Congrats Arinbjorn!
               
            
            
                22.01.2025 20:59 β π 3    π 0    π¬ 1    π 0                      
            
         
            
        
            
            
            
            
            
    
    
            
                        
                Genesis
                
            
        
    
    
            Pretty impressive new simulation framework - Genesis genesis-embodied-ai.github.io "takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 " genesis-world.readthedocs.io/en/latest/us...
               
            
            
                19.12.2024 16:29 β π 2    π 0    π¬ 0    π 0                      
            
         
            
        
            
            
                            
            
            
            
    
    
    
    
            Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation.
Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map.
With @ericdexheimer.bsky.social* @ajdavison.bsky.social (*Equal Contribution)
               
            
            
                16.12.2024 15:43 β π 99    π 16    π¬ 5    π 6                      
            
         
            
        
            
            
            
            
                                                
                                                
    
    
    
    
            Interesting and inspiring keynote talk by Danica Kragic
Learning for Interaction and Interaction for Learning
Missed? Watch it here: https://buff.ly/49SzilH
               
            
            
                13.12.2024 17:37 β π 15    π 3    π¬ 0    π 0                      
            
         
            
        
            
            
            
            
                                                
                                                
    
    
    
    
            Have you ever wondered how to train an autoregressive generative transformer on text and raw pixels, without a pretrained visual tokenizer (e.g. VQ-VAE)?
We have been pondering this during summer and developed a new model: JetFormer ππ€
arxiv.org/abs/2411.19722
A thread π
1/
               
            
            
                02.12.2024 16:41 β π 155    π 36    π¬ 4    π 7                      
            
         
            
        
            
            
            
            
                                                
                                                
    
    
    
    
            Tired of saturated benchmarks? Want scope for a significant leap in capabilities?
π₯ Introducing BALROG: a Benchmark for Agentic LLM and VLM Reasoning On Games!
BALROG is a challenging benchmark for LLM agentic capabilities, designed to stay relevant for years to come.
1/π§΅
               
            
            
                21.11.2024 16:24 β π 96    π 20    π¬ 4    π 7                      
            
         
            
        
            
            
            
            
            
    
    
            
                            
                        
                Neuronal sequences in population bursts encode information in human cortex - Nature
                The temporal order of neuronal firing within bursts of population spiking in the human anterior temporal lobe is dependent on the category as well as the identity of the individual stimulus, and this ...
            
        
    
    
            This study shows that spike sequences carry information beyond what rates and latency to first spike do:
www.nature.com/articles/s41...
My reactions:
1) Cool to see this in humans.
2) Are people still surprised that spike times carry information beyond rates/first-spike latency?!?!?!
π§ π π§ͺ
               
            
            
                28.11.2024 16:55 β π 175    π 33    π¬ 6    π 7                      
            
         
            
        
            
            
            
            
            
    
    
    
    
            πββοΈ
               
            
            
                25.11.2024 19:47 β π 1    π 0    π¬ 0    π 0                      
            
         
            
        
            
            
            
            
            
    
    
    
    
            Would love to be added
               
            
            
                25.11.2024 17:34 β π 0    π 0    π¬ 0    π 0                      
            
         
    
         
        
            
        
                            
                    
                    
                                            We study the mathematical principles of learning, perception & action in brains & machines. Funded by the Gatsby Charitable Foundation. Based at UCL. www.ucl.ac.uk/gatsby
                                     
                            
                    
                    
                                            Research Institute of the Free State of Bavaria for software-intensive systems
                                     
                            
                    
                    
                                            Official account of the Dynamic Walking 2025 conference. 
Aachen, Germany. July 14 - 17. 
Submission deadline: extended to May 7th
http://dynamicwalking2025.org/
                                     
                            
                    
                    
                                            Manchester Centre for AI FUNdamentals | UoM | Alumn UCL, DeepMind, U Alberta, PUCP | Deep Thinker | Posts/reposts might be non-deep | Carpe espresso β
                                     
                            
                    
                    
                                            Neuroscience & AI @ Imperial & Cambridge |
www.danakarca.com
                                     
                            
                    
                    
                                            Computational and systems neuroscience, data analysis, machine learning, neurophysics
                                     
                            
                    
                    
                                            Physics Professor, NMBU & University of Oslo. Host of two podcasts: Theoretical Neuroscience Podcast (http://theoreticalneuroscience.no) & Vett og vitenskap (http://vettogvitenskap.no).  Likes brain physics and Sunderland football club.
                                     
                            
                    
                    
                                            CoSMO, Neuromatch, Neuro4Pros co-founder.
Comp neuro at Queen's U π¨π¦ studying sensorimotor control.
Vice-Director (Queen's) of Connected Minds.
Mentor, dad, brewing, gardener, artist, antifa. 
Renaissance man. Believer in humanity!
http://compneurosci.com/
                                     
                            
                    
                    
                                            Associate Professor of Applied and Computational Mathematics and Statistics and Biological Sciences at U Notre Dame. Theoretically a Neuroscientist.
                                     
                            
                            
                    
                    
                                            In search of computational principles of natural adaptive behavior. Postdoc with Peter Dayan @mpicybernetics.bsky.social
Website: http://roxanazeraati.org/
                                     
                            
                    
                    
                                            ποΈπ§ π₯οΈπ§ͺπ€ Associate Professor in @ucsb-cs.bsky.social and Psychological & Brain Sciences at @ucsantabarbara.bsky.social. PI of @bionicvisionlab.org.
#BionicVision #Blindness #LowVision #VisionScience #CompNeuro #NeuroTech #NeuroAI
                                     
                            
                    
                    
                                            Computational neuroscience postdoc in the Milstein Lab at Rutgers University, studying synaptic plasticity, bio-plausible deep learning / neuroAI, neuromorphic computing. Previously @ Francis Crick Institute & UCL
                                     
                            
                    
                    
                                            Neuroscientist at Scripps Research. Postdoc in Ann Kennedy's lab (@antihebbiann). Dynamical systems, mathematical modeling, neural computation. Open-source promoter and scientific software developer (github.com/pyrates-neuroscience)
                                     
                            
                    
                    
                                            PhD candidate in computational neuroscience, university of Geneva. 
Studying the dynamical properties of neural activity during speech processing.π»π§ 
webpage: nosratullah.github.io
                                     
                            
                    
                    
                                            Researching neuromorphic computing. Curious about abstractions. Cares about FOSS.
Author of Neuromorphic Intermediate Representation in NatComm: https://www.nature.com/articles/s41467-024-52259-9
                                     
                            
                    
                    
                                            Computational neuroscientist.
Senior Lecturer at Ulster University in the Great City of Derry, Northern Ireland.
"not articulate enough"
https://odonnellgroup.github.io
                                     
                            
                    
                    
                                            π³οΈβππ§ π¬π΄ββοΈ Neuroscientist. Associate Director of Data and Outreach at Allen Institute for Neural Dynamics. Focused on how we do Science in the Open. She/her. 
                                     
                            
                    
                    
                                            Computational neuroscientist studying learning and memory in health and disease. Dad, yogi, Assistant Professor at Rutgers University.
                                     
                            
                    
                    
                                            Computational neuroscientist chasing the secret of the brain. Junior professor at JΓΌlich Research Center & University of Cologne.