Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation

Kavli Affiliate: Wei Gao | First 5 Authors: Kai Huang, Hanyun Yin, Heng Huang, Wei Gao, | Summary: Fine-tuning is the most effective way of adapting pre-trained large language models (LLMs) to downstream applications. With the fast growth of LLM-enabled AI applications and democratization of open-souced LLMs, fine-tuning has become possible for non-expert individuals, but […]


Continue.. Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation

Deep Learning with Photonic Neural Cellular Automata

Kavli Affiliate: Alireza Marandi | First 5 Authors: Gordon H. Y. Li, Christian R. Leefmans, James Williams, Robert M. Gray, Midya Parto | Summary: Rapid advancements in deep learning over the past decade have fueled an insatiable demand for efficient and scalable hardware. Photonics offers a promising solution by leveraging the unique properties of light. […]


Continue.. Deep Learning with Photonic Neural Cellular Automata

Exact coherent structures in two-dimensional turbulence identified with convolutional autoencoders

Kavli Affiliate: Michael P. Brenner | First 5 Authors: Jacob Page, Joe Holey, Michael P. Brenner, Rich R. Kerswell, | Summary: Convolutional autoencoders are used to deconstruct the changing dynamics of two-dimensional Kolmogorov flow as $Re$ is increased from weakly chaotic flow at $Re=40$ to a chaotic state dominated by a domain-filling vortex pair at […]


Continue.. Exact coherent structures in two-dimensional turbulence identified with convolutional autoencoders

mixed attention auto encoder for multi-class industrial anomaly detection

Kavli Affiliate: Feng Wang | First 5 Authors: Jiangqi Liu, Feng Wang, , , | Summary: Most existing methods for unsupervised industrial anomaly detection train a separate model for each object category. This kind of approach can easily capture the category-specific feature distributions, but results in high storage cost and low training efficiency. In this […]


Continue.. mixed attention auto encoder for multi-class industrial anomaly detection

Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes

Kavli Affiliate: Mark Churchland, Liam Paninski | Authors: Yizi Zhang, Tianxiao He, Julien Boussard, Charlie Windolf, Olivier Winter, Eric Trautmann, Noam Roth, Hailey Barrell, Mark M Churchland, Nicholas A Steinmetz, The International Brain Laboratory, Erdem Varol, Cole Hurwitz and Liam Paninski | Summary: Neural decoding and its applications to brain computer interfaces (BCI) are essential […]


Continue.. Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes

Placebo treatment affects brain systems related to affective and cognitive processes, but not nociceptive pain

Kavli Affiliate: Martin Lindquist | Authors: Rotem Botvinik-Nezer, Bogdan Petre, Marta Ceko, Martin A. Lindquist, Naomi P. Friedman and Tor D. Wager | Summary: Placebo analgesia is a replicable and well-studied phenomenon, yet it remains unclear to what degree it includes modulation of nociceptive processes. Some studies find effects consistent with nociceptive effects, but meta-analyses […]


Continue.. Placebo treatment affects brain systems related to affective and cognitive processes, but not nociceptive pain

Exploring Neural Dynamics in Self-Voice Processing and Perception: Implications for Hallucination Proneness

Kavli Affiliate: David Linden | Authors: Suvarnalata Xanthate Duggirala, Hanna Honcamp, Michael Schwartze, Therese Amelsvoort, Ana Pinheiro, David Linden and Sonja A Kotz | Summary: Altered sensory feedback processing and attention control are assumed to contribute to auditory verbal hallucinations, which are experienced by the general population and patients with psychosis, implying a continuum of […]


Continue.. Exploring Neural Dynamics in Self-Voice Processing and Perception: Implications for Hallucination Proneness

Single cell analysis of dup15q syndrome reveals developmental and postnatal molecular changes in autism

Kavli Affiliate: Arnold R. Kriegstein | Authors: Yonatan Perez, Dmitry Velmeshev, Li Wang, Matthew White, Clara Siebert, Jennifer Baltazar, Natalia Garcia Dutton, Shaohui Wang, Maximilian Haeussler, Stormy Chamberlain and Arnold Kriegstein | Summary: Duplication 15q (dup15q) syndrome is the most common genetic cause of autism spectrum disorder (ASD). Due to a higher genetic and phenotypic […]


Continue.. Single cell analysis of dup15q syndrome reveals developmental and postnatal molecular changes in autism

Bering: joint cell segmentation and annotation for spatial transcriptomics with transferred graph embeddings

Kavli Affiliate: Jin Kang | Authors: Kang Jin, Zuobai Zhang, Ke Zhang, Francesca Viggiani, Claire Callahan, Jian Tang, Bruce J. Aronow and Jian Shu | Summary: Single-cell spatial transcriptomics such as in-situ hybridization or sequencing technologies can provide subcellular resolution that enables the identification of individual cell identities, locations, and a deep understanding of subcellular […]


Continue.. Bering: joint cell segmentation and annotation for spatial transcriptomics with transferred graph embeddings

ICM-SHOX. Paper I: Methodology overview and discovery of a gas–dark matter velocity decoupling in the MACS J0018.5+1626 merger

Kavli Affiliate: Sunil Golwala | First 5 Authors: Emily M. Silich, Elena Bellomi, Jack Sayers, John ZuHone, Urmila Chadayammuri | Summary: Galaxy cluster mergers are rich sources of information to test cluster astrophysics and cosmology. However, cluster mergers produce complex projected signals that are difficult to interpret physically from individual observational probes. Multi-probe constraints on […]


Continue.. ICM-SHOX. Paper I: Methodology overview and discovery of a gas–dark matter velocity decoupling in the MACS J0018.5+1626 merger