9). Evaluation of o1 – provides a comprehensive evaluation of OpenAI's o1-preview LLM; shows strong performance across many tasks such as competitive programming, generating coherent and accurate radiology reports, high school-level mathematical reasoning tasks, chip design
MACHINE LEARNING
-

Architecture Search Framework Optimizes LLM Inference Techniques
By
–
4). Architecture Search Framework for Inference-Time Techniques – introduces a modular framework for building and optimizing LLMs by combining multiple inference-time techniques…
-
RATIONALYST: Process Supervision Model for Reasoning Generalization
By
–
5). RATIONALYST – a model for process-supervision of reasoning that enables generalization across diverse reasoning tasks; this process is achieved with pre-training on a collection of 79k rationales from the Pile and a combination of reasoning datasets with minimal human
-

RNNs Revisited: Efficient Parallel Training Without Hidden States
By
–
2). Were RNNs All We Needed? – revisits RNNs and shows that by removing the hidden states from input, forget, and update gates RNNs can be efficiently trained in parallel.
-
Top Machine Learning Papers of the Week
By
–
The Top ML Papers of the Week (Sep 30 – Oct 6): – Movie Gen
– RATIONALYST
– An Analysis of o1-preview
– Were RNNs All We Needed?
– LLMs Know More Than They Show
– Not All LLM Reasoners Are Created Equal Read on for more: -

Language Identification vs Generation: Revisiting Gold’s Classic Result
By
–
Super cool talk and result. Classic work by Gold in 1967 (!) shows that language identification is impossible. But they revisit this setting with a focus on *generation* showing it's always possible.
-

Jon Kleinberg presents Language Generation in the Limit
By
–
Second talk of the day is by Jon Kleinberg, on "Language Generation in the Limit"
-

Turing’s Research Style: Lessons for Modern ML Community
By
–
Avi concluded with some comments on Turing's research style, as one of the most brilliant and influential scientists of our era. The ML community could take note of the last one: "Does not rush to publish"
-

Blood Proteins Reveal Aging and Disease Patterns Through AI
By
–
Thousands of proteins in our blood are illuminating our pace of individual organ and body-wide biological aging, the impact of diet and lifestyle, and enabling discovery of novel cause and effect for diseases.
Reviewed in the new Ground Truths
(link in my profile, d/t -
Intense Mathematics Competition Sparks Engagement
By
–
Intense math battle!
— Amitav Bhattacharjee (@bamitav) 6 octobre 2024
pic.twitter.com/DGnt30hAG0#Mathematics #math
@KirkDBorne @patricegorissen @jeffkagan @EdwardKens50830 @enilev @insom_ai333 @ChrisCCrowley @sallyeaves @gurmeet_judge @CurieuxExplorer @LavaletteAstrid @bamitav @chidambara09 @adamsconsulting @AkwyZ @alvinfoo…Intense math battle! #Mathematics #math @KirkDBorne @patricegorissen @jeffkagan @radres @enilev @insom_ai333 @cc_crowley @sallyeaves @gurmeet_judge @CurieuxExplorer @LavaletteAstrid @bamitav @chidambara09 @adamsconsulting @AkwyZ @alvinfoo