·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents49m◆SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks49m◆Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence49m◆Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs49m◆Test-Time Training with Next-Token Prediction49m◆Randomized YaRN Improves Length Generalization for Long-Context Reasoning49m◆SHERLOC: Structured Diagnostic Localization for Code Repair Agents49m◆Syntactic Belief Update as the Driver of Garden Path Processing Difficulty49m◆Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models49m◆Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data49m◆Tastes without distinction: silicon samples and the synthetic construction of tastes49m◆When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs49m◆Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance49m◆MemDefrag: Latent Memory Defragmentation for Large Language Models49m◆WikiSTAR: A System for Shedding Light on the Hidden History of Scientific Wikipedia Articles49m◆Notes to Self: Can LLMs Benefit from Experiential Abstractions?49m◆EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation49m◆DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues49m◆ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification49m◆Dynamically Allocating Evaluation Effort for Model Ranking49m◆Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents49m◆SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks49m◆Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence49m◆Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs49m◆Test-Time Training with Next-Token Prediction49m◆Randomized YaRN Improves Length Generalization for Long-Context Reasoning49m◆SHERLOC: Structured Diagnostic Localization for Code Repair Agents49m◆Syntactic Belief Update as the Driver of Garden Path Processing Difficulty49m◆Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language Models49m◆Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data49m◆Tastes without distinction: silicon samples and the synthetic construction of tastes49m◆When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs49m◆Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance49m◆MemDefrag: Latent Memory Defragmentation for Large Language Models49m◆WikiSTAR: A System for Shedding Light on the Hidden History of Scientific Wikipedia Articles49m◆Notes to Self: Can LLMs Benefit from Experiential Abstractions?49m◆EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation49m◆DuplexGen: Adaptive Synthesis of Human-AI Turn-Taking Dialogues49m◆ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification49m◆Dynamically Allocating Evaluation Effort for Model Ranking49m◆
News/Efficient Long-Horizon Learning for Learned Optimization
arxiv
PublishedJuly 10, 2026 at 4:00 AM
▲bullish

Efficient Long-Horizon Learning for Learned Optimization

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

arXiv:2607.06772v2 Announce Type: replace Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distribution of tasks. While recent work has greatly advanced the architectural design and inductive bi

Models mentioned
03
  • 01AI organization logo
    gpt2
    gpt2
  • 02google logo
    vit-base-patch16-224-in21k
    google/vit-base-patch16-224-in21k
  • 03microsoft logo
    resnet-50
    microsoft/resnet-50
Compare these 3 models→
Related
05
  • arxivJul 31
    NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus
  • arxivJun 2
    How Much Orthogonalization Does Muon Need?
  • arxivMay 1
    Making Logic a First-Class Citizen in Generative ML for Networking
  • arxivApr 20
    Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
  • arxivApr 10
    Information as Structural Alignment: A Dynamical Theory of Continual Learning
Stay posted· Newsletter

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

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

Discussion
Mentioned models
06
  • 01
    Adam
  • 02
    Muon
  • 03
    gpt2
    gpt2
  • 04
    gpt2
    gpt2
  • 05
    vit-base-patch16-224-in21k
    google/vit-base-patch16-224-in21k
  • 06
    resnet-50
    microsoft/resnet-50
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#optimization#meta-learning#language-modeling#image-classification
Mentioned companies
01
Meta

No replies yet. Be first.

Mentioned models
06
  • 01
    Adam
  • 02
    Muon
  • 03
    gpt2
    gpt2
  • 04
    gpt2
    gpt2
  • 05
    vit-base-patch16-224-in21k
    google/vit-base-patch16-224-in21k
  • 06
    resnet-50
    microsoft/resnet-50
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#optimization#meta-learning#language-modeling#image-classification
Mentioned companies
01
Meta

Related coverage

More from ARXIV
arxivAre Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents49marxivSciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks49marxivBeyond NL2Code: A Structured Survey of Multimodal Code Intelligence49marxivWho Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs49m
The Bubble Brief
WEEKLY

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

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

Originally published on arxiv ↗
HomeModelsNews