Hot Tweets

@ylecun
MMS: Massively Multilingual Speech. - Can do speech2text and text speech in 1100 languages. - Can recognize 4000 sp… https://t.co/SWSbEJrQUh
2023-05-22 Super Hot
@ylecun
LIMA : LLaMA 65B + 1000 supervised samples = {GPT4, Bard} level performance. From @MetaAI https://t.co/FIuIo6agXa
2023-05-22 Super Hot
@ylecun
Many people are more capable than their boss. AI systems may become more capable than you, but you'll still be thei… https://t.co/X9ATYltwlw
2023-05-21 Super Hot
@ylecun
Since we are talking about insults, This is one of the two rarest, most original, witty, and intelligent ones invol… https://t.co/MEHHx7W9Mu
2023-05-20 Super Hot
@ylecun
AI won't take your job. But it will transform it and create new ones. This NYT article has quotes from economists w… https://t.co/ozqyJ1Gpss
2023-05-21 Super Hot
@ylecun
Wondering if people who are afraid of open-source AI infrastructure have, in fact, a deep distrust of human intelli… https://t.co/DLXtDOJv7E
2023-05-21 Super Hot
@KirkDBorne
Free 449-page PDF eBook >> Understanding #MachineLearning — From Theory to #Algorithms: https://t.co/6NiPp59qXA ———… https://t.co/Aaw73u7SCP
2023-05-21 Super Hot
@ylecun
Learn to write like an LLM! Question: what do you think of person A's declaration that X is caused by Y ? LLM Ans… https://t.co/R6TGRZ35q9
2023-05-21 Super Hot
@ylecun
Wrinkled so much, I am not. But when 900 years old I reach, look as good I will not. https://t.co/ZJsJy1DDk3
2023-05-21 Super Hot
@hillbig
言語モデル（LM）が意味を理解しているのかを調べるため、プログラムに対するLMを構築し、LMの内部状態からプログラムの意味を推定する実験をした結果、単語予測精度と意味推定精度の改善ペースがほぼ一致し、またLMが将来に何を生成するか… https://t.co/QozfTwkgoz
2023-05-21 Hot
@arankomatsuzaki
LIMA: Less Is More for Alignment Presents LIMA, a 65B LLaMa language model fine-tuned on only 1k curated samples w… https://t.co/Afz2vKS7ki
2023-05-22 Hot
@ylecun
3 obstacles for a piece of content to have an impact on people. 1. Production 2. Dissemination 3. Attention Comput… https://t.co/2KOsOF6sJV
2023-05-20 Hot
@ylecun
@elonmuskewl 2 minutes ago 😂
2023-05-20 Hot
@arankomatsuzaki
Any-to-Any Generation via Composable Diffusion Present CoDi, a novel generative model capable of generating any co… https://t.co/xtNBlihK6N
2023-05-22 Hot
@omarsar0
A General Taxonomy of LLM Prompts Proposes a general taxonomy to design prompts that can be used to benchmark LLMs… https://t.co/i9H8IbpQAU
2023-05-22 Hot
@ylecun
No need to find the ones that work in French. I've heard them all since elementary school.
2023-05-21 Hot
@arankomatsuzaki
How Does Generative Retrieval Scale to Millions of Passages? Finds that the use of synthetic queries as a document… https://t.co/1mrhXTqwo5
2023-05-22 Hot
@arankomatsuzaki
Multimodal Web Navigation with Instruction-Finetuned Foundation Models Their 3B model outperforms the SoTA, PaLM-5… https://t.co/cUiTFlNRh2
2023-05-22 Hot
@ylecun
AI has actually played a hugely *positive* role in 2 and 3: Content moderation on social networks makes massive use… https://t.co/oT2FvN2HUx
2023-05-20 Hot
@KirkDBorne
How to build a portfolio to get a #DataScientist job: https://t.co/bIYqY70UKH ———— #BigData #DataScience #AI… https://t.co/eIjRGs83cR
2023-05-21
@ylecun
Correct link to paper: https://t.co/yFrcnSiqft
2023-05-22
@KirkDBorne
👉Download 471-page PDF >> The Principles of Deep Learning Theory — Theoretical & Mathematical Foundations:… https://t.co/YvBZwPwSnJ
2023-05-21
@abacusai
100% FREE book about Multimodal Deep Learning. Multimodal learning is about learning from data of multiple modalit… https://t.co/HcfHftDvr1
2023-05-21
@DataScienceDojo
💡 Complete guide on deep learning architectures: https://t.co/to9SWdsx6j #DeepLearning #Architectures #DataScience https://t.co/mr9uLm7kPl
2023-05-21
@KirkDBorne
I just posted 40+ resources exclusively for my Twitter Subscribers, including a variety of FREE downloads that cove… https://t.co/gWogJWsp5r
2023-05-20
@ylecun
@nareshshah139 @MetaAI They are a component of the future. They are the short-term future. They are not the medium-… https://t.co/aU6bK2GM2g
2023-05-22
@ylecun
@ESYudkowsky I can give you 100 reasons why turbojets would fail. Yet modern turbojets are insanely reliable. The p… https://t.co/qZgSxvdyze
2023-05-21
@ylecun
@Miles_Brundage Sorry, but the absence of such robots has nothing to do with the speed of edge GPUs (or lack thereo… https://t.co/b1ivLXD5hF
2023-05-20
@johnjnay
Chain-of-Symbol Prompting Elicits Planning in LLMs -Represent complex environments w/ condensed symbolic spatial r… https://t.co/8Cv9sN76VU
2023-05-21
@KirkDBorne
Probabilistic #MachineLearning — An INTRODUCTION (2nd Ed. 2022, free PDF): https://t.co/3T7n57r99e by @sirbayes ➕ P… https://t.co/kT5qScaP8z
2023-05-21
@ylecun
@Eriler Eric Sadin is an angry philosopher with a huge superiority complex embattled against everything and anythin… https://t.co/tT5E0cRZZY
2023-05-20
@ylecun
@clemmihai I heard those in first grade.
2023-05-21
@ylecun
@jiwa986 @erikbryn @GoldmanSachs @geoffreyhinton Both Geoff Hinton and Yoshua Bengio are good friends for whom I ha… https://t.co/JpM37rUzrf
2023-05-21
@KirkDBorne
100+ Free #DataScience eBooks (downloadable PDF) for Beginners and for Experts — via @TheInsaneApp —————… https://t.co/oTO3QZZq6N
2023-05-21
@ylecun
@0karma108 I like that one!
2023-05-21
@icoxfog417
大規模LLMのFine Tuning はデータ量よりデータの質が鍵とする論文。65BのLLaMaモデルを1000件の厳選したサンプルで学習することでGPT-4と比較して人間が選好/同等とする割合が43%、またGPT-3ベースのda… https://t.co/NeUTljYadx
2023-05-22
@ylecun
A thread on MMS by author @MichaelAuli https://t.co/P6HGbLSqfh
2023-05-22
@ylecun
@youcantcallmeal I've been cited as "Cun, Yann L." Which is one reason I changed the spelling from "Le Cun" to "LeCun"
2023-05-21
@ylecun
@_jameshatfield_ My question was specific (with particular instantiations of A,X,Y, and Z). I just replaced them by… https://t.co/K8bltAUw5F
2023-05-21
@ylecun
@ESYudkowsky Objectives that make AI systems subservient to human bosses. Those objectives would be optimized at ru… https://t.co/uxKhThDEtz
2023-05-21
@ylecun
@technomancers @Miles_Brundage I'm not saying we won't. I'm saying we don't. The exceptions today are managed fle… https://t.co/keHCOxuCX8
2023-05-20
@ylecun
@davidsancar Technology increases productivity, i.e. the amount of wealth produced per hour worked. That is intrins… https://t.co/u0iiwSmmjs
2023-05-21
@ylecun
@JeromeColombain I don't know about your writing habits, but I would not recommend it.
2023-05-21
@ylecun
The insult was: "Turing Award laureate, I doubt this guy can even pass the test" 😂😂😂 But the author seems spooked by my retweet.
2023-05-20
@Ronald_vanLoon
Meta #AI researchers develop ways to read speech from people’s brains by @kytsune @SiliconANGLE Go to:… https://t.co/uEf3DRGifL
2023-05-20
@ylecun
@s_batzoglou Wrinkled so much, I am not. But 900 years old, I am not either.
2023-05-21
@AntonioParis
Did water flow on #Mars? Read our latest research "The Transport of Extrusive Volcanic Deposits on Jezero Crater".… https://t.co/eW20xrH3DB
2023-05-21
@johnjnay
LLM Pre-training vs. Instruction-Tuning -LLaMa 65B pre-trained -Only simple fine-tuning, w/ only 1k (carefully cho… https://t.co/zgoEF63pY9
2023-05-22
@hillbig
VisionLLMは画像中心のタスクに対し、言語で指示を与え、言語で結果を得る（検出やマスクは位置列で扱う）。指示を元に画像特徴から交差注意機構で情報抽出し、特徴トークンを得たあと、LLMを使ったタスク条件付復号化器で出力を求める… https://t.co/h2qrSe4uDa
2023-05-22
@matei_zaharia
Interesting phenomenon that is a real risk when everyone is using one central provider. We observed similar changes… https://t.co/dRo4Ybt81M
2023-05-21
@philipcball
Wow, Einstein wrote about the formation of meanders in rivers. I had no idea. https://t.co/iDunLufDqW
2023-05-22
@ylecun
@jeremyphoward @adamdangelo @robinhanson @SchmidhuberAI I sure did.
2023-05-21
@ipfconline1
How Soon Will #AI Kill Authentic Music? https://t.co/WEJRFDwUD9 via @Hackernoon #MachineLearning #DeepLearning… https://t.co/ZztwHp2odS
2023-05-20
@KirkDBorne
“Multimodal #DeepLearning” https://t.co/P1UPfNge2j [Download 272-page PDF eBook] ——— #BigData #DataScience #AI #ML… https://t.co/uqyHJFmBU4
2023-05-21
@johnjnay
Tree of Thoughts: LLMs Deliberately Solving Problems -LLMs consider multiple reasoning paths -Self-evaluate choice… https://t.co/kaFoLMW9qv
2023-05-20
@philipcball
Gravitational machines and how to spot them. This must be a fairly old article by Freeman Dyson, and I'm not sure w… https://t.co/eW1wlQSgOr
2023-05-22
@AstroKirsten
New paper just dropped! I've finally put my first paper relating to my PhD research onto arXiv now that it's been… https://t.co/a4J13AoGUI
2023-05-22
@KirkDBorne
#MachineLearning and #DeepLearning Papers Explained — project by @RitvikRastogi19 on @dair_ai —… https://t.co/tmqbDgWLd7
2023-05-21
@ylecun
@Newsalertswork @jiwa986 @erikbryn @GoldmanSachs @geoffreyhinton I picked a bunch of economists who I know for a fa… https://t.co/e8K8Wns4uq
2023-05-21
@KirkDBorne
Productivity tools by @abacusai at https://t.co/C1Qr43DRjs — built on Large Language Models #LLMs: 🟢ChatLLM—search… https://t.co/GTTgo8J8Uz
2023-05-20
@Cool_Davey
/ teaching My boys how to count👨‍🎓1️⃣2️⃣3️⃣ #FaceFuck #ThickDick #DomDaddy #VerbalTop #deeplearning #justforfans 🆒… https://t.co/asoh09VKAp
2023-05-20
@BrianRoemmele
I will be experimenting this week with Drag Your GAN written about in this paper and shown in the video below. Thi… https://t.co/rUij9SZTXh
2023-05-22
@jurafsky
(3/3) We hope string2string will be a valuable asset for researchers & practitioners across NLP, bioinformatics, CS… https://t.co/r84qSSZVbg
2023-05-20
@yuqirose
Congratulations to Dr. Rui (Ray) Wang @Rayruw on his awesome PhD thesis defense in @ucsd_cse! Ray spearheaded the… https://t.co/czdHWK290q
2023-05-22
@RationalWiki
AI detectors are biased against non-native writers of English https://t.co/QRwpFny91i
2023-05-21
@timnitGebru
"we present an alternative explanation for emergent abilities:...when analyzing fixed model outputs, one can choose… https://t.co/h93Bdsj1yt
2023-05-20
@KirkDBorne
The 7 features needed in an #EnterpriseKnowledge Management solution: https://t.co/GtLtSBnMOR ** The @Mindbreeze In… https://t.co/3asDT6J2RG
2023-05-20
@KirkDBorne
How #AI Fails Us: https://t.co/4LMG58N2ed [download 24-page PDF report] —————— #RegTech #AIEthics #TrustedAI… https://t.co/SAd4RMPWE4
2023-05-21
@KirkDBorne
How Computers Learn (Gradient Descent & Backpropagation) — #NeuralNetworks Explained: https://t.co/Rp80ylBPiu [Vide… https://t.co/k3K2PTR2wE
2023-05-21
@AIBoom_net
道徳的な判断を行うためのヒントをAIが引き出す 論文：https://t.co/weN8etNMyA ワシントン大などの研究グループが開発したAIシステム「CLARIFY DELPHI」は、人間が道徳的な判断を行う際に、さまざ… https://t.co/UFNfsUHTN5
2023-05-21
@BDAnalyticsnews
10 Algorithms for that dominate our world.. #ArtificialIntelligence #AI #DataScience #DataScientists #CodeNewbies… https://t.co/crQ6NYNYLD
2023-05-20
@KirkDBorne
#ChatGPT and #AI in Education [#infographic] ======= #EdTech #GenerativeAI #MachineLearning #NLProc #DeepLearning… https://t.co/evAC7NWh0g
2023-05-20
@KirkDBorne
Learn #DataScience from Scratch [using this curriculum with 20 free online courses] ————— #BigData #DataScientists… https://t.co/g2RMAaJSBr
2023-05-21
@ylecun
@OmarSaydThat @elonmuskewl Many of my friends and colleagues are not on Twitter. A friend once told me "Twitter giv… https://t.co/i8psV4ikZN
2023-05-20
@johnjnay
LLM vs LLM: Detecting Errors via Cross Examining Agents -An incorrect claim is likely to result in inconsistency w… https://t.co/EXUkVfwUbY
2023-05-23
@giswqs
I just added the GroundingDINO package to PyPI. Object detection with text prompts is coming to segment-geospatial… https://t.co/vV7x7HEySN
2023-05-22
@KirkDBorne
*Online* eBook [open access; NO DOWNLOAD] — #MachineLearning from Scratch: https://t.co/xiIOcPlDBx ————— #BigData… https://t.co/Ed3uPvvOlM
2023-05-21
@KirkDBorne
Download FREE 824-page classic book on #ComputerVision — Algorithms and Applications: https://t.co/N1e4HzeqrI —————… https://t.co/uYaGnhNHhw
2023-05-21
@ylecun
@jenningsgreg Yes, and they are authoritarian governments.
2023-05-21
@KirkDBorne
[Download FREE 379-page eBook] #Python #DeepLearning — Techniques, #NeuralNetwork Architectures, and #GANs with PyT… https://t.co/rVVYwKMJR3
2023-05-21

Hot Papers

Scaling laws for language encoding models in fMRI
Richard Antonello, Aditya Vaidya, Alexander G. Huth
2023-05-22
HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
Junyi Li, Xiaoxue Cheng, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen
2023-05-22
Appraising the Potential Uses and Harms of LLMs for Medical Systematic Reviews
Hye Sun Yun, Iain J. Marshall, Thomas Trikalinos, Byron C. Wallace
2023-05-22
Prompting with Pseudo-Code Instructions
Mayank Mishra, Prince Kumar, Riyaz Bhat, Rudra Murthy V, Danish Contractor, Srikanth Tamilselvam
2023-05-22
Lighting and Rotation Invariant Real-time Vehicle Wheel Detector based on YOLOv5
Michael Shenoda
2023-05-28
Neural Machine Translation with Dynamic Graph Convolutional Decoder
Lei Li, Kai Fan, Lingyu Yang, Hongjia Li, Chun Yuan
2023-05-28
Rethinking Masked Language Modeling for Chinese Spelling Correction
Hongqiu Wu, Shaohua Zhang, Yuchen Zhang, Hai Zhao
2023-05-28
A Comparative Analysis of Portfolio Optimization Using Mean-Variance, Hierarchical Risk Parity, and Reinforcement Learning Approaches on the Indian Stock Market
Jaydip Sen, Aditya Jaiswal, Anshuman Pathak, Atish Kumar Majee, Kushagra Kumar, Manas Kumar Sarkar, Soubhik Maji
2023-05-27
Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
Yutao Mou, Xiaoshuai Song, Keqing He, Chen Zeng, Pei Wang, Jingang Wang, Yunsen Xian, Weiran Xu
2023-05-28
A Model-Based Method for Minimizing CVaR and Beyond
Si Yi Meng, Robert M. Gower
2023-05-27
Text-to-SQL Error Correction with Language Models of Code
Ziru Chen, Shijie Chen, Michael White, Raymond Mooney, Ali Payani, Jayanth Srinivasa, Yu Su, Huan Sun
2023-05-28
Reliable and Interpretable Drift Detection in Streams of Short Texts
Ella Rabinovich, Matan Vetzler, Samuel Ackerman, Ateret Anaby-Tavor
2023-05-28
Exploring Partial Knowledge Base Inference in Biomedical Entity Linking
Hongyi Yuan, Keming Lu, Zheng Yuan
2023-05-31
On the Power of Foundation Models
Yang Yuan
2023-05-31
Volume Feature Rendering for Fast Neural Radiance Field Reconstruction
Kang Han, Wei Xiang, Lu Yu
2023-05-31
Plug-and-Play Knowledge Injection for Pre-trained Language Models
Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
2023-05-28
A Multi-Modal Transformer Network for Action Detection
Matthew Korban, Scott T. Acton, Peter Youngs
2023-05-31
Forecasting Local Behavior of Self-organizing Many-agent System without Reconstruction
Beomseok Kang, Minah Lee, Harshit Kumar, Saibal Mukhopadhyay
2023-05-31
GRES: Generalized Referring Expression Segmentation
Chang Liu, Henghui Ding, Xudong Jiang
2023-06-01
Speaker-specific Thresholding for Robust Imposter Identification in Unseen Speaker Recognition
Ashutosh Chaubey, Sparsh Sinha, Susmita Ghose
2023-06-01
Differential Diffusion: Giving Each Pixel Its Strength
Eran Levin, Ohad Fried
2023-06-01
EEL: Efficiently Encoding Lattices for Reranking
Prasann Singhal, Jiacheng Xu, Xi Ye, Greg Durrett
2023-06-01
Exposing Attention Glitches with Flip-Flop Language Modeling
Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
2023-06-01
"Let's not Quote out of Context": Unified Vision-Language Pretraining for Context Assisted Image Captioning
Abisek Rajakumar Kalarani, Pushpak Bhattacharyya, Niyati Chhaya, Sumit Shekhar
2023-06-01
Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
Christian H. X. Ali Mehmeti-Göpel, Jan Disselhoff
2023-06-01
Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition
Yuchen Hu, Nana Hou, Chen Chen, Eng Siong Chng
2023-05-27
Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extraction
Ting Xu, Huiyun Yang, Zhen Wu, Jiaze Chen, Fei Zhao, Xinyu Dai
2023-05-27
Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models
Zhong Zhang, Bang Liu, Junming Shao
2023-05-27
Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature
Khang Nguyen, Hieu Nong, Vinh Nguyen, Nhat Ho, Stanley Osher, Tan Nguyen
2023-05-31
Dense-ATOMIC: Towards Densely-connected ATOMIC with High Knowledge Coverage and Massive Multi-hop Paths
Xiangqing Shen, Siwei Wu, Rui Xia
2023-05-28

Fresh Papers

Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li, Christoph Feichtenhofer
2023-06-01
StyleGAN knows Normal, Depth, Albedo, and More
Anand Bhattad, Daniel McKee, Derek Hoiem, D. A. Forsyth
2023-06-01
Continual Learning for Abdominal Multi-Organ and Tumor Segmentation
Yixiao Zhang, Xinyi Li, Huimiao Chen, Alan Yuille, Yaoyao Liu, Zongwei Zhou
2023-06-01
Diffusion Self-Guidance for Controllable Image Generation
Dave Epstein, Allan Jabri, Ben Poole, Alexei A. Efros, Aleksander Holynski
2023-06-01
Using generative AI to investigate medical imagery models and datasets
Oran Lang, Doron Yaya-Stupp, Ilana Traynis, Heather Cole-Lewis, Chloe R. Bennett, Courtney Lyles, Charles Lau, Christopher Semturs, Dale R. Webster, Greg S. Corrado, Avinatan Hassidim, Yossi Matias, Yun Liu, Naama Hammel, Boris Babenko
2023-06-01
StyleDrop: Text-to-Image Generation in Any Style
Kihyuk Sohn, Nataniel Ruiz, Kimin Lee, Daniel Castro Chin, Irina Blok, Huiwen Chang, Jarred Barber, Lu Jiang, Glenn Entis, Yuanzhen Li, Yuan Hao, Irfan Essa, Michael Rubinstein, Dilip Krishnan
2023-06-01
StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners
Yonglong Tian, Lijie Fan, Phillip Isola, Huiwen Chang, Dilip Krishnan
2023-06-01
SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds
Yanyu Li, Huan Wang, Qing Jin, Ju Hu, Pavlo Chemerys, Yun Fu, Yanzhi Wang, Sergey Tulyakov, Jian Ren
2023-06-01
Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds
Shaowei Liu, Saurabh Gupta, Shenlong Wang
2023-06-01
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Xingyu Dang, Song Han
2023-06-01
TopEx: Topic-based Explanations for Model Comparison
Shreya Havaldar, Adam Stein, Eric Wong, Lyle Ungar
2023-06-01
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
Yuanwen Yue, Sabarinath Mahadevan, Jonas Schult, Francis Engelmann, Bastian Leibe, Konrad Schindler, Theodora Kontogianni
2023-06-01
Active Reinforcement Learning under Limited Visual Observability
Jinghuan Shang, Michael S. Ryoo
2023-06-01
Intriguing Properties of Text-guided Diffusion Models
Qihao Liu, Adam Kortylewski, Yutong Bai, Song Bai, Alan Yuille
2023-06-01
Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models
Chang Liu, Haoning Wu, Yujie Zhong, Xiaoyun Zhang, Weidi Xie
2023-06-01
Improving and Benchmarking Offline Reinforcement Learning Algorithms
Bingyi Kang, Xiao Ma, Yirui Wang, Yang Yue, Shuicheng Yan
2023-06-01
ViCo: Detail-Preserving Visual Condition for Personalized Text-to-Image Generation
Shaozhe Hao, Kai Han, Shihao Zhao, Kwan-Yee K. Wong
2023-06-01
GRES: Generalized Referring Expression Segmentation
Chang Liu, Henghui Ding, Xudong Jiang
2023-06-01
The Hidden Language of Diffusion Models
Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Mosseri, Lior Wolf
2023-06-01
BUOL: A Bottom-Up Framework with Occupancy-aware Lifting for Panoptic 3D Scene Reconstruction From A Single Image
Tao Chu, Pan Zhang, Qiong Liu, Jiaqi Wang
2023-06-01
Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation
Minghui Hu, Jianbin Zheng, Daqing Liu, Chuanxia Zheng, Chaoyue Wang, Dacheng Tao, Tat-Jen Cham
2023-06-01
Dynamic Algorithms for Matroid Submodular Maximization
Kiarash Banihashem, Leyla Biabani, Samira Goudarzi, MohammadTaghi Hajiaghayi, Peyman Jabbarzade, Morteza Monemizadeh
2023-06-01
LIV: Language-Image Representations and Rewards for Robotic Control
Yecheng Jason Ma, William Liang, Vaidehi Som, Vikash Kumar, Amy Zhang, Osbert Bastani, Dinesh Jayaraman
2023-06-01
The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects
Ruohan Gao, Yiming Dou, Hao Li, Tanmay Agarwal, Jeannette Bohg, Yunzhu Li, Li Fei-Fei, Jiajun Wu
2023-06-01
Speaker-specific Thresholding for Robust Imposter Identification in Unseen Speaker Recognition
Ashutosh Chaubey, Sparsh Sinha, Susmita Ghose
2023-06-01
Differential Diffusion: Giving Each Pixel Its Strength
Eran Levin, Ohad Fried
2023-06-01
EEL: Efficiently Encoding Lattices for Reranking
Prasann Singhal, Jiacheng Xu, Xi Ye, Greg Durrett
2023-06-01
Exposing Attention Glitches with Flip-Flop Language Modeling
Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
2023-06-01
CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions
Ben Adcock, Juan M. Cardenas, Nick Dexter
2023-06-01
Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance
Jinbo Xing, Menghan Xia, Yuxin Liu, Yuechen Zhang, Yong Zhang, Yingqing He, Hanyuan Liu, Haoxin Chen, Xiaodong Cun, Xintao Wang, Ying Shan, Tien-Tsin Wong
2023-06-01

reinforcement learning

SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning
Dongseok Shim, Seungjae Lee, H. Jin Kim
2023-05-31
A Simulation Environment and Reinforcement Learning Method for Waste Reduction
Sami Jullien, Mozhdeh Ariannezhad, Paul Groth, Maarten de Rijke
2023-05-26
Centralised rehearsal of decentralised cooperation: Multi-agent reinforcement learning for the scalable coordination of residential energy flexibility
Flora Charbonnier, Bei Peng
2023-05-30
Self-Supervised Reinforcement Learning that Transfers using Random Features
Boyuan Chen, Chuning Zhu, Pulkit Agrawal, Kaiqing Zhang, Abhishek Gupta
2023-05-26
Video Prediction Models as Rewards for Reinforcement Learning
Alejandro Escontrela, Ademi Adeniji, Wilson Yan, Ajay Jain, Xue Bin Peng, Ken Goldberg, Youngwoon Lee, Danijar Hafner, Pieter Abbeel
2023-05-30
Video Prediction Models as Rewards for Reinforcement Learning
Alejandro Escontrela, Ademi Adeniji, Wilson Yan, Ajay Jain, Xue Bin Peng, Ken Goldberg, Youngwoon Lee, Danijar Hafner, Pieter Abbeel
2023-05-23
XRoute Environment: A Novel Reinforcement Learning Environment for Routing
Zhanwen Zhou, Hankz Hankui Zhuo, Xiaowu Zhang, Qiyuan Deng
2023-05-23
Model-based adaptation for sample efficient transfer in reinforcement learning control of parameter-varying systems
Ibrahim Ahmed, Marcos Quinones-Grueiro, Gautam Biswas
2023-05-20
Natural Language Specification of Reinforcement Learning Policies through Differentiable Decision Trees
Pradyumna Tambwekar, Andrew Silva, Nakul Gopalan, Matthew Gombolay
2023-05-20
A Survey on Causal Reinforcement Learning
Yan Zeng, Ruichu Cai, Fuchun Sun, Libo Huang, Zhifeng Hao
2023-06-01
STEEL: Singularity-aware Reinforcement Learning
Xiaohong Chen, Zhengling Qi, Runzhe Wan
2023-05-26
Distributionally Robust Optimization Efficiently Solves Offline Reinforcement Learning
Yue Wang, Yuting Hu, Jinjun Xiong, Shaofeng Zou
2023-05-22
Action valuation of on- and off-ball soccer players based on multi-agent deep reinforcement learning
Hiroshi Nakahara, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii
2023-05-29
Conditional Mutual Information for Disentangled Representations in Reinforcement Learning
Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah P. Hanna, Stefano V. Albrecht
2023-05-23
Cross-Entropy Estimators for Sequential Experiment Design with Reinforcement Learning
Tom Blau, Edwin Bonilla, Iadine Chades, Amir Dezfouli
2023-05-29
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
Guan-Ting Liu, En-Pei Hu, Pu-Jen Cheng, Hung-yi Lee, Shao-Hua Sun
2023-05-31
On First-Order Meta-Reinforcement Learning with Moreau Envelopes
Mohammad Taha Toghani, Sebastian Perez-Salazar, César A. Uribe
2023-05-20
HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environments
Ji Liu, Zhihua Wu, Dianhai Yu, Yanjun Ma, Danlei Feng, Minxu Zhang, Xinxuan Wu, Xuefeng Yao, Dejing Dou
2023-05-28
Provably Efficient Generalized Lagrangian Policy Optimization for Safe Multi-Agent Reinforcement Learning
Dongsheng Ding, Xiaohan Wei, Zhuoran Yang, Zhaoran Wang, Mihailo R. Jovanović
2023-05-31
The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication
Xing Xu, Rongpeng Li, Zhifeng Zhao, Honggang Zhang
2023-05-29
RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states
Ziyuan Zhou, Guanjun Liu
2023-05-31
Representation-Driven Reinforcement Learning
Ofir Nabati, Guy Tennenholtz, Shie Mannor
2023-05-31
Approximating Energy Market Clearing and Bidding With Model-Based Reinforcement Learning
Thomas Wolgast, Astrid Nieße
2023-05-25
Online Nonstochastic Model-Free Reinforcement Learning
Udaya Ghai, Arushi Gupta, Wenhan Xia, Karan Singh, Elad Hazan
2023-05-27
A New Policy Iteration Algorithm For Reinforcement Learning in Zero-Sum Markov Games
Anna Winnicki, R. Srikant
2023-05-25
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression
Sami Jullien, Romain Deffayet, Jean-Michel Renders, Paul Groth, Maarten de Rijke
2023-05-26
Active Reinforcement Learning under Limited Visual Observability
Jinghuan Shang, Michael S. Ryoo
2023-06-01
Offline Experience Replay for Continual Offline Reinforcement Learning
Sibo Gai, Donglin Wang, Li He
2023-05-23
RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environments
Daniel Coelho, Miguel Oliveira, Vitor Santos
2023-05-29
GOATS: Goal Sampling Adaptation for Scooping with Curriculum Reinforcement Learning
Yaru Niu, Shiyu Jin, Zeqing Zhang, Jiacheng Zhu, Ding Zhao, Liangjun Zhang
2023-05-26

language

Prompting Is Programming: A Query Language for Large Language Models
Luca Beurer-Kellner, Marc Fischer, Martin Vechev
2023-05-30
Towards Leaving No Indic Language Behind: Building Monolingual Corpora, Benchmark and Models for Indic Languages
Sumanth Doddapaneni, Rahul Aralikatte, Gowtham Ramesh, Shreya Goyal, Mitesh M. Khapra, Anoop Kunchukuttan, Pratyush Kumar
2023-05-24
Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languages
Yash Madhani, Mitesh M. Khapra, Anoop Kunchukuttan
2023-05-25
BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting
Zheng-Xin Yong, Hailey Schoelkopf, Niklas Muennighoff, Alham Fikri Aji, David Ifeoluwa Adelani, Khalid Almubarak, M Saiful Bari, Lintang Sutawika, Jungo Kasai, Ahmed Baruwa, Genta Indra Winata, Stella Biderman, Edward Raff, Dragomir Radev, Vassilina Nikoulina
2023-05-27
BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting
Zheng-Xin Yong, Hailey Schoelkopf, Niklas Muennighoff, Alham Fikri Aji, David Ifeoluwa Adelani, Khalid Almubarak, M Saiful Bari, Lintang Sutawika, Jungo Kasai, Ahmed Baruwa, Genta Indra Winata, Stella Biderman, Edward Raff, Dragomir Radev, Vassilina Nikoulina
2023-05-25
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Ayyoob ImaniGooghari, Peiqin Lin, Amir Hossein Kargaran, Silvia Severini, Masoud Jalili Sabet, Nora Kassner, Chunlan Ma, Helmut Schmid, André F. T. Martins, François Yvon, Hinrich Schütze
2023-05-20
Images in Language Space: Exploring the Suitability of Large Language Models for Vision & Language Tasks
Sherzod Hakimov, David Schlangen
2023-05-23
LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages
Milind Agarwal, Md Mahfuz Ibn Alam, Antonios Anastasopoulos
2023-05-23
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Ayyoob Imani, Peiqin Lin, Amir Hossein Kargaran, Silvia Severini, Masoud Jalili Sabet, Nora Kassner, Chunlan Ma, Helmut Schmid, André F. T. Martins, François Yvon, Hinrich Schütze
2023-05-26
How do languages influence each other? Studying cross-lingual data sharing during LLM fine-tuning
Rochelle Choenni, Dan Garrette, Ekaterina Shutova
2023-05-22
Rethinking Annotation: Can Language Learners Contribute?
Haneul Yoo, Rifki Afina Putri, Changyoon Lee, Youngin Lee, So-Yeon Ahn, Dongyeop Kang, Alice Oh
2023-05-29
BigTrans: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages
Wen Yang, Chong Li, Jiajun Zhang, Chengqing Zong
2023-05-29
Instruct-Align: Teaching Novel Languages with to LLMs through Alignment-based Cross-Lingual Instruction
Samuel Cahyawijaya, Holy Lovenia, Tiezheng Yu, Willy Chung, Pascale Fung
2023-05-23
Scaling Speech Technology to 1,000+ Languages
Vineel Pratap, Andros Tjandra, Bowen Shi, Paden Tomasello, Arun Babu, Sayani Kundu, Ali Elkahky, Zhaoheng Ni, Apoorv Vyas, Maryam Fazel-Zarandi, Alexei Baevski, Yossi Adi, Xiaohui Zhang, Wei-Ning Hsu, Alexis Conneau, Michael Auli
2023-05-22
IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages
AI4Bharat, Jay Gala, Pranjal A. Chitale, Raghavan AK, Sumanth Doddapaneni, Varun Gumma, Aswanth Kumar, Janki Nawale, Anupama Sujatha, Ratish Puduppully, Vivek Raghavan, Pratyush Kumar, Mitesh M. Khapra, Raj Dabre, Anoop Kunchukuttan
2023-05-25
PaLI: A Jointly-Scaled Multilingual Language-Image Model
Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Nan Ding, Keran Rong, Hassan Akbari, Gaurav Mishra, Linting Xue, Ashish Thapliyal, James Bradbury, Weicheng Kuo, Mojtaba Seyedhosseini, Chao Jia, Burcu Karagol Ayan, Carlos Riquelme, Andreas Steiner, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut
2023-05-29
Computational Language Assessment in patients with speech, language, and communication impairments
Charalambos Themistocleous
2023-05-31
Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models
Orevaoghene Ahia, Sachin Kumar, Hila Gonen, Jungo Kasai, David R. Mortensen, Noah A. Smith, Yulia Tsvetkov
2023-05-23
Machine Translation by Projecting Text into the Same Phonetic-Orthographic Space Using a Common Encoding
Amit Kumar, Shantipriya Parida, Ajay Pratap, Anil Kumar Singh
2023-05-21
SERENGETI: Massively Multilingual Language Models for Africa
Ife Adebara, AbdelRahim Elmadany, Muhammad Abdul-Mageed, Alcides Alcoba Inciarte
2023-05-26
A Crosslingual Investigation of Conceptualization in 1335 Languages
Yihong Liu, Haotian Ye, Leonie Weissweiler, Philipp Wicke, Renhao Pei, Robert Zangenfeind, Hinrich Schütze
2023-05-26
mPLM-Sim: Unveiling Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Models
Peiqin Lin, Chengzhi Hu, Zheyu Zhang, André F. T. Martins, Hinrich Schütze
2023-05-23
Multi-lingual and Multi-cultural Figurative Language Understanding
Anubha Kabra, Emmy Liu, Simran Khanuja, Alham Fikri Aji, Genta Indra Winata, Samuel Cahyawijaya, Anuoluwapo Aremu, Perez Ogayo, Graham Neubig
2023-05-25
GlobalBench: A Benchmark for Global Progress in Natural Language Processing
Yueqi Song, Catherine Cui, Simran Khanuja, Pengfei Liu, Fahim Faisal, Alissa Ostapenko, Genta Indra Winata, Alham Fikri Aji, Samuel Cahyawijaya, Yulia Tsvetkov, Antonios Anastasopoulos, Graham Neubig
2023-05-24
Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models
Ratish Puduppully, Raj Dabre, Ai Ti Aw, Nancy F. Chen
2023-05-22
Better Low-Resource Entity Recognition Through Translation and Annotation Fusion
Yang Chen, Vedaant Shah, Alan Ritter
2023-05-24
X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages
Feilong Chen, Minglun Han, Haozhi Zhao, Qingyang Zhang, Jing Shi, Shuang Xu, Bo Xu
2023-05-22
Better Low-Resource Entity Recognition Through Translation and Annotation Fusion
Yang Chen, Vedaant Shah, Alan Ritter
2023-05-23
Measuring Gender Bias in West Slavic Language Models
Sandra Martinková, Karolina Stańczak, Isabelle Augenstein
2023-05-25
Machine-Created Universal Language for Cross-lingual Transfer
Yaobo Liang, Quanzhi Zhu, Junhe Zhao, Nan Duan
2023-05-22