Sensory Compression as a Unifying Principle for Action Chunking and Time Coding in the Brain

Posted by dbos UCSD / Salk

Kavli Affiliate: Marcelo Mattar | Authors: Sreejan Kumar, Matthieu B Le Cauchois, Alexander Mathis, Lea Duncker, Jonathon R. Howlett and Marcelo G. Mattar | Summary: The brain seamlessly transforms sensory information into precisely-timed movements, enabling us to type familiar words, play musical instruments, or perform complex motor routines with millisecond precision. This process often involves […]


Continue.. Sensory Compression as a Unifying Principle for Action Chunking and Time Coding in the Brain

Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation

Posted by klaurent Berkeley

Kavli Affiliate: Feng Wang | First 5 Authors: Tianhao Guo, Tianhao Guo, , , | Summary: Single image super-resolution traditionally assumes spatially-invariant degradation models, yet real-world imaging systems exhibit complex distance-dependent effects including atmospheric scattering, depth-of-field variations, and perspective distortions. This fundamental limitation necessitates spatially-adaptive reconstruction strategies that explicitly incorporate geometric scene understanding for optimal […]


Continue.. Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation

Misspecification-robust amortised simulation-based inference using variational methods

Posted by klaurent Cambridge

Kavli Affiliate: Kaisey Mandel | Summary:Recent advances in neural density estimation have enabled powerful simulation-based inference (SBI) methods that can flexibly approximate Bayesian inference for intractable stochastic models. Although these methods have demonstrated reliable posterior estimation when the simulator accurately represents the underlying data generative process (DGP), recent work has shown that they perform poorly […]


Continue.. Misspecification-robust amortised simulation-based inference using variational methods

Robust variational neural posterior estimation for simulation-based inference

Posted by klaurent Cambridge

Kavli Affiliate: Kaisey Mandel| First 5 Authors: Matthew O’Callaghan, Matthew O’Callaghan, , , | Summary:Recent advances in neural density estimation have enabled powerful simulation-based inference (SBI) methods that can flexibly approximate Bayesian inference for intractable stochastic models. Although these methods have demonstrated reliable posterior estimation when the simulator accurately represents the underlying data generative process […]


Continue.. Robust variational neural posterior estimation for simulation-based inference

LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding

Posted by klaurent Peking

Kavli Affiliate: Ke Wang | First 5 Authors: Yuxuan Hu, Yuxuan Hu, , , | Summary: Recent progress in Large Language Models (LLMs) has opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). However, existing LLM-driven NAS approaches rely heavily on prompt engineering and domain-specific tuning, limiting their practicality and scalability […]


Continue.. LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding

Interaction-driven quantum criticality in two-dimensional quadratic band crossing semimetals with time-reversal symmetry breaking

Posted by klaurent Peking

Kavli Affiliate: Jing Wang | First 5 Authors: Yi-Kun Fang, Yi-Kun Fang, , , | Summary: We present a systematic investigation of all sixteen marginally relevant fermion-fermion interactions in two-dimensional time-reversal symmetry-breaking kagom’e semimetals hosting a quadratic band crossing point. Employing a momentum-shell renormalization group approach that treats every interaction on equal footing, we derive […]


Continue.. Interaction-driven quantum criticality in two-dimensional quadratic band crossing semimetals with time-reversal symmetry breaking

Hybrid-illumination multiplexed Fourier ptychographic microscopy with robust aberration correction

Posted by klaurent Caltech

Kavli Affiliate: Changhuei Yang | Summary:Fourier ptychographic microscopy (FPM) is a powerful computational imaging modality that achieves high space-bandwidth product imaging for biomedical samples. However, its adoption is limited by slow data acquisition due to the need for sequential measurements. Multiplexed FPM strategies have been proposed to accelerate imaging by activating multiple LEDs simultaneously, but […]


Continue.. Hybrid-illumination multiplexed Fourier ptychographic microscopy with robust aberration correction