7. AlphaOne Introduces a universal framework, α1, for modulating the reasoning progress of large reasoning models (LRMs) during inference. Rather than relying on rigid or automatic schedules, α1 explicitly controls when and how models engage in “slow thinking” using a tunable
RESEARCH
-

Common Pile v0.1: 8TB Open Licensed Text Dataset for LLM Training
By
–
8. Common Pile v0.1 The Common Pile v0.1 is an 8TB dataset of openly licensed text designed for LLM pretraining, addressing legal and ethical concerns of unlicensed data use.
-
Self-Challenging Language Model Agents for Multi-Turn Tool Use
By
–
6. Self-Challenging Language Model Agents Proposes a novel self-improvement method for multi-turn tool-use LLM agents, called the Self-Challenging Agent (SCA). It trains LLMs entirely from tasks they generate themselves, avoiding the need for human-annotated tasks or
-

Evaluating LLM Knowledge and Reasoning with KI InfoGain
By
–
3. Knowledge or Reasoning Introduces a fine-grained evaluation framework to dissect LLM thinking into two components: knowledge correctness and reasoning informativeness, measured via Knowledge Index (KI) and Information Gain (InfoGain), respectively.
-

OpenThoughts3: SFT Data Curation for Open-Source Reasoning
By
–
4. Open Thoughts This paper presents OpenThoughts3, a systematic recipe for curating supervised fine-tuning (SFT) data that advances the performance of open-source reasoning models.
-
Information-Theoretic Framework for LLM Semantic Knowledge Organization
By
–
2. From Tokens to Thoughts This paper introduces an information-theoretic framework to examine whether LLMs organize semantic knowledge like humans, balancing compression and meaning.
-
AI Independently Passes Peer Review at Top Scientific Conference
By
–
A new impressive moment for generative AI AI directed and wrote a research paper accepted at a tier-1 scientific conference the first AI system to independently pass peer review at an A* scientific conference¹—the highest bar for scientific work in the field.
-
Quantum and Classical Computing: Coexistence and Future Balance
By
–
Quantum vs Classical Computing: Understanding Tomorrow’s Tech Balance Quantum isn’t replacing classical computing — it’s complementing it. Learn how both models will coexist and power the future together. Read more https://
bernardmarr.com/quantum-vs-cla
ssical-computing-understanding-tomorrows-tech-balance/
… #QuantumComputing #TechBalance -
Large Reasoning Models Show Inconsistent Effort Across Problem Complexity
By
–
Despite the catchy title, that's not what the paper says. It says "[large reasoning models] reasoning effort increases with problem complexity up to a point, then declines…they reason inconsistently across puzzles" Is human reasoning effort ever inconsistent?
-
GRU Neural Networks Rise in Deep Learning Research
By
–
I also didn't realise you were on this paper Rupesh. So cool! How do you feel about the rise of GRU and friends nowadays? https://
arxiv.org/abs/1503.04069