Causica
Causica is a deep learning library for end-to-end causal inference, including both causal discovery and inference.
π₯ Github: https://github.com/microsoft/causica
β© Paper: https://arxiv.org/abs/2303.12703v1
@ArtificialIntelligencedl
Causica is a deep learning library for end-to-end causal inference, including both causal discovery and inference.
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€1π₯1
From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels
π₯ Github: https://github.com/yzd-v/cls_KD
β© Paper: https://arxiv.org/abs/2303.13005v1
π¨ Dataset: https://paperswithcode.com/dataset/cifar-100
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€2π₯1
Human Guided Ground-truth Generation for Realistic Image Super-resolution
π₯ Github: https://github.com/chrisdud0257/hggt
β© Paper: https://arxiv.org/abs/2303.13069
π¨ Dataset: https://paperswithcode.com/dataset/div2k
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€2π₯1
π Planning Goals for Exploration
π₯ Github: https://github.com/penn-pal-lab/peg
β© Paper: https://arxiv.org/abs/2303.13002v1
π¨ Colab: https://colab.research.google.com/drive/1mbr8HHjWAhTQHUP2Y-QOgByuOOXBpusD?usp=sharing
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4π₯3β€1
StereoScene: BEV-Assisted Stereo Matching Empowers 3D Semantic Scene Completion
π₯ Github: https://github.com/Arlo0o/StereoScene
β© Paper: https://arxiv.org/abs/2303.13959v1
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4π₯2β€1
3D-Aware Multi-Class Image-to-Image Translation with NeRFs
π₯ Github: https://github.com/sen-mao/3di2i-translation
β© Paper: https://arxiv.org/abs/2303.15012v1
π¨ Dataset: https://paperswithcode.com/dataset/afhq
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π7β€1π₯°1π1
qEUBO: A Decision-Theoretic Acquisition Function for Preferential Bayesian Optimization
π₯ Github: https://github.com/facebookresearch/qeubo
β© Paper: https://arxiv.org/abs/2303.15746v1
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π8β€2π₯1
Novel View Synthesis of Humans using Differentiable Rendering
π₯ Github: https://github.com/guillaumerochette/humanviewsynthesis
β© Paper: https://arxiv.org/abs/2303.15880v1
π¨ Dataset: https://paperswithcode.com/dataset/afhq
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
β€3π₯2π1
Efficient Quality Diversity Optimization of 3D Buildings through 2D Pre-optimization
π₯ Github: https://github.com/lettucecfd/lettuce
β© Paper: https://arxiv.org/abs/2303.15896v1
π¨ Video: https://www.youtube.com/watch?v=7nVCuuZDCYA
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
β€3π2π₯1
Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation
π₯ Github: https://github.com/hikvision-research/3dvision
β© Paper: https://arxiv.org/abs/2303.17167v1
π¨ Dataset: https://paperswithcode.com/dataset/scenenn
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
β€3π1π₯1
ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing
π₯ Github: https://github.com/alibaba/easyrobust/tree/main/benchmarks/imagenet-e
β© Paper: https://arxiv.org/abs/2303.17096v1
π¨ Dataset: https://paperswithcode.com/dataset/objectnet
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€3π₯1
Zero-shot Referring Image Segmentation with Global-Local Context Features
π₯ Github: https://github.com/seonghoon-yu/zero-shot-ris
β© Paper: https://arxiv.org/pdf/2303.17811v1.pdf
π¨ Dataset: https://paperswithcode.com/dataset/coco
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π8π₯2β€1
CAMEL: Communicative Agents for "Mind" Exploration of Large Scale Language Model Society
π₯ Github: https://github.com/lightaime/camel
β© Paper: https://arxiv.org/pdf/2303.17760v1.pdf
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
β€5π₯2π₯°1
Procedure-Aware Pretraining for Instructional Video Understanding
π₯ Github: https://github.com/salesforce/paprika
β© Paper: https://arxiv.org/pdf/2303.18230v1.pdf
π¨ Dataset: https://paperswithcode.com/dataset/howto100m
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
β€3π₯°3π₯2
βΎ-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
π₯ Github: https://github.com/samb-t/infty-diff
β© Paper: https://arxiv.org/pdf/2303.18242v1.pdf
π¨ Dataset: https://paperswithcode.com/dataset/ffhq
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
β€4π2π₯2
Adaptive Sparse Pairwise Loss for Object Re-Identification
π₯ Github: https://github.com/astaxanthin/adasp
β© Paper: https://arxiv.org/pdf/2303.18247v1.pdf
π¨ Dataset: https://paperswithcode.com/dataset/market-1501
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4π₯3β€1π1
CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X
π₯ Github: https://github.com/THUDM/CodeGeeX
β© Paper: https://arxiv.org/pdf/2303.17568v1.pdf
π¨ Dataset: https://paperswithcode.com/dataset/humaneval-x
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π₯4π3β€1
Complementary Random Masking for RGB-Thermal Semantic Segmentation
π₯ Github: https://github.com/UkcheolShin/CRM_RGBTSeg
β© Paper: https://arxiv.org/pdf/2303.17386v1.pdf
@ArtificialIntelligencedl
@ArtificialIntelligencedl
Please open Telegram to view this post
VIEW IN TELEGRAM
π4β€1π₯1
OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction
π₯ Github: https://github.com/zhangyp15/occformer
β© Paper: https://arxiv.org/abs/2304.05316
π¨ Dataset: https://paperswithcode.com/dataset/semantickitti
@ArtificialIntelligencedl1
@ArtificialIntelligencedl1
Please open Telegram to view this post
VIEW IN TELEGRAM
π3β€2π₯2