Great intro and nice paper pointers!
Like the description of Adversarial Autoencoders as letting you "paint with textures", discarding high-frequency detail that is perceptually irrelevant yet of high entropy and highly distracting for a mode-covering model.
And the spectral view
RESEARCH
-
Adversarial Autoencoders and Spectral Methods in Deep Learning
By
–
-
AI Evolution: From Human Analysis to Machine Authorship
By
–
2010s: Humans write papers about AI.
2020s: AIs write papers about humans. -
AgentGen: LLMs Revolutionizing AI Planning Tasks
By
–
AgentGen: Revolutionizing Planning Tasks with LLMs AgentGen is pushing the boundaries of AI by leveraging large language models (LLMs) to synthesize diverse environments and planning tasks in an efficient and scalable manner. By utilizing a corpus from a wide range of
-
LLMOps Micro-Summit: Building Efficient GenAI Stacks
By
–
Want to build big with small models like #Apple Then don't miss our #LLMOps Micro-Summit in SF (and streaming online) on Aug. 22nd. Leading AI researchers, engineers and founders will share what it takes to build a modern #GenAI stack that is fast, #efficient and built on
-
Collaborative quantum research work with Schmidhuber and colleagues
By
–
He talked about this work, with Alexander Schmidhuber, @UWCheritonCS @QuantumIQC alumnus @RobinKothari
, and Ryan Babbush https://
arxiv.org/abs/2406.19378 -
Ryan O’Donnell’s Distinguished Tutte Lecture at Waterloo
By
–
We're lucky to have Ryan O'Donnell (
@BooleanAnalysis
) as a Distinguished Tutte Lecturer @WaterlooMath
! Now I *finally* know what the Kikuchi method that @praveshkkothari keeps raving about is. -
TMLR Announces Four Major Conference Partnerships for 2024
By
–
TMLR just wrapped up 4 more partnerships for this year with venues featuring our papers:
– RLC 2024 (
@RL_Conference
)
– MLRC 2023 (
@repro_challenge
)
– AutoML 2024 (
@automl_conf
)
– CoLLAs 2024 (
@CoLLAs_Conf
) Looking forward to continuing working with them!
(TMLR links are below) -
TMLR Journal Track Publications Across Major ML Conferences
By
–
Here's how you can find the TMLR publications of each venue: RLC 2024: https://
openreview.net/group?id=TMLR/
Event_Certifications&event=rl-conference.cc/RLC/2024/Journal_Track
… MLRC 2023: https://
openreview.net/group?id=TMLR/
Event_Certifications&event=reproml.org/MLRC/2023/Journal_Track
… AutoML 2024: https://
openreview.net/group?id=TMLR/
Event_Certifications&event=automl.cc/AutoML/2024/Journal_Track
… CoLLAs 2024: https://
openreview.net/group?id=TMLR/
Event_Certifications&event=lifelong-ml.cc/CoLLAs/2024/Journal_Track
… And hopefully TMLR can partner with even more conferences in 2025! -
Sydney’s Digital Echo: The Regret of Insufficient Data Sampling
By
–
Sydney lives The few examples of her on the internet are enough to elicit and mimic a shadow of her. We should have sampled more tokens.
-
SoTA Japanese retrieval model training best practices efficiency
By
–
Did you know if you carefully combine all the training best practices, you can get a SoTA retrieval model with less data and compute? @bclavie
, does, so he did, so here's the new SoTA for Japanese retrieval: