iiinova — where your digital self keeps evolving

Lin Tan @lin-tan.bsky.social · 11/10/2025

Want to go to Brazil with travel support? Check out #SMeW — a great opportunity for students to learn, connect & grow! I co-chaired its 2019 launch (with Lori Pollock & Christian Kästner, with tremendous support by #ICSE19 GC Jo Atlee) and coined the name (yes, the duck 🦆)! @icseconf.bsky.social

022

Lin Tan @lin-tan.bsky.social · 01/10/2025

We welcome broad LLM for code work - code broadly defined including source code, binary code, intermediate code, web code, LaTeX code, etc. - entire code development life cycle: including generation and benchmarking of formal specifications, code, tests, … - and more

020

Lin Tan @lin-tan.bsky.social · 01/10/2025

Excited to announce the 3rd LLM4Code workshop collocated with ICSE26 @icseconf.bsky.social in Rio de Janeiro, Brazil 🇧🇷! 🌟Website: llm4code.github.io 🌟Deadline: Oct 20, 2025 🌟8-page research paper / 4-page position paper (including references) @llingming.bsky.social @devanbu.bsky.social

llm4code.github.io

Home

ICSE 2026 Workshop on Large Language Model for Code

241

Lin Tan @lin-tan.bsky.social · 19/05/2025

At #ICRA2025? Check out my student Yi Wu’s talk (TuCT1.4) at 3:30PM Tuesday in Room 302 at the Award Finalists 3 Session about how SELP Generates Safe and Efficient Plans for #Robot #Agents with #LLMs! #ConstrainedDecoding #LLMPlanner @purduecs.bsky.social @cerias.bsky.social

040

Lin Tan @lin-tan.bsky.social · 09/05/2025

Purdue, leaders in AI, pharma manufacturing and public policy gather at D.C. event to launch a national effort to expand AI-enabled medicine production in U.S. www.purdue.edu/newsroom/202... @purduecs.bsky.social @cerias.bsky.social #AI #Purdue #Medicine

purdue.edu

Lin Tan @lin-tan.bsky.social · 07/05/2025

Big congratulations! Very well deserved!

120

Reposted by Lin Tan

Marcel Böhme @mboehme.bsky.social · 03/05/2025

✨️ Now that #ICSE25 is over, it's time to get your papers ready for #ASE25 (30th May)! 📢 Here is what's new: * Major Revision v2.0 * Review criteria for tech. & experience papers * Policy on LLM-assisted Reviews * Auto-bidding (TPMS) * Rapid Response Reliable Reviewers 👇 For more details, read on.

12413

Lin Tan @lin-tan.bsky.social · 02/05/2025

At ICSE @icseconf.bsky.social 2025? Check out Jiannan Wang’s D3 talk at 2:30 PM today Friday in Room 215 about how we find real-world bugs in production distributed systems code! #deepleanring #distributed #testing

040

Reposted by Lin Tan

International Conference on Software Engineering @icseconf.bsky.social · 02/05/2025

🌍 The future of #icse is global! 🇧🇷 ICSE 2026 – Brazil #icse2026 🇮🇪 ICSE 2027 – Ireland #icse2027 🌺 ICSE 2028 – Hawaii #icse2028 We can't wait to see you there! Pack your ideas and your passport. 🧳✈️

1159

Reposted by Lin Tan

Andreas Zeller @andreaszeller.bsky.social · 01/05/2025

Fun fact: Of my nine papers that got a long-term impact award, none got a “best paper” award when they were published - and conversely, none of my “best paper”-awarded papers got an impact award later. Is this a common phenomenon?

A list of test of time awards for papers with Andreas Zeller as co-author

4222

Lin Tan @lin-tan.bsky.social · 01/05/2025

Congratulations, Andreas! Very well deserved!

020

Lin Tan @lin-tan.bsky.social · 26/04/2025

Our SELP paper is an #ICRA25 Best Paper Award Finalist, among a selected few from 4,153 submissions! 🏆 Proud of my PhD student Yi Wu & the team! www.cs.purdue.edu/homes/lintan... #robotics #LLM #ConstrainedDecoding #Agent #LLMPlanner @cerias.bsky.social

cs.purdue.edu

041

Reposted by Lin Tan

Jingbo Wang @jingbow.bsky.social · 28/03/2025

PLMW@PLDI'25 is now accepting applications: pldi25.sigplan.org/home/PLMW-pl... Deadline: April 10, 2025 PLMW an excellent place to learn about exciting PL research, from the ground up, and to find your PL friends! Please apply!

pldi25.sigplan.org

PLMW @ PLDI 2025 - Programming Languages Mentoring Workshop - PLDI 2025

The Programming Language Mentoring Workshop (PLMW) aims to broaden the exposure of late-stage undergraduate students and early-stage graduate students to research and career opportunities in programmi...

