·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
NVIDIA Kumo Forecast Combines Pretrained Time-Series Representations with Historical Pattern Retrieval and Interpretability1h◆Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories2h◆An AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response9h◆Learning Transferable Latent User Preferences for Human-Aligned Decision Making9h◆Repair the Core, Not the Symptom: Planning-Graph Repair for Long-Horizon Agents9h◆IndustryForge-27B: A Domain-Enhanced Multimodal Foundation Model for Industrial CAD9h◆Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value9h◆PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models9h◆WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations9h◆When Synthetic Speech Is All You Have: Better Call GRPO9h◆Reducing belief in conspiracy theories as they unfold using large language models9h◆Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors9h◆EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization9h◆Composing What Each Teacher Learned: Delta Distillation for Multi-Teacher On-Policy Learning9h◆CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding9h◆WeGR: Towards Unified Generative Retrieval via Behavior-aware Tokenization and Preference Alignment9h◆StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions9h◆Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents9h◆Secure Agentic Coding through Counterexample-Grounded Feedback9h◆Policy Search in Code Space for Multi-Agent Pathfinding9h◆NVIDIA Kumo Forecast Combines Pretrained Time-Series Representations with Historical Pattern Retrieval and Interpretability1h◆Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories2h◆An AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response9h◆Learning Transferable Latent User Preferences for Human-Aligned Decision Making9h◆Repair the Core, Not the Symptom: Planning-Graph Repair for Long-Horizon Agents9h◆IndustryForge-27B: A Domain-Enhanced Multimodal Foundation Model for Industrial CAD9h◆Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value9h◆PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models9h◆WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations9h◆When Synthetic Speech Is All You Have: Better Call GRPO9h◆Reducing belief in conspiracy theories as they unfold using large language models9h◆Harnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors9h◆EDISCO: Equivariant DIScrete Diffusion for Euclidean Combinatorial Optimization9h◆Composing What Each Teacher Learned: Delta Distillation for Multi-Teacher On-Policy Learning9h◆CRISP: Fixing Flying Pixels in Latent LiDAR Generation via Diffusion Decoding9h◆WeGR: Towards Unified Generative Retrieval via Behavior-aware Tokenization and Preference Alignment9h◆StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions9h◆Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents9h◆Secure Agentic Coding through Counterexample-Grounded Feedback9h◆Policy Search in Code Space for Multi-Agent Pathfinding9h◆
News/model/gemma-4-26B-A4B

gemma-4-26B-A4B news

19 articles mentioning gemma-4-26B-A4B

arxivSep 29

Words Speak Louder Than Order: A Behavioral Evaluation of Gemma 4

arXiv:2609.30716v1 Announce Type: cross Abstract: When a language model receives two conflicting documents as input, how does it decide which one to prioritize? Does it rely on how the sources are framed or the presentation order of the documents? We evaluated this behavior on Google's pre-trained G

arxivSep 7

Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3

arXiv:2609.04808v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavior, but it remains unclear whether a feature found in one language context plays the same causal role when processing prompts in another language. We st

arxivJul 27

Gemma 4 Technical Report

arXiv:2607.02770v2 Announce Type: replace Abstract: We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures,

arxivJul 24

Do Active SAE Feature Planes Carry More Holonomy? A Preregistered Reversal in Gemma

arXiv:2607.20522v1 Announce Type: new Abstract: This paper tests whether holonomy concentrates on active sparse-autoencoder (SAE) feature planes in Gemma 2 2B, a concrete operationalization of the broader semantic-concentration prediction. Holonomy is measured at the final-token layer-12 to layer-13

huggingfaceJul 1

Hugging Face and Cerebras bring Gemma 4 to real-time voice AI

arxivJun 3

Fine-Tuning and Serving Gemma 4 31B on Google Cloud TPU: A Technical Comparison with GPU Baselines

arXiv:2605.25645v2 Announce Type: replace-cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison of TPU and GPU platforms for large language model adaptation. Using LoRA on a Google TPU v5

arxivMay 20

Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B

arXiv:2605.00333v2 Announce Type: replace-cross Abstract: Frozen Gemma 4 31B weights pretrained exclusively on text, unmodified, transfer through a thin trainable interface to non-text modalities the substrate has never processed. On the L24--L29 slice (192 attention heads), an English-text TxtCopy

arxivMay 7

PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation

arXiv:2605.05159v1 Announce Type: new Abstract: We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fine-tunes separate Gemma~3 models (12B and 27B parameters) per language using Low-Rank Adaptation (LoR

arxivApr 29

Distilling Self-Consistency into Verbal Confidence: A Pre-Registered Negative Result and Post-Hoc Rescue on Gemma 3 4B

arXiv:2604.24070v1 Announce Type: cross Abstract: Small instruct-tuned LLMs produce degenerate verbal confidence under minimal elicitation: ceiling rates above 95%, near-chance Type-2 AUROC, and Invalid validity profiles. We test whether confidence-conditioned supervised fine-tuning (CSFT) with self

huggingfaceApr 22

Gemma 4 VLA Demo on Jetson Orin Nano Super

arxivApr 11

Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma

arXiv:2604.07490v1 Announce Type: new Abstract: Representation learning for geospatial and spatio-temporal data plays a critical role in enabling general-purpose geospatial intelligence. Recent geospatial foundation models, such as the Population Dynamics Foundation Model (PDFM), encode complex popu

arxivApr 9

Gemma 4, Phi-4, and Qwen3: Accuracy-Efficiency Tradeoffs in Dense and MoE Reasoning Language Models

arXiv:2604.07035v1 Announce Type: new Abstract: Mixture-of-experts (MoE) language models are often expected to offer better quality-efficiency tradeoffs than dense models because only a subset of parameters is activated per token, but the practical value of that advantage depends on end-to-end behav

huggingfaceApr 2

Welcome Gemma 4: Frontier multimodal intelligence on device

huggingfaceJun 26

Gemma 3n fully available in the open-source ecosystem!

huggingfaceMar 12

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

huggingfaceJul 31

Google releases Gemma 2 2B, ShieldGemma and Gemma Scope

huggingfaceJun 27

Welcome Gemma 2 - Google’s new open LLM

huggingfaceFeb 23

Fine-Tuning Gemma Models in Hugging Face

huggingfaceFeb 21

Welcome Gemma - Google’s new open LLM

PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews