·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Thousand Token Wood: shipping a multi-agent economy on a 3B model4h◆Startup Battlefield 200 applications officially close in 3 days6h◆Google will pay SpaceX $920M per month for compute7h◆The most interesting startups right now want to get you off your phone9h◆This is your laptop… on AI9h◆New York lawmakers pass one-year ban on new data centers10h◆The token bill comes due: Inside the industry scramble to manage AI’s runaway costs11h◆The latest AI news we announced in May 202611h◆The ‘together tech’ wave might be the most intriguing startup bet of 202612h◆This AI startup says it can tell if a script will make a hit film12h◆AirTrunk commits $30B to build 5GW of AI data centers in India13h◆The Meta hack shows there’s more to AI security than Mythos17h◆Mira Murati steps back into the spotlight, carefully21h◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning22h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning22h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models22h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents22h◆Why Muon Outperforms Adam: A Curvature Perspective22h◆Vision Hopfield Memory Networks22h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies22h◆Thousand Token Wood: shipping a multi-agent economy on a 3B model4h◆Startup Battlefield 200 applications officially close in 3 days6h◆Google will pay SpaceX $920M per month for compute7h◆The most interesting startups right now want to get you off your phone9h◆This is your laptop… on AI9h◆New York lawmakers pass one-year ban on new data centers10h◆The token bill comes due: Inside the industry scramble to manage AI’s runaway costs11h◆The latest AI news we announced in May 202611h◆The ‘together tech’ wave might be the most intriguing startup bet of 202612h◆This AI startup says it can tell if a script will make a hit film12h◆AirTrunk commits $30B to build 5GW of AI data centers in India13h◆The Meta hack shows there’s more to AI security than Mythos17h◆Mira Murati steps back into the spotlight, carefully21h◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning22h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning22h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models22h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents22h◆Why Muon Outperforms Adam: A Curvature Perspective22h◆Vision Hopfield Memory Networks22h◆Provably Auditable and Safe LLM Agents from Human-Authored Ontologies22h◆
Tag

#calibration

5 articles tagged #calibration

arxiv2d agobullish

Before Fusion, Ask What to Keep: Contextual Calibration of Multimodal Signals

arXiv:2606.02679v1 Announce Type: new Abstract: Multimodal systems often benefit from combining information across language, sound, and visual streams, but this benefit is not guaranteed. A modality that is useful for one input may become distracting for another, and local feature responses within t

#multimodal#fusion#calibrationRead on arxiv →
arxivMay 29

Calibrating Generative Models to Distributional Constraints

arXiv:2510.10020v4 Announce Type: replace-cross Abstract: Generative models frequently suffer miscalibration, wherein statistics of the sampling distribution, such as the fraction of generations in a given class, deviate from desired values. We frame calibration as a constrained optimization problem

#machine-learning#calibration#optimizationRead on arxiv →
arxivMay 22

Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift

arXiv:2605.21552v1 Announce Type: new Abstract: Confidence calibration for classification models is vital in safety-critical decision-making scenarios and has received extensive attention. General confidence calibration methods assume training and test data are independent and identically distribute

#calibration#covariate-shift#domain-adaptationRead on arxiv →
arxivMay 4

Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification

arXiv:2605.00326v1 Announce Type: new Abstract: Single-prompt first-token probabilities from zero-shot vision-language model (VLM) safety classifiers are treated as decision scores, but we show they are unreliable under semantically equivalent prompt reformulation: even when the binary label is cons

ZE1 model#safety#benchmark#calibrationRead on arxiv →
arxivMay 1

Geometry-Calibrated Conformal Abstention for Language Models

arXiv:2604.27914v1 Announce Type: new Abstract: When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about the answer. Retraining models to reward admitting ignorance can lead to

#conformal-prediction#language-models#calibrationRead on arxiv →
HomeModelsNews