Can you k-shot it with ground truth examples of photos and their depth maps? Like a 2-by-n grid of examples with the final image missing.
MACHINE LEARNING
-
Prototype Viability: When 90% Done Isn’t Really Done
By
–
Oh I’m sure. One horrible version of this is when the muggle thinks his vibe coded prototype is 90% there just because it kinda works.
-
Self-Orthogonalizing Attractor Neural Networks from Free Energy
By
–
Self-orthogonalizing attractor neural networks emerging from the free energy principle Tamas Spisak, Karl Friston : https://
arxiv.org/abs/2505.22749 #ArtificialIntelligence #DeepLearning #MachineLearning -
arxiv research paper obligation response link shared
By
–
you know im obligated to respond with this: http://
arxiv.org/abs/1908.04626 -
Visualizing Transformer Internals: Attribution Graphs and Beyond
By
–
you're talking about the attribution graphs lib i assume? anyway — there is definitely room for more people to work on visualizing the internals of transformers
-
Exploring Alternative Visualizations for Transformer Internal Mechanisms
By
–
surely there are other ways to visualize the internal mechanisms of transformers
-
Why Attention Visualizations Disappeared From Modern AI Models
By
–
when people were working on BERT i always found these types of visualizations compelling. seeing the attention mechanism in action is so cool why are they not popular anymore? do our models have too many layers for us to understand now? or are attention maps just not useful?
-
Open Models Data Gap: Why Algorithms Aren’t Enough
By
–
every new model is a combination of two things, training algorithms and data open-source algorithms are up-to-date. the things that work are usually fairly simple but the data is complex, massive, gatekept, ever-changing. here open models are way behind, and probably hopeless
-
Tesla Optimus Robot Dances and Learns Autonomously From YouTube
By
–
Optimus, le robot humanoïde de Tesla, danse, apprend seul depuis YouTube… J’ai décortiqué cette démo historique dans une vidéo à chaud. C’est le début d’un nouveau monde. Lien de ma dernière vidéo : https://
youtu.be/o1WcIdQLH80 -
State-of-the-art LLMs performance on uncontaminated math competitions
By
–
How do state-of-the-art LLMs perform on uncontaminated math competitions? Researchers at ETH Zurich set out to answer this by building MathArena, a benchmark designed to evaluate SOTA models on clean, competition-style math problems. They then tested leading models on this