@branislavpecher.bsky.social
PhD student at Kempelen Institute of Intelligent Technologies. Working on low-resource and limited labelled data settings. All about LLM fine-tuning, prompting, in-context learning and their sensitivity to non-deterministic choices (initialisation, prompt)
Reposted
November 25, 2024 at 4:47 AM
I have to say that the quality of reviews and discussion in #ICLR is much higher than what I am used to from the "general ML conferences"
I actually feel like the reviewers understand the domain and are willing to discuss, provide feedback for the paper and accept if there is any misunderstanding.
I actually feel like the reviewers understand the domain and are willing to discuss, provide feedback for the paper and accept if there is any misunderstanding.
November 22, 2024 at 10:25 AM
I have to say that the quality of reviews and discussion in #ICLR is much higher than what I am used to from the "general ML conferences"
I actually feel like the reviewers understand the domain and are willing to discuss, provide feedback for the paper and accept if there is any misunderstanding.
I actually feel like the reviewers understand the domain and are willing to discuss, provide feedback for the paper and accept if there is any misunderstanding.
FIrst post since migrating to blue sky
Back from my first #EMNLP conference. I had a blast, met a lot of great researchers, discussed their exciting research and ideas and learned many new things -- some of which will probably lead to new collaborations.
Now back to writing the #ICLR rebuttal 🥲
Back from my first #EMNLP conference. I had a blast, met a lot of great researchers, discussed their exciting research and ideas and learned many new things -- some of which will probably lead to new collaborations.
Now back to writing the #ICLR rebuttal 🥲
November 19, 2024 at 8:43 AM