·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning1h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning1h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models1h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents1h◆Why Muon Outperforms Adam: A Curvature Perspective1h◆Archi: Agentic Operations at the CMS Experiment1h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies1h◆Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control and Management1h◆Tomography by Design: An Algebraic Approach to Low-Rank Quantum States1h◆A Unified Framework for Locality in Scalable MARL1h◆Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthromorphism, and Maxims1h◆Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues1h◆Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers1h◆Coherence Maximization Improves Pluralistic Alignment1h◆Efficient Reasoning on the Edge1h◆D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models1h◆Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions1h◆Sparse Bayesian Deep Functional Learning with Structured Region Selection1h◆UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding1h◆High-Quality Entity Segmentation and Grounding1h◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning1h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning1h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models1h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents1h◆Why Muon Outperforms Adam: A Curvature Perspective1h◆Archi: Agentic Operations at the CMS Experiment1h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies1h◆Toward Autonomous O-RAN: A Multi-Scale Agentic AI Framework for Real-Time Network Control and Management1h◆Tomography by Design: An Algebraic Approach to Low-Rank Quantum States1h◆A Unified Framework for Locality in Scalable MARL1h◆Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthromorphism, and Maxims1h◆Fine-grained Fragment Retrieval in Multi-modal Long-form Dialogues1h◆Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers1h◆Coherence Maximization Improves Pluralistic Alignment1h◆Efficient Reasoning on the Edge1h◆D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models1h◆Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions1h◆Sparse Bayesian Deep Functional Learning with Structured Region Selection1h◆UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding1h◆High-Quality Entity Segmentation and Grounding1h◆
News/Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
arxiv
PublishedMay 28, 2026 at 4:00 AM
—neutral

Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning

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

arXiv:2602.01745v2 Announce Type: replace-cross Abstract: Token-level reweighting is a simple yet effective mechanism for controlling supervised fine-tuning, but common indicators are largely one-dimensional: the ground-truth probability reflects downstream alignment, while token entropy reflects in

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
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning1harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning1harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models1harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents1h
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