apple presents CLaRa Bridging Retrieval and Generation with Continuous Latent Reasoning
Jie He
@Jiehenlp
Nov 25, 2025
Happy to introduce my internship work at @Apple . We introduce CLaRa: Continuous Latent Reasoning, an end-to-end training framework that jointly trains retrieval and generation ! 🧠📦 🔗 arxiv.org/pdf/2511.18659… #RAG #LLMs #Retrieval #Reasoning #AI
Jie He
@Jiehenlp
Jul 30, 2025
I couldn’t make it to #ACL2025, but excited to share our paper GenTool from @MSFTResearch and @EdinburghUni! aclanthology.org/2025.findings-… We introduce GenTool: a training framework that simulates zero-to-one and weak-to-strong tool transitions to boost tool generalization in LLMs.
aclanthology.org
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong...
Jie He, Jennifer Neville, Mengting Wan, Longqi Yang, Hui Liu, Xiaofeng Xu, Xia Song, Jeff Z. Pan, Pei Zhou. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
Jie He
@Jiehenlp
Oct 7, 2023
Excited to share that our paper titled "Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification" has been accepted at the finding of #emnlp2023 together w/Simon, @vicgtzbasulto, @jpansw!🎉 Stay tuned for more.