Deep Learning For Code (DL4C) Workshop (ICLR'22, '23, '25, NeurIPS'25, and soon ICML'26)
Seoul
Joined October 2021
- Tweets128
- Following34
- Followers1.1K
- Likes53
Deep Learning For Code @ ICML'26 retweeted
At @icmlconf 🇰🇷 this week and excited to host the 5th @DL4Code this Friday! We have an amazing lineup of speakers:
- @Diyi_Yang (@stanfordnlp/@humansand)
- @syhw (@AIatMeta)
- @lschmidt3 (@Stanford/@AnthropicAI)
- @LittleXie5 (@hkust/@Alibaba_Qwen)
plus great papers and custom DL4C swag!📍HALL B2
Also very proud of two of my past interns presenting at the main conference:
- @terryyuezhuo on "Training Language Model Agents to Find Vulnerabilities with CTF-Dojo" Tue 2pm HALL A #3314
- @setlur_amrith on "Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes" Wed 10:30am HALL A #1902
Come say hi! ☕️👋
Deep Learning For Code @ ICML'26 retweeted
🚨 Due to overwhelming interest, we’re extending the workshop submission deadline to May 19, 2026 @ 11:59 PM AOE ⏰
You’ve got extra time and submit your best work! 📄✨
🚀 5th DL4C Workshop @ ICML'26
Towards Human-Centered Coding Agents! 🤖👥
Deadline: May 15, 2026 ⏰
Submit now: openreview.net/group?id=ICML…
Deep Learning For Code @ ICML'26 retweeted
Excited to share that 𝘁𝗵𝗲 𝟱𝘁𝗵 @DL4Code 𝘄𝗼𝗿𝗸𝘀𝗵𝗼𝗽 𝗶𝘀 𝗰𝗼𝗺𝗶𝗻𝗴 𝘁𝗼 #ICML2026🇰🇷. Grateful to everyone who helped make this such an energizing space for the field!
Also, a belated update on our position paper 𝗛𝘂𝗺𝗮𝗻𝘀 𝗮𝗿𝗲 𝗠𝗶𝘀𝘀𝗶𝗻𝗴 𝗳𝗿𝗼𝗺 𝗔𝗜 𝗖𝗼𝗱𝗶𝗻𝗴 𝗔𝗴𝗲𝗻𝘁 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵. What I’m especially proud of in the paper is the core argument: the next frontier for coding agents is not just more autonomy, but better human collaboration. As agents get stronger, the real bottleneck is increasingly whether people can align with them, steer them, verify their outputs, and trust them in real workflows. We turn that observation into concrete research agenda for building coding agents that are genuinely more useful.
The seed for this paper came from an early conversation with the awesome @KLieret at #NeurIPS. I later discussed the idea with @jyangballin, which led to further conversations with @ZhiruoW @Diyi_Yang, and the final paper was led by these folks together with a fantastic group of co-authors. Parts of the argument were also shaped by wonderful discussions at the #DL4C workshops at #ICLR and #NeurIPS last year.
Check it out! zorazrw.github.io/files/posi…
Deep Learning For Code @ ICML'26 retweeted
Often, a bug I have had to fix has been tied directly to overly verbose or defensive code from an AI agent that has eroded my project as the specs changed. Why isn't there an eval for this?
There is now. Very excited to announce SlopCodeBench scbench.ai
Deep Learning For Code @ ICML'26 retweeted
I will be talking about the Future of Multimodal AI applications at this @iclr_conf workshop on Monday 28th April at 2 pm local time #ICLR25 dl4c.github.io/schedule/ – at Minato-ku, Tokyo
Deep Learning For Code @ ICML'26 retweeted
Cannot attend #ICLR2025 in person (will be NAACL and Stanford soon!), but do check out 👇
▪️Apr 27: "Exploring the Pre-conditions for Memory-Learning Agents" led by @viishruth and Vishwa Shah, at SSI-FM workshop
▪️Apr 28: our @DL4Code workshop with a fantastic line of works & speakers!
▪️Apr 28: @dan_fried's talk at the DL4C about "Inducing Functions to Improve LLM Agents"
Just 6 days until #DL4C! 🗓️ Daniel Fried (CMU / Meta AI) @dan_fried @AIatMeta will be sharing insights on how inducing functions from code makes LLM agents smarter and more efficient. Don't miss it! See you Sunday! #ICLR2025 #iclr
Deep Learning For Code @ ICML'26 retweeted
Deep Learning For Code @ ICML'26 retweeted
🚀Thrilled to announce that the Deep Learning for Code (@DL4Code) workshop is returning to @ICLR_conf'25!
