·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Learning to Discretize: Diffusion-Based Adaptive Mesh with Spectral Guidance7h◆Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap7h◆ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams7h◆Mirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection7h◆The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context7h◆What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking7h◆Scalable Optimal Transport Algorithm for Network Alignment7h◆Evaluating Reliability in Machine Learning Models for Early Chronic Kidney Disease Prediction: A Systematic Review of Data Leakage and Predictor Stability7h◆Self-Evolving In-Context Learning for Direct Pilot-to-Beamformer Design in MU-MISO Systems7h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs7h◆AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration7h◆The Benjamini--Hochberg Procedure Can Fail to Control the FDR for Correlated Two-Sided Gaussian Tests7h◆Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel7h◆ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories7h◆MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization7h◆Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction7h◆Label-Decoupled Style Augmentation for Domain Generalization in Multi-Label Remote Sensing Scene Classification7h◆Physically Consistent Parameter Inference: Transparent Machine Learning Emulation in High Energy Physics and Cosmology7h◆NetForge RL: A Multi-Agent Simulation Environment for Cyber Defense with Durative Actions7h◆PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies7h◆Learning to Discretize: Diffusion-Based Adaptive Mesh with Spectral Guidance7h◆Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap7h◆ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams7h◆Mirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection7h◆The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context7h◆What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking7h◆Scalable Optimal Transport Algorithm for Network Alignment7h◆Evaluating Reliability in Machine Learning Models for Early Chronic Kidney Disease Prediction: A Systematic Review of Data