·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations3h◆Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence3h◆SimOPD: Relational Knowledge Transfer for On-Policy Distillation3h◆Generative Policy Improvement from Observational Data3h◆SkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents3h◆GEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs3h◆OwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning3h◆Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability3h◆Hard Instances on Demand3h◆ARBOR: Locating Reasoning Failures in Long Chains of Thought through Reasoning State Tracking3h◆Aligning Language Models Towards Counterfactual Invariance3h◆Language Models Learn to Improve Language Models3h◆TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models3h◆STAIF: A Stage-wise Optimization for Complex Instruction Following3h◆Q-Reflector: Learning GUI Action Reflection with Generated Conditions3h◆When Should Agents Check External State? Budgeting Observations for Stored Intentions3h◆RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees3h◆MultiWorldBench: Do Independently Controlled Views Describe One Shared World?3h◆Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration3h◆Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift3h◆GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations3h◆Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence3h◆SimOPD: Relational Knowledge Transfer for On-Policy Distillation3h◆Generative Policy Improvement from Observational Data3h◆SkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents3h◆GEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs3h◆OwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning3h◆Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability3h◆Hard Instances on Demand3h◆ARBOR: Locating Reasoning Failures in Long Chains of Thought through Reasoning State Tracking3h◆Aligning Language Models Towards Counterfactual Invariance3h◆Language Models Learn to Improve Language Models3h◆TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models3h◆STAIF: A Stage-wise Optimization for Complex Instruction Following3h◆Q-Reflector: Learning GUI Action Reflection with Generated Conditions3h◆When Should Agents Check External State? Budgeting Observations for Stored Intentions3h◆RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees3h◆MultiWorldBench: Do Independently Controlled Views Describe One Shared World?3h◆Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration3h◆Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift3h◆
News/The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline
arxiv
PublishedJuly 16, 2026 at 4:00 AM
—neutral

The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline

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

arXiv:2607.12079v1 Announce Type: new Abstract: Decoding continuous language from fMRI signals remains a core challenge in non-invasive brain-computer interface research. We present two complementary investigations. First, we improve the Huth et al. ridge regression encoding pipeline through expande

Models mentioned
02
  • 01AI organization logo
    gpt2-medium
    gpt2-medium
  • 02decapoda-research logo
    llama-3.2-1b
    decapoda-research/llama-3.2-1b
Compare these 2 models→
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
Mentioned models
03
  • 01
    GPT-1
  • 02
    gpt2-medium
    gpt2-medium
  • 03
    llama-3.2-1b
    decapoda-research/llama-3.2-1b
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#nlp#brain-computer-interfaces#neural-decoding#evaluation

No replies yet. Be first.

Mentioned models
03
  • 01
    GPT-1
  • 02
    gpt2-medium
    gpt2-medium
  • 03
    llama-3.2-1b
    decapoda-research/llama-3.2-1b
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#nlp#brain-computer-interfaces#neural-decoding#evaluation

Related coverage

More from ARXIV
arxivGlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations3harxivAlgorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence3harxivSimOPD: Relational Knowledge Transfer for On-Policy Distillation3harxivGenerative Policy Improvement from Observational Data3h
The Bubble Brief
MON · WED · FRI

Read nlp 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