·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
The Zoom hack that says, ‘Don’t record me’1h◆Agility Robotics plants its flag in Tesla’s backyard2h◆AI-driven memory crunch jolts India’s smartphone market2h◆TikTok is testing an AI likeness detection tool2h◆How Apple’s big lawsuit could disrupt OpenAI’s IPO plans4h◆Apple’s plot to crush OpenAI4h◆Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers6h◆Patreon stops asking AI bots not to scrape — and starts blocking them7h◆Apple’s lawsuit couldn’t come at a worse time for OpenAI8h◆Why the first GPU financiers are turning to inference chips in a $400 million deal10h◆A scorecard for the AI age12h◆The risk of weather data sabotage is rising13h◆The Steering Budget: Examples beat Knobs18h◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs18h◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination18h◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models18h◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation18h◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System18h◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets18h◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility18h◆The Zoom hack that says, ‘Don’t record me’1h◆Agility Robotics plants its flag in Tesla’s backyard2h◆AI-driven memory crunch jolts India’s smartphone market2h◆TikTok is testing an AI likeness detection tool2h◆How Apple’s big lawsuit could disrupt OpenAI’s IPO plans4h◆Apple’s plot to crush OpenAI4h◆Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers6h◆Patreon stops asking AI bots not to scrape — and starts blocking them7h◆Apple’s lawsuit couldn’t come at a worse time for OpenAI8h◆Why the first GPU financiers are turning to inference chips in a $400 million deal10h◆A scorecard for the AI age12h◆The risk of weather data sabotage is rising13h◆The Steering Budget: Examples beat Knobs18h◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs18h◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination18h◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models18h◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation18h◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System18h◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets18h◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility18h◆
News/Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics
arxiv
PublishedMay 22, 2026 at 4:00 AM
—neutral

Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2605.20441v1 Announce Type: cross Abstract: Transformers trained on modular arithmetic exhibit sharp transitions between memorization, generalization, and collapse. We show that weight decay acts as a scalar empirical control parameter for these regimes, and introduce two cheap online diagnost

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivThe Steering Budget: Examples beat Knobs18harxivPolestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs18harxivRxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination18harxivWhen a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models18h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews