InteNSE
@InteNSEWorkshop
Followers
48
Following
2
Media
9
Statuses
37
InteNSE workshop concerns Interpretability, Robustness (Generalizability), and Benchmarking in Neural Software Engineering. Co-located with @ICSEconf
Lisbon, Portugal
Joined November 2022
If you're working on benchmarking/interpreting Code LLMs, or evaluating their generalizability to different programming tasks, consider submitting your work to @ConfForge!.
0
0
0
InteNSE workshop is accepted to appear @ICSEconf 2025. However, we decided to merge our efforts in promoting non-functional properties of LLMs (interpretability/generalizability/robustness) and benchmarking them with the @ConfForge conference, co-located with @ICSEconf ☺️.
1
0
0
Max Hort presented their most recent research at Simula Research Lab on the impact of LLM non-determinism for log parsing
0
0
3
Carlos Jimenez is presenting the well-known benchmark, SWE-bench at the InteNSE workshop.
0
0
0
Dylan Zhang presented a work on interpreting transformers to better understand how they deal with recursion
0
0
2
The last session of the workshop consists of two talks on (1) interpreting transformer models to demystify how they learn recursion and (2) SWE-Bench. Starting in 10 minutes!.
0
0
0
The tutorial on neuro-symbolic programming is about to start. Please join if you're interested.
0
0
2
Mark Harman starts his keynote with the story of how he gets where he is 🙂
0
0
1
Our first keynote, Denys Poshyvanyk, talked about how important it is to address the hard problem of interpretability in the software engineering community.
0
0
1
We're starting in an hour, with a paper presentation and keynote! Looking forward to seeing you all 😊.
0
0
0
The participants will gain hands-on experience in how to write neurosymbolic programs that include both neural networks and traditional symbolic programs (e.g., with if-then-else statements).
0
0
0
The tutorial will focus on neurosymbolic programming, an emerging programming paradigm that bridges the areas of deep learning and program languages. Neurosymbolic programming can offer multiple advantages over end-to-end deep learning.
1
0
0
We have a new component at InteNSE'24: A Neuro-symbolic Programming Tutorial. Please find additional information about the tutorial in this thread. (1) Registration for the InteNSE workshop AND (2) filling out the following form are mandatory to attend:
1
1
2
We sent the notifications out this morning and are working to finalize the program soon! Congratulations to the authors of the accepted papers. We have exciting news to come! Stay tuned.
0
1
1
Good news! We are extending the submission deadline to December 15th! Keep working on those interesting submissions to get a chance to attend ICSE'24 and InteNSE'24 workshop. We have awesome keynote speakers and interesting workshop components that we will announce soon!.
0
1
2
Less than two weeks until the submission deadline! Submit your awesome research to the InteNSE workshop and secure a space for attending two amazing keynotes by Mark Harman (@Mark_Harman @Meta) and Denys Poshyvanyk (@williamandmary).
0
1
2
We are looking for energetic people to serve on the PC of InteNSE workshop. If your research is at the intersection of machine learning and software engineering, please self-nominate yourself:
docs.google.com
We are at the process of forming InteNSE'24 workshop. The workshop concerns interpretability, robustness/generalizability, and benchmarking of code language models. The focus of this year is on LLMs...
0
4
7
Check out the website for more information about the CFP and important dates:
0
0
0
We are also interested in seeing positive or negative results related to utilizing LLMs on real-world, more complex projects than simple, crafted benchmarks. New metrics to evaluate and benchmark LLMs for Code is another topic of interest.
0
1
0