Looking forward to your submissions and meeting everyone in Singapore this April! Check out the full details in the thread below ⬇️
🚀Excited to share the 3rd Deep Learning for Code workshop is back at @iclr_conf'25! This year we’ll focus on emergent challenges in the field, e.g., agents, post-training, developer productivity, open science, and benchmarking for code Submit by Feb 3 dl4c.github.io🧵⬇️
Deep Learning For Code @ ICML'26 retweeted
After a successful launch of 💫StarCoder - our new 15B LLM for code. I'm Happy to be presenting this afternoon our previous paper "SantaCoder: don't reach for the stars!" aka smol StarCoder at ICLR @DL4Code workshop this afternoon. #ICLR2023
huggingface.co/blog/starcode…
Deep Learning For Code @ ICML'26 retweeted
A series of exciting workshops are lined up for ICLR 2023:
blog.iclr.cc/2022/12/21/anno…. Please consider contributing to the workshops and joining the first major AI conference in Africa. #ICLR
Deep Learning For Code @ ICML'26 retweeted
Excited to share that the second installment of Deep Learning for Code workshop is back at ICLR 2023! Considering submitting your work by Feb 3rd, 2023. Details: dl4c.github.io/callforpapers…
@tscholak @GOrlanski @DL4Code
Deep Learning For Code @ ICML'26 retweeted
Submissions are now open at: openreview.net/group?id=ICLR….
Deep Learning For Code @ ICML'26 retweeted
Excited to co-organize the 2nd @DL4Code workshop w/ @DishaShrivasta9 @tscholak @GOrlanski . We are looking for contributions (due Feb. 3) and reviewers. See dl4c.github.io/callforpapers… for details. Workshop sponsored by @AmazonScience
Excited to share that the second installment of Deep Learning for Code workshop is back at ICLR 2023! Considering submitting your work by Feb 3rd, 2023. Details: dl4c.github.io/callforpapers…
@tscholak @GOrlanski @DL4Code
Deep Learning For Code @ ICML'26 retweeted
Thrilled to share our work on Scotch today at @DL4Code workshop at #ICLR2022.
Scotch is a contextual and semantic code search engine for IDEs, eliminating the need to navigate to web browsers to search for code.
Paper: openreview.net/forum?id=rSxf…
@adyasha10 @mohitban47 @uncnlp
Deep Learning For Code @ ICML'26 retweeted
Tomorrow, excited to present some recent work on using natural language supervision to build better models of policies and programs at the @DL4Code workshop!
ALT Sample talk slide. Text: "Programs are compositional. This compositional structure is reflected in language!" Images: plans and graphics programs accompanied by natural language descriptions.
Deep Learning For Code @ ICML'26 retweeted
Tomorrow we will present our spotlight presentation and poster at the @DL4Code workshop at @iclr_conf! Come to chat!
Paper:
CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
openreview.net/forum?id=rd-G…
Deep Learning For Code @ ICML'26 retweeted
We'll be presenting our Scratchpad work at the Deep Learning for Code workshop (@DL4Code) at @iclr_conf Friday 2pm ET / 11am PT!
Come say hi!
New paper! arxiv.org/abs/2112.00114
We show that huge language models (137B params!) can be trained to solve algorithmic tasks by “showing their work”---writing intermediate text to a scratchpad. This “scratchpad” technique even allows us to predict the execution of Python code.
Deep Learning For Code @ ICML'26 retweeted
Hi there! I will host the Deep Learning for Code panel at the @DL4Code workshop at @iclr_conf on Friday at 1pm EDT. If you have questions for our amazing panelists, please use this form, forms.gle/NaQJdiVsF69Uj99G8, and select "Panel Discussion", and I will try to include them. – at Montréal, Québec
ALT The DL4C Panelists
Deep Learning For Code @ ICML'26 retweeted
Excited to announce our work: Learning to Superoptimize Real-World Programs has been selected as the best paper at the @DL4Code workshop! Congrats and a huge thanks as well to my co-authors @gneubig, Ed Schwartz, @pengchengyin, @clegoues, and @jlacomis. dl4c.github.io/papers/