Volume 232 Proceedings of the 2023 Conference on Lifelong Learning Agents https://
proceedings.mlr.press/v232/ Is now available on PMLR
MACHINE LEARNING
-
Volume 232 of 2023 Conference on Lifelong Learning Agents Available
By
–
-
Rise of Multimodal Data Science in AI
By
–
Beyond Text and Numbers: The Rise of Multimodal Data Science #ai #datascience #MachineLearning
-
Skip Connections Research and Computer Vision Architecture Alternatives
By
–
You gonna pretend there isn’t research suggesting skip connections aren’t needed, and that anyway there’s dozens of ways in CV of dealing with that issue?
-
Fine-tuned Open-Source LLMs Outperform Commercial Solutions
By
–
Developers are realizing that #finetuned open-source LLMs like #Llama2 are more cost-effective and performant than commercial LLMs like #GPT4. Don't miss our interactive discussion on all things fine-tuning #LLMs to learn how to get started. https://
pbase.ai/3MQUwWL -
Data AI Summit Call for Presentations Now Open
By
–
Do you have compelling #GenerativeAI, data science, or ML insights? Or maybe you’ve crafted noteworthy features in open-source tech? The #DataAISummit community wants to hear from you. Call for Presentations is now open! Submissions end Jan 5, act now: https://
bit.ly/3sOkYt0 -
Computer Vision Learnings Transfer to Other AI Domains
By
–
Yeah it’s another place where it seems likely some learnings from CV will cross over some day
-
Latent space sequence-to-sequence translation advantages explained
By
–
what do you think are the advantages of doing this kind of sequence-to-sequence translation in latent space?
-
Pretrained Embeddings Optimization Insights and Implementation
By
–
super cool! I wonder if it might work better if you work in the space of a pretrained embedding. care to share some insight on why this doesn't work so well initially?
-
Embedding to Text Reconstruction: Three-Step Technical Approach
By
–
– step 1 can be implemented with any off-the-shelf embedder
– step 3 is solved with vec2text (
http://
github.com/jxmorris12/vec
2text
…)
– step 2 doesn't exist yet – some tasks might be solvable even with a simple embedding-to-embedding linear mapping if you're interested in trying this, DM me 🙂 -
Text Diffusion in Embedding Space for Sequence Tasks
By
–
cool research idea for someone: text diffusion in embedding space solve any sequence-to-sequence task in three steps:
1. embed source sentence text
2. build diffusion model that maps input text embedding to target text embedding
3. invert to produce target text