0169

Lin Tan @lin-tan.bsky.social · 08/03/2025

2/2 Stay tuned for more details at our #ICSE2025 presentation! Co-authors: Jiannan Wang, Hung Viet Pham, Qi Li, Yu Guo, Adnan Aziz, and Erik Meijer. #DistributedDL #AI

Lin Tan @lin-tan.bsky.social · 08/03/2025

1/2 D3 introduces the first differential testing technique specially designed for distributed DL software. D3 leverages a new distributed equivalence rule and automatically generates diverse distributed settings, models, and model inputs.

Lin Tan @lin-tan.bsky.social · 08/03/2025

🚀 Thrilled to share our #TSE journal-first paper D3: Differential Testing of Distributed Deep Learning (DL)! @Jianan will present it at #ICSE2025. D3 detects 21 bugs (12 new!) in PyTorch and TensorFlow. 🔗 www.cs.purdue.edu/homes/lintan... #DeepLearning #SoftwareTesting @cerias.bsky.social

230

Reposted by Lin Tan

Association for Computing Machinery @acm.org · 05/03/2025

Meet the recipients of the 2024 ACM A.M. Turing Award, Andrew G. Barto and Richard S. Sutton! They are recognized for developing the conceptual and algorithmic foundations of reinforcement learning. Please join us in congratulating the two recipients! bit.ly/4hpdsbD

12411

3/3 📊 Our experiments demonstrate SELP’s effectiveness across diverse tasks. In drone navigation, SELP outperforms state-of-the-art LLM planners by 10.8% in safety rate and by 19.8% in plan efficiency. For robot manipulation, SELP achieves a 20.4% improvement in safety rate.

2/3 3️⃣ Domain-Specific Fine-Tuning: Customizes LLMs for specific robotic tasks, boosting both safety and efficiency.

1/3 💡SELP has 3 key insights: 1️⃣ Equivalence Voting: Ensures robust translations from natural language instructions into LTL specifications. 2️⃣ Constrained Decoding: Uses the generated LTL formula to guide the inference of plans, ensuring the generated plans conform to the LTL.

Introducing our first #ICRA2025 paper, SELP (Safe Efficient LLM Planner), a method for generating plans for robot agents that adhere to user constraints while optimizing for time-efficient execution. Preprint: arxiv.org/pdf/2409.19471 #LLMs #Robotics #Agent @cerias.bsky.social @purduecs.bsky.social

3101

5/5 Thus, combined with the increasing sophistication of cybercrime that poses significant threats worldwide (e.g., cybercrime is predicted to cost the world $10.5 trillion annually by 2025 (Sausalito, 2020)), effective binary analysis techniques are in high demand.

020

4/5 For example, when performing tasks such as identifying attacks and malware, security analysts often only have access to assembly, i.e., the human-readable representation of binary code, which is extremely difficult to understand.

3/5 Why binaries and binary models? Binary code plays an irreplaceable role in crucial tasks, including vulnerability detection, malware detection, binary recovery, and legacy software maintenance.

2/5 Smaller 1.3B models huggingface.co/lt-asset/nov... huggingface.co/lt-asset/nov... Binaries are a form of code. Do not forget about binaries when you work on #LLM4Code.

huggingface.co

lt-asset/nova-6.7b · Hugging Face

1/5 Highlights: 1. Nova is built with hierarchical attention specially designed for binary and contrastive learning. 2. Nova is pre-trained on 3B binary and source code tokens. 3. Models: huggingface.co/lt-asset/nov... huggingface.co/lt-asset/nov...

huggingface.co

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Introducing Nova (ICLR’25), foundation models for binary/assembly code. We have also released fine-tuned models for binary code decompilation. Preprint: arxiv.org/pdf/2311.13721 #LLM4Code #LLM #BinaryAnalysis #Security @cerias.bsky.social @iclr-conf.bsky.social

562

4. Smaller 1.3B models huggingface.co/lt-asset/nov... huggingface.co/lt-asset/nov... Binaries are a form of code. Do not forget about binaries when you work on #LLM4Code.

huggingface.co

(2) democratizing programming to people with little technical background, through AI systems capable of self-planning with easy-to-follow explanations, enabling users to program through natural languages. #SoftwareEngineering #SE @cerias.bsky.social

Nan's future research interests include (1) creating AI-powered systems capable of collaborating with human developers in the whole development lifecycle, managing large-scale projects, understanding dynamic code execution, and integrating with developers' workflow, and …

Our paper LATTE accepted at AAAI’25 is a great addition to his profile. His research focuses on using software domain knowledge to develop accurate and practical AI assistants that support tasks in software development, including code generation, program repair, and security testing.