Heng Ji
@hengjinlp
We are extremely excited to announce mCLM, a Modular Chemical Language Model that is friendly to automatable block-based chemistry and mimics bilingual speakers by “code-switching” between functional molecular modules and natural language descriptions of the functions. 1/2
We cast software issue localization (identifying where to make the fix given a bug report) as a code ranking problem. Our proposed SWERank framework significantly outperforms agent-based systems, while being considerably more cost effective. Our 7B SWERankEmbed retriever even…
🆕Excited to announce SWERank, our code ranking framework for software issue localization. ➡️Paper: bit.ly/3S0x1fV ➡️GitHub Project Page: bit.ly/42SESm3 ➡️AI-Generated Podcast: bit.ly/3GMF51H ➡️Code, Data and Models: Coming soon! (1/3) 🧵 Pinpointing…
We're excited to be hosting Alexi for a talk on Energy-Based Transformers on July 23rd! Sign-up here: lu.ma/m3j5yucg
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…
Awesome work!
Grateful for the chance to present EmbodiedBench at ICML as an Oral. A rewarding experience full of learning. Thanks for @RuiYang70669025 @hengjinlp @jyzhang1208 @huan_zhang12 Mark_Zhao @ManlingLi_ Tong_Zhang and many others who make it possible. See you next time.
Constantly receiving these super generous compliments, mentoring and support ftom my collaborators is the major reason for me to stay at UIUC. siebelschool.illinois.edu/news/AI-medici…
Very proud of this work on energy based model by the amazing @AlexiGlad
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 AI evolve from statically 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨 𝘢𝘣𝘰𝘶𝘵 𝘪𝘮𝘢𝘨𝘦𝘴 → dynamically 𝘵𝘩𝘪𝘯𝘬𝘪𝘯𝘨 𝘸𝘪𝘵𝘩 𝘪𝘮𝘢𝘨𝘦𝘴 as cognitive workspaces, similar to the human mental sketchpad? 🔍 What’s the 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗿𝗼𝗮𝗱𝗺𝗮𝗽 from tool-use → programmatic…
I’m looking for a new postdoc to start this fall working on AI for Science/Science-Inspired AI (focusing on chemistry and bioengineering domains for now). Please drop me a CV if interested.
We are looking to publish our paper on LLM bias in hiring decisions to arXiv, and are looking for a cs.LG endorsement! Reach out if you'd like to read the full paper! The endorsement link is here: arxiv.org/auth/endorse?x… @hengjinlp @arxivblog @arxiv @ArXiv_articles @Arxiv_Daily
We’ve been seeing amazing results from trying out the SWERank framework on public GitHub issues. We’re looking for support in building a VSCode plugin/PR review bot to assist developers with issue localization. If you’re interested, please DM!
We cast software issue localization (identifying where to make the fix given a bug report) as a code ranking problem. Our proposed SWERank framework significantly outperforms agent-based systems, while being considerably more cost effective. Our 7B SWERankEmbed retriever even…
The models and code are now public! Models on HF: huggingface.co/collections/Sa… Code: github.com/SalesforceAIRe… Project Page: salesforceairesearch.github.io/SweRank/ If you are interesting in integrating the SweRank models as a plug-in within VS Code, please do reach out! We have more exciting…
📣 SweRank: How AI is Revolutionizing Software Issue Localization 📣 See how it works: bit.ly/44pQw8G SweRank offers a more efficient solution for locating exact code parts that need modification to resolve software issues, using a two-step "retrieve-and-rerank"…
🧠Let’s teach LLMs to learn smarter, not harder💥[arxiv.org/pdf/2506.06972] 🤖How can LLMs verify complex scientific information efficiently? 🚀We propose modular, reusable atomic reasoning skills that reduce LLMs’ cognitive load to verify scientific claims with little data.…
Yangyi is awesome and moves extremely fast. Hire him!
🚀 I'm looking for full-time research scientist jobs on foundation models! I study pre-training and post-training of foundation models, and LLM-based coding agents. The figure highlights my research/publications. Please DM me if there is any good fit! Highly appreciated!
Congratulations and I’m super proud of you! @AlexiGlad
I am super grateful to find out I got the @NSF GRFP! My award level got switched from honorable mention to awardee. Huge thanks to @hengjinlp @LiJundong @BeingMIAkashs @tiqbal_uva Di Wang @uiuc_nlp @siebelschool @UofIllinois Excited to work on ambitious and fundamental AI…
🔥Today is submission deadline (June 6th AoE) of our 𝐀𝐂𝐋 𝟐𝟎𝟐𝟓 𝐰𝐨𝐫𝐤𝐬𝐡𝐨𝐩: 𝐓𝐨𝐰𝐚𝐫𝐝𝐬 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞𝐚𝐛𝐥𝐞 𝐅𝐨𝐮𝐧𝐝𝐚𝐭𝐢𝐨𝐧 𝐌𝐨𝐝𝐞𝐥𝐬!🔥 🔗workshop website: knowledgeable-lm.github.io 🔗 submission portal: openreview.net/group?id=aclwe… 🏆 The Best Paper…
In partnership with @CapitalOne we’ve launched the Center for Generative Artificial Intelligence Safety, Knowledge Systems and Cybersecurity (ASKS). A $3M pledge from Capital One will fund fellowships for cutting-edge #GenAI research. siebelschool.illinois.edu/news/capitalon…
What’s is the agent? What is the optimal behavior to achieve the predefined goal? And how to learn that behavior policy? We formally introduce a systematic Theory of Agent (ToA), analogous to the cognitive framework of Theory of Mind (ToM). Where ToM refers to the ability to…
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…