·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Figma announces new features to define how agents work on its platform3h◆CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing3h◆FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks3h◆Narrowing the Collaboration Gap, Probably3h◆Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine3h◆Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion3h◆LLMs program using Reusable and Composable Abstract Representations3h◆FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing3h◆Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents3h◆MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces3h◆New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents3h◆TIMERSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models3h◆What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization3h◆ProtModernBERT: Compute-Efficient Protein Language Modeling3h◆CAST: History-Adaptive Spectral Clipping for LLM Pretraining3h◆AVA-Encoder: Towards Agent-Native Video Representation Learning3h◆Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers3h◆Efficient contextual partial monitoring with general function approximation3h◆VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting3h◆When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models3h◆Figma announces new features to define how agents work on its platform3h◆CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing3h◆FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks3h◆Narrowing the Collaboration Gap, Probably3h◆Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine3h◆Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion3h◆LLMs program using Reusable and Composable Abstract Representations3h◆FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing3h◆Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents3h◆MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces3h◆New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents3h◆TIMERSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models3h◆What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization3h◆ProtModernBERT: Compute-Efficient Protein Language Modeling3h◆CAST: History-Adaptive Spectral Clipping for LLM Pretraining3h◆AVA-Encoder: Towards Agent-Native Video Representation Learning3h◆Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers3h◆Efficient contextual partial monitoring with general function approximation3h◆VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting3h◆When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models3h◆
News/Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens
arxiv
PublishedSeptember 16, 2026 at 4:00 AM

Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens

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

arXiv:2609.05111v2 Announce Type: replace Abstract: Supervised fine-tuning (SFT), few-shot in-context learning (ICL), KL-regularized RLHF/RLVR, and on-policy distillation are usually treated as distinct post-training paradigms. We develop a unified Bayesian perspective in which each is an instance o

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

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

Your email is used only to send The Bubble Brief. Privacy policy

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
arxivCSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing3harxivFireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks3harxivNarrowing the Collaboration Gap, Probably3harxivRiding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine3h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

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

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews