Control-R: Towards controllable test-time scaling
Paper: https://
arxiv.org/pdf/2506.00189
.pdf
…
MACHINE LEARNING
-
Control-R: Controllable Test-Time Scaling for AI Models
By
–
-
Cohere and Arc Institute Launch BioReason AI for Disease Prediction
By
–
Cohere and Arc Institute dropped BioReason, a reasoning AI for biology It fuses DNA models (Evo2) & LLMs (Qwen3) and uses step-by-step biological reasoning to predict disease pathways with 97% accuracy
-
High-Entropy Minority Tokens Improve LLM Reasoning via Reinforcement Learning
By
–
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
Paper: https://
arxiv.org/pdf/2506.01939
.pdf
…
Project： https://
shenzhi-wang.github.io/high-entropy-m
inority-tokens-rlvr/
… -
High-Entropy Tokens Drive LLM Reasoning in RLVR
By
–
It turns out you can drop 80% lowest-entropy tokens and still get good performance. This paper shows that only ~20% of tokens—those with the highest entropy—actually drive the reasoning process in LLMs trained with Reinforcement Learning with Verifiable Rewards (RLVR). The rest?
-
NVIDIA AI Blueprint Enhances Credit Card Fraud Detection Speed
By
–
Fraud detection just got smarter with #AI. At #Money2020EU, NVIDIA unveiled a new AI Blueprint designed to help financial firms detect credit card fraud faster and more precisely. Powered by accelerated computing and graph neural networks, and supported by NVIDIA partners, this
-
How Sebastian Ruder Made ULMFiT Paper Happen
By
–
How @seb_ruder made the ULMFiT paper happen (from 2018 http://
fast.ai student notes: https://
cedrickchee.gitbook.io/knowledge/cour
ses/fast.ai/deep-learning-part-2-cutting-edge-deep-learning-for-coders/2018-edition/lesson-10-transfer-learning-nlp
…) -
RLHF 101: Technical Tutorial on Reinforcement Learning from Human Feedback
By
–
RLHF 101 from ML@CMU A Technical Tutorial on Reinforcement Learning from Human Feedback "This blog dives into the full training pipeline of the RLHF framework. We will explore every stage — from data generation and reward model inference, to the final training of an
-
AlphaOne: Reasoning Models Thinking Slow and Fast
By
–
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time
Paper: https://
arxiv.org/pdf/2505.24863
.pdf
…
Project: https://
alphaone-project.github.io
Code: https://
github.com/ASTRAL-Group/A
lphaOne
… (coming soon) -
AlphaOne: Modulated Reasoning Optimizes LRM Performance
By
–
Large Reasoning Models (LRMs) often struggle to balance deep thinking with efficient generation. Prior methods use monotonic scaling (e.g. "more steps = better results") but lack flexibility. Enter AlphaOne: Modulated Reasoning at Test Time AlphaOne introduces a universal