Thanks Brian for the fun discussion! Here's the link to the project I mentioned on Language Embedded Radiance Fields: https://
lerf.io
RESEARCH
-
Language Embedded Radiance Fields Project Link Shared
By
–
-
AI World: Historical Perspective on Recent Developments
By
–
it's an AI, AI world. read this essay — it's chock full of historical perspective and excellent details RE the last several months of crazy– by @BradStone
. -
NeRFs Generate 3D Models from Low Quality Videos
By
–
Big ass NeRFs from shitty videos. Wow. https://t.co/BA4oX2G7D2
— Robert Scoble (@Scobleizer) 15 juin 2023Big ass NeRFs from shitty videos. Wow.
-
Research SuperCluster Enables Breakthrough AI Research at Scale
By
–
The Research SuperCluster enables our research teams to do new, breakthrough AI research at an even greater scale and pace than ever before. Ning Dong and Maha Elbayad shared more about how it's enabling their work.
— AI at Meta (@AIatMeta) 15 juin 2023
More details ➡️ https://t.co/i1W6ld96Eb pic.twitter.com/ZgtcmrzF8OThe Research SuperCluster enables our research teams to do new, breakthrough AI research at an even greater scale and pace than ever before. Ning Dong and Maha Elbayad shared more about how it's enabling their work. More details https://
bit.ly/3N2qHCR -
Postdoc Position: Cloud Robotics and AWS/Google Cloud Systems
By
–
Seeking Postdoc with experience in Robotics and Cloud-Based Systems (AWS, Google Cloud, Azure) to work closely with @UCBerkeley Profs. Ken Goldberg and Joey Gonzales on research on cloud robotics architectures and platforms such as FogROS2: https://
docs.google.com/document/d/e/2
PACX-1vR5n3aHbRl0luk3acq2xmf3HzmS6gJvEX7LC24c503PIT8mlWybxJiWAb3ZRVT2XKJWU62ztMvpQrqr/pub
… -
Progressively Optimized Local Radiance Fields for Robust View Synthesis
By
–
Progressively Optimized Local Radiance Fields for Robust View Synthesis
— AK (@_akhaliq) 15 juin 2023
paper page: https://t.co/9NUDJbvUtR
present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most… pic.twitter.com/Vt1dGq5hSWProgressively Optimized Local Radiance Fields for Robust View Synthesis paper page: https://
huggingface.co/papers/2303.13
791
… present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most -
Language Inclusion in Pretraining and Dataset Swapping
By
–
If the language has been included during pretraining, I that shouldn't be a problem (via swapping the dataset). Otherwise, I am not sure:
-
Proprietary Data and LLM Training Strategy for Enterprises
By
–
A few topics: * Why proprietary data enables enterprises to build higher quality large language models * Should your organization fine-tune pre-trained models or train from scratch * What are the steps that need to be considered before training your first model
-
Fine-tuning Limitations and Cross-lingual Transfer in Language Models
By
–
Interesting point! Next to instruction-finetuning, finetuning is usually for a specific task (e.g., language translation). Not sure how well the model would do if you change source language. I.e., I haven't seen any studies investigating that, yet.
-
LoRA-trained models show competitive performance with less overfitting
By
–
The performance of LoRA-trained models is usually pretty competitive. Sometimes even better than fully finetuned (prob due to less overfitting).
(Table from https://
arxiv.org/abs/2106.09685)