📌 Marque-pages Pinboard

← Retour à tous les marque-pages
Réinitialiser
Recherche en cours...
140 résultats (1-140 marque-pages affichés)
www.geoffreylitt.com
www.nature.com
Early examples of computers were almost exclusively based on mechanical devices. Although electronic computers became dominant in the past 60 years, recent advancements in three-dimensional micro-additive manufacturing technology provide new fabrication techniques for complex microstructures which have rekindled research interest in mechanical computations. Here we propose a new digital mechanical computation approach based on additively-manufacturable micro-mechanical logic gates. The proposed mechanical logic gates (i.e., NOT, AND, OR, NAND, and NOR gates) utilize multi-stable micro-flexures that buckle to perform Boolean computations based purely on mechanical forces and displacements with no electronic components. A key benefit of the proposed approach is that such systems can be additively fabricated as embedded parts of microarchitected metamaterials that are capable of interacting mechanically with their surrounding environment while processing and storing digital data internally without requiring electric power. Mechanical computing based on the logic devices that utilize mechanical energy can be an alternative to conventional electronic computing. Here, Song et al. show a micromechanical logic gate, fabricated using multi-stable buckling flexures, which is capable of realizing all digital logic operations.
github.com
Stable Virtual Camera: Generative View Synthesis with Diffusion Models - Stability-AI/stable-virtual-camera
medium.com
People + AI Research: thinking together about people and AI.
www.comparia.beta.gouv.fr
github.com
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models. - Tencent/Hunyuan3D-2
github.com
Instant neural graphics primitives: lightning fast NeRF and more - NVlabs/instant-ngp
pubmed.ncbi.nlm.nih.gov
PubMedÂź comprises more than 37 million citations for biomedical literature from MEDLINE, life science journals, and online books. Citations may include links to full text content from PubMed Central and publisher web sites.
junxuan-li.github.io
URAvatar: Universal Relightable Gaussian Codec Avatars
leolty.github.io
Tianyang Liu's personal website.
arxiv.org
Abstract page for arXiv paper 2212.10496: Precise Zero-Shot Dense Retrieval without Relevance Labels
oasis-model.github.io
Generating Worlds in Realtime
darioamodei.com
Dario Amodei is the CEO of Anthropic, a public benefit corporation dedicated to building AI systems that are steerable, interpretable and safe.
en.wikipedia.org
nvlabs.github.io
www.datacomp.ai
In search of the next generation of multimodal datasets
stability-ai.github.io
www.yitay.net
t5tts.github.io
nlp.stanford.edu
actu.epfl.ch
github.com
A library for efficient similarity search and clustering of dense vectors. - Home · facebookresearch/faiss Wiki
github.com
A library for efficient similarity search and clustering of dense vectors. - facebookresearch/faiss
link.springer.com
Moral intuitions are a central motivator in human behavior. Recent work highlights the importance of moral intuitions for understanding a wide range of iss
wordasimage.github.io
www.epfl.ch
github.com
YOLOv10: Real-Time End-to-End Object Detection. Contribute to THU-MIG/yolov10 development by creating an account on GitHub.
www.fredericgardi.com
Frédéric Gardi
mhamilton.net
A Model-Agnostic Framework for Features at Any Resolution
journals.sagepub.com
Big Data & Society publishes interdisciplinary work principally in the social sciences, humanities and computing and their intersections with the arts and n...
chakazul.github.io
sites.google.com
intrinsic-lora.github.io
Generative Models capture intrinsic image representations and we show how to extract them using a unified approach that works for any generative model including autoregressive, gan and difussion.
gaussianobject.github.io
GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting
navigu.net
NAVIGU lets you dive into the ocean of images. Drag the image sphere or double-click on an image you like to browse large collections.
rd.nytimes.com
Research & Development at The New York Times explores how emerging technologies can be applied in service of journalism.
willcrichton.net
A proposal for the next generation of portable documents.
github.com
Implementation of Nougat Neural Optical Understanding for Academic Documents - facebookresearch/nougat: Implementation of Nougat Neural Optical Understanding for Academic Documents
github.com
đŸ€— PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. - huggingface/peft: đŸ€— PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
www.uva.nl
B. BodĂł. Faculty of Law. Information Law. Nieuwe Achtergracht 166. Room number: 5.15.
maxime-flin.github.io
zju3dv.github.io
q-transformer.github.io
Q-Transformer
karpathy.github.io
Musings of a Computer Scientist.
stardrive.org
Stardrive - Internet Science Education Project
socradar.io
The rapidly evolving threats in the field of cybersecurity are being met with sophisticated methods such as "FUD" Crypter...
github.com
A library for efficient similarity search and clustering of dense vectors. - Home · facebookresearch/faiss Wiki
github.com
Generative Agents: Interactive Simulacra of Human Behavior - joonspk-research/generative_agents: Generative Agents: Interactive Simulacra of Human Behavior
www.college-de-france.fr
pix2pixzero.github.io
github.com
Contrastive Language-Image Pretraining. Contribute to openai/CLIP development by creating an account on GitHub.
www.anthropic.com
Anthropic AI research company site
w3.insp.upmc.fr
valle-demo.github.io
deepimagination.cc
www.lajauneetlarouge.com
Des jumelles russes à Polytechnique, ça ne passe pas inaperçu. Dinara et Margarita Veshchezerova font partie des élÚves de la promo 2015.
exposing.ai
Exposing.ai
www.vldb.org
SQLite: Past, Present, and Future
felixkreuk.github.io
bigscience.huggingface.co
www.fatimafellowship.com
huggingface.co
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
film-net.github.io
FILM creates slow motion footage from two near duplicate photos.
laion.ai
rated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to stron
stability.ai
We are delighted to announce the public release of Stable Diffusion and the launch of DreamStudio Lite.
paperswithcode.com
github.com
Collection of quotes on notation design & how it affects thought. - k-qy/notation: Collection of quotes on notation design & how it affects thought.
nlpparis.wordpress.com
fauconnier.github.io
Jean-Philippe Fauconnier's Homepage
imagen.research.google
www.amazon.science
Reformulating the mapping problem to take advantage of sequence-to-sequence Transformers improves performance by an average of 15%.
www.eleuther.ai
laion.ai
www.cs.cmu.edu
www.cs.cmu.edu
www.cs.cmu.edu
www.cs.cmu.edu
www.frozenark.org
imgur.com
openai.com
synth.app
replicated.cc
arxiv.org
Dimension reduction (DR) techniques such as t-SNE, UMAP, and TriMAP have demonstrated impressive visualization performance on many real world datasets. One tension that has always faced these methods is the trade-off between preservation of global structure and preservation of local structure: these methods can either handle one or the other, but not both. In this work, our main goal is to understand what aspects of DR methods are important for preserving both local and global structure: it is difficult to design a better method without a true understanding of the choices we make in our algorithms and their empirical impact on the lower-dimensional embeddings they produce. Towards the goal of local structure preservation, we provide several useful design principles for DR loss functions based on our new understanding of the mechanisms behind successful DR methods. Towards the goal of global structure preservation, our analysis illuminates that the choice of which components to preserve is important. We leverage these insights to design a new algorithm for DR, called Pairwise Controlled Manifold Approximation Projection (PaCMAP), which preserves both local and global structure. Our work provides several unexpected insights into what design choices both to make and avoid when constructing DR algorithms.
vdfresearch.org
cbr.stanford.edu
fr.wikipedia.org
research.google
twitter.com
karpathy.github.io
fr.wikipedia.org
labos1point5.org
math.mit.edu
www.cs.toronto.edu
idl.cs.washington.edu
people.sutd.edu.sg
hackingresear.ch
barnabemonnot.com
louismartin.eu
academictorrents.com
www.abg.asso.fr
www.gdr-isis.fr
www.litmaps.co
imagine.enpc.fr
paperswithcode.com
www.youtube.com
artagnon.com
www.cs.purdue.edu
fchollet.com
kesen.realtimerendering.com
geometry.cs.ucl.ac.uk
dellaert.github.io
www.biorxiv.org
homes.cs.washington.edu
www.robots.ox.ac.uk