Learning to Ground Instructional Articles in Videos through Narrations paper page: https://
huggingface.co/papers/2306.03
802
… present an approach for localizing steps of procedural activities in narrated how-to videos. To deal with the scarcity of labeled data at scale, we source the step
RESEARCH
-
Grounding Instructional Steps in Narrated How-To Videos
By
–
-
Emergent Correspondence Discovery in Image Diffusion Models
By
–
Emergent Correspondence from Image Diffusion paper page: https://
huggingface.co/papers/2306.03
881
… Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explicit supervision. We -
Mega-TTS: Zero-Shot Text-to-Speech Scaling with Inductive Bias
By
–
Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias paper page: https://
huggingface.co/papers/2306.03
509
… Scaling text-to-speech to a large and wild dataset has been proven to be highly effective in achieving timbre and speech style generalization, particularly in zero-shot -
LEACE: Perfect Linear Concept Erasure in Closed Form
By
–
LEACE: Perfect linear concept erasure in closed form paper page: https://
huggingface.co/papers/2306.03
819
… introduce LEAst-squares Concept Erasure (LEACE), a closed-form method which provably prevents all linear classifiers from detecting a concept while inflicting the least possible damage to -
Natural Language Commanding via Program Synthesis for Productivity Software
By
–
Natural Language Commanding via Program Synthesis paper page: https://
huggingface.co/papers/2306.03
460
… present Semantic Interpreter, a natural language-friendly AI system for productivity software such as Microsoft Office that leverages large language models (LLMs) to execute user intent across -
Large Language Models Struggle With Code Containing Potential Bugs
By
–
Large Language Models of Code Fail at Completing Code with Potential Bugs paper page: https://
huggingface.co/papers/2306.03
438
… Large language models of code (Code-LLMs) have recently brought tremendous advances to code completion, a fundamental feature of programming assistance and code -
Static Evaluation of Code Completion by Large Language Models
By
–
A Static Evaluation of Code Completion by Large Language Models paper page: https://
huggingface.co/papers/2306.03
203
… Large language models trained on code have shown great potential to increase productivity of software developers. Several execution-based benchmarks have been proposed to -
Deductive Verification of Chain-of-Thought Reasoning in Large Language Models
By
–
Deductive Verification of Chain-of-Thought Reasoning paper page: https://
huggingface.co/papers/2306.03
872
… Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive -
Guggenheim Fellows Reception Celebrates Diverse AI and Science Awardees
By
–
Wonderful reception for @GuggFellows in NYC. Awardees from diverse backgrounds including scientists, artists, writers, historians, choreographers. Met @NarangLab in person and Ronitt Rubinfield (who was a wonderful mentor when I was at @MITEECS ) https://
gf.org/announcements/ -
Google Releases 7 Free Generative AI Courses for Learners
By
–
Google just dropped 7 new FREE generative #AI courses! 1. Intro to #GenerativeAI
2. Intro to LLMs
3. Responsible AI
4. Image Generation
5. Transformer Models & BERT Model
6. Create Image Captioning Models
7. Intro to Gen AI Studio via @Saboo_Shubham_