Is #AI really just dumb statistics? "Olympiad-level physics problem-solving presents a significant challenge for both humans and artificial intelligence (AI), as it requires a sophisticated integration of precise calculation, abstract reasoning, and a fundamental grasp of physical principles," says the (abstract of the) paper https://arxiv.org/abs/2511.10515: "The Chinese Physics Olympiad (CPhO), renowned for its complexity and depth, serves as an ideal and rigorous testbed for these advanced capabilities. In this paper, we introduce LOCA-R (LOgical Chain Augmentation for Reasoning), an improved version of the LOCA framework adapted for complex reasoning, and apply it to the CPhO 2025 theory examination. LOCA-R achieves a near-perfect score of 313 out of 320 points, solidly surpassing the highest-scoring human competitor and significantly outperforming all baseline methods." Oops ...?
Series B, Episode 10 - Voice from the Past
JENNA: Zen, abort course for asteroid PK One One Eight and resume course for planet Del Ten. Confirm with arrival time.
ZEN: Arrival at planet Del Ten at zero four five plus one.
[Liberator turns in space]
https://blake.torpidity.net/m/210/164
"The Value of Public Domain Day"
a thoughtful piece on the economics and the loss by our overzealous locking up of our culture.
https://www.authorsalliance.org/2026/01/01/the-value-of-public-domain-day/
but please celebra…
Der Hamburger Verkehrsverbund (#HVV) passt ab Januar 2026 seine #Ticketpreise an.
Einzelne Fahrkarten steigen um bis zu 13 %. Besonders betroffen ist das #Nahbereich-Ticket, das künftig 3,50 E…
Un Momento 🕰️
一瞬 🕰️
📷 Zeiss Ikon Super Ikonta 533/16
🎞️ Lucky SHD 400
#filmphotography #Photography #blackandwhite
@… Sorry!
BTW, did you see that Beamer presentations won’t be accessible, and you need to use a new class, which is unfinished and only partly compatible: https://www.
@… Sorry!
BTW, did you see that Beamer presentations won’t be accessible, and you need to use a new class, which is unfinished and only partly compatible: https://www.
A US federal trial of Carl Rinsch, accused of swindling Netflix out of millions when making sci-fi series White Horse, begins with an ex-Netflix exec testifying (Antonio Ferme/Variety)
https://variety.com/2025/tv/news/carl-rinsch-netflix-fraud-trial-begins…
Meta-learning three-factor plasticity rules for structured credit assignment with sparse feedback
Dimitra Maoutsa
https://arxiv.org/abs/2512.09366 https://arxiv.org/pdf/2512.09366 https://arxiv.org/html/2512.09366
arXiv:2512.09366v1 Announce Type: new
Abstract: Biological neural networks learn complex behaviors from sparse, delayed feedback using local synaptic plasticity, yet the mechanisms enabling structured credit assignment remain elusive. In contrast, artificial recurrent networks solving similar tasks typically rely on biologically implausible global learning rules or hand-crafted local updates. The space of local plasticity rules capable of supporting learning from delayed reinforcement remains largely unexplored. Here, we present a meta-learning framework that discovers local learning rules for structured credit assignment in recurrent networks trained with sparse feedback. Our approach interleaves local neo-Hebbian-like updates during task execution with an outer loop that optimizes plasticity parameters via \textbf{tangent-propagation through learning}. The resulting three-factor learning rules enable long-timescale credit assignment using only local information and delayed rewards, offering new insights into biologically grounded mechanisms for learning in recurrent circuits.
toXiv_bot_toot
🪣 Drivers Beg for Relief Bill to Allow More Parking for Bathroom Breaks and Rest
#nyc