·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Integrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications36m◆Lifelong Multi-Subsystem Pickup and Delivery with Buffer-Limited Handover Stations36m◆MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference36m◆Mobile Network Control with a World Model36m◆DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance Segmentation36m◆Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking36m◆Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning36m◆Time-Frequency Consistency Learning for Robust Speech Deepfake Detection36m◆Autonomous Discovery of Wireless Communications Algorithms36m◆FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches36m◆Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence36m◆Persona-as-Configuration: Generative Stakeholder Reporting for Agricultural Floods36m◆CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging36m◆ETAS: An Effect-Typed Language for Agent Systems36m◆BrainNext: A General-Purpose Self-Supervised Foundation Model for Brain MRI Analysis36m◆Feature Attribution-Based Explainability Analysis of Deep Learning Models in Predictive Process Monitoring36m◆Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models36m◆Medical Imaging Fusing Vision Transformer: Laryngeal Cancer Screening with Explanation36m◆ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video36m◆Vis2Reg: Visibility-Aware Landmark-Free Geometric 3D--2D Registration for Liver Laparoscopy36m◆Integrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications36m◆Lifelong Multi-Subsystem Pickup and Delivery with Buffer-Limited Handover Stations36m◆MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference36m◆Mobile Network Control with a World Model36m◆DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer for Unseen Object Instance Segmentation36m◆Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking36m◆Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning36m◆Time-Frequency Consistency Learning for Robust Speech Deepfake Detection36m◆Autonomous Discovery of Wireless Communications Algorithms36m◆FIFA World Cup 2026 as a Contamination-Free Benchmark for LLM Forecasting Agents: Four Models, a Bookmaker, and 104 Matches36m◆Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence36m◆Persona-as-Configuration: Generative Stakeholder Reporting for Agricultural Floods36m◆CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging36m◆ETAS: An Effect-Typed Language for Agent Systems36m◆BrainNext: A General-Purpose Self-Supervised Foundation Model for Brain MRI Analysis36m◆Feature Attribution-Based Explainability Analysis of Deep Learning Models in Predictive Process Monitoring36m◆Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models36m◆Medical Imaging Fusing Vision Transformer: Laryngeal Cancer Screening with Explanation36m◆ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video36m◆Vis2Reg: Visibility-Aware Landmark-Free Geometric 3D--2D Registration for Liver Laparoscopy36m◆
News/RELISH: LLM REgression with a Latent Iterative State Head
arxiv
PublishedJuly 13, 2026 at 4:00 AM
—neutral

RELISH: LLM REgression with a Latent Iterative State Head

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

arXiv:2604.01206v2 Announce Type: replace Abstract: We present RELISH (REgression with a Latent Iterative State Head), a novel, lightweight architecture designed for text regression with large language models. Rather than decoding numeric targets as text or aggregating multiple generated outputs, RE

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
arxivIntegrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications36marxivLifelong Multi-Subsystem Pickup and Delivery with Buffer-Limited Handover Stations36marxivMXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference36marxivMobile Network Control with a World Model36m
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