·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Pixi’s new iOS app turns text messages into interactive AR experiences1h◆Effects of sparsity and superposition on loss in simple autoencoders9h◆Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies9h◆Ensuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED9h◆Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising9h◆Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs9h◆Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning9h◆A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation9h◆LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection9h◆DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation9h◆SCAN: Enhance Time Series Anomaly Detection via Multi-Scale Neighborhood-Centered Clustering9h◆A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction9h◆UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation9h◆Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns9h◆SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning9h◆CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation9h◆MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design9h◆Sensory Restoration via Brain-Computer Interfaces: A Unified 2 x 2 Framework and Convergence Roadmap9h◆Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning9h◆Enhancing Pathological VLMs with Cross-scale Reasoning9h◆Pixi’s new iOS app turns text messages into interactive AR experiences1h◆Effects of sparsity and superposition on loss in simple autoencoders9h◆Bridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies9h◆Ensuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED9h◆Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising9h◆Controllable Quantum Memory Capacity in Quantum Reservoir Networks with Tunable partial-SWAPs9h◆Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning9h◆A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation9h◆LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection9h◆DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation9h◆SCAN: Enhance Time Series Anomaly Detection via Multi-Scale Neighborhood-Centered Clustering9h◆A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction9h◆UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation9h◆Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns9h◆SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning9h◆CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation9h◆MeEvo: Metacognitive Evolution Combined with Natural Evolution for Automatic Heuristic Design9h◆Sensory Restoration via Brain-Computer Interfaces: A Unified 2 x 2 Framework and Convergence Roadmap9h◆Calibrated Sampling-Free Uncertainty Estimation in Bayesian Deep Learning9h◆Enhancing Pathological VLMs with Cross-scale Reasoning9h◆
News/Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation
arxiv
PublishedJune 18, 2026 at 4:00 AM

Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation

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

arXiv:2606.19120v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a model on its own rollouts and uses a frozen copy to provide dense token-level targets conditioned on a reference target. This works well for LLM reasoning, but a direct extension to multimodal large language

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
arxivEffects of sparsity and superposition on loss in simple autoencoders9harxivBridging Data Gaps in Structural Fragility Modeling through Transfer Learning: Methodology and Case Studies9harxivEnsuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED9harxivPyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising9h
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