Located in Paris, Available Remote
Paris, FR
Joined July 2026
- Tweets16
- Following101
- Followers34
- Likes21
2026 NeurIPS Workshop on Network Artifacts As Data retweeted
Hot take: this isn’t fully new ;) weight space learning / model modification has been around for a sec
Interested in learning more? Come to our NeurIPS workshop @artifactsasdata
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
We just released paper decisions ✨✨✨ Congrats to all those with accepted papers, & thank you to the reviewers, ACs and PCs that made all of this possible.
We’re slowly working through our inbox—if your work was accepted, expect a few follow-ups soon.
2026 NeurIPS Workshop on Network Artifacts As Data retweeted
(1/n) 🧠 Neural Network Artifacts Workshop at @NeurIPSConf 2026!
🔗 Details: lnkd.in/daifXMQC
#NeurIPS2026 #NeuralNetworkArtifactsWorkshop #MachineLearning #ArchimedesUnit #AthenaResearchCenter
Neural Network Artifacts Are Data Too!
📣Join us for our 2026 @neuripsConf workshop on how to learn from populations of weights, gradients, representations, training trajectories & more.
🗓️ Deadline: Sept 1st AoE
🔗 artifactsasdata.org/
2026 NeurIPS Workshop on Network Artifacts As Data retweeted
Introducing Parallax 🔍
We're a new UK/EU-based nonprofit research lab building scalable methods and infrastructure to audit the beliefs, goals, and plans that shape model behaviours in long-horizon agentic evaluations.
parallx.ai — Thread 🧵 1/
⏳ Less than one week until our CFP closes!
Working on model populations, weights, gradients, representations, or training trajectories? We'd love to see your work at our #NeurIPS2026 workshop on neural network artifacts.
🗓 Deadline: Sept 1 AoE
artifactsasdata.org/
Excited to announce Naomi Saphra (Assistant Professor @BU_Tweets) as an invited speaker for the NeurIPS 2026 Workshop on Neural Network Artifacts as a New Data Modality!
🗓️ CFP deadline: Sept 1, 2026 — submit via OpenReview!
📄 CFP: artifactsasdata.org/cfp
@nsaphra's work on training dynamics & interpretability aligns closely with our themes. Check out one of her recent papers:
teapawt.org/nsaphra/status/2066507…
We don’t always know what problems are hard for LLMs. So devs evaluate on tasks HUMANS find hard or on broad benchmarks. What if we could instead anticipate which scenarios a model will fail on—all without evaluating specific input examples?
🧵NEW PAPER by @jenniferlumeng &al
1
131
2026 NeurIPS Workshop on Network Artifacts As Data retweeted
If you are working in anything related to neural network artifacts and model populations I highly recommend submitting to this NeurIPS workshop that takes place in Paris 🔥
📣 CFP: Neural Network Artifacts Are Data Too!
We welcome extended abstracts & full papers on model populations, weights, gradients, representations & training dynamics for our #NeurIPS2026 workshop.
Join us in Paris!
🗓 Sept 1 AoE
🔗 artifactsasdata.org/
📣 CFP: Neural Network Artifacts Are Data Too!
We welcome extended abstracts & full papers on model populations, weights, gradients, representations & training dynamics for our #NeurIPS2026 workshop.
Join us in Paris!
🗓 Sept 1 AoE
🔗 artifactsasdata.org/
Organizers and steering committee: @BoZhao__ @aspenkhopkins @_AmilDravid @kpal_koyena @ffabffrasca @gbouritsas @HaggaiMaron @damianborth @GalChechik @msbernst @StefanieJegelka Alex Bronstein
2
139
2026 NeurIPS Workshop on Network Artifacts As Data retweeted
Check out and submit to our workshop on treating neural nets themselves as a form of data! Deadline: Sept. 1 AOE
Neural Network Artifacts Are Data Too!
📣Join us for our 2026 @neuripsConf workshop on how to learn from populations of weights, gradients, representations, training trajectories & more.
🗓️ Deadline: Sept 1st AoE
🔗 artifactsasdata.org/
2026 NeurIPS Workshop on Network Artifacts As Data retweeted
So excited about our NNArtifacts #NeurIPS workshop! If you've ever wondered what a population of weights, gradients, or representations can tell you, submit 👇
Neural Network Artifacts Are Data Too!
📣Join us for our 2026 @neuripsConf workshop on how to learn from populations of weights, gradients, representations, training trajectories & more.
🗓️ Deadline: Sept 1st AoE
🔗 artifactsasdata.org/
2026 NeurIPS Workshop on Network Artifacts As Data retweeted
Are you thinking about weights, representations, traces (and other artifacts) as things we can learn from? Have we got the workshop for you!
🎉🎉🎉 Excited to co-organize this @NeurIPSConf workshop on Neural Network Artifacts as A New Data Modality. Ping us for more details ;)
Neural Network Artifacts Are Data Too!
📣Join us for our 2026 @neuripsConf workshop on how to learn from populations of weights, gradients, representations, training trajectories & more.
🗓️ Deadline: Sept 1st AoE
🔗 artifactsasdata.org/
Neural Network Artifacts Are Data Too!
📣Join us for our 2026 @neuripsConf workshop on how to learn from populations of weights, gradients, representations, training trajectories & more.
🗓️ Deadline: Sept 1st AoE
🔗 artifactsasdata.org/
Interested in being on the program committee? Sign up here: forms.gle/M7DrsCuqmc9gZiik7
1
3
149