| 🌐 Website | http://www.matrig.net |
| 💻 Github | https://github.com/matrig |
| 🎓 Google Scholar | https://scholar.google.com/citations?user=TmHt7CwAAAAJ |
| 🟢 ORCID | https://orcid.org/0000-0001-6466-2810 |
If you're at #NeurIPS2025 tomorrow (Dec 3, 11:00–14:00 PST), Brown Ebouky will present our new work:
“Eliciting Reasoning in Language Models with Cognitive Tools” where we combine cognitive architectures with #agentic workflows to enhance #LLM reasoning 🧠
Check it out here: https://neurips.cc/virtual/2025/loc/san-diego/poster/119804
📣 Come join us at IBM Research Zurich for a fully funded PhD position on Reliable Multimodal Large Language Models (LLMs), combining language, vision, and advanced reasoning!
You'll be located in Zurich🇨🇭 and co-supervised by Katja Hose at TU Vienna 🇦🇹
as part of the cool new MSCA ARMADA Doctoral Network https://armada-dn.eu
Apply here: https://www.zurich.ibm.com/careers/2025_008.html
China exports jump 8% in April despite tariffs
https://www.ft.com/content/fd98d384-fa82-489e-8f50-0ff84214733c
More important & informative than ever: repository of tangible benefits stemming from publicly-funded research
If you ask its (few remaining) fans about Tesla having the highest rate of fatal accidents, their main excuse is that Tesla drivers misuse FSD and misunderstand safety features.
So, they'd rather blame themselves than Tesla 🤷♂️
Extreme polarization is now also entering the transformer-based architectures discourse 😅
"Transformers without Normalization" vs Normalizations everywhere, which team are you on?
This #DeepRL paper from University of Alberta seems quite cool:
"Deep reinforcement learning without experience replay, target networks, or batch updates"
As the title says, they succeeded in training deep RL networks in streaming setting getting rid of replay buffers.
The main tricks for that to work seem to be signal normalization and bounding the step-size 🤯
💻Code: http://github.com/mohmdelsayed/streaming-drl
📄Paper: https://openreview.net/pdf?id=yqQJGTDGXN
No worries, just keep using paper straws
https://edition.cnn.com/2024/11/12/energy/shell-climate-case-netherlands/index.html
Shell is not obliged to dramatically reduce its planet-heating pollution by 2030, a Dutch appeals court ruled Tuesday, overturning a previous verdict that imposed steep carbon emissions reductions on the British oil and gas giant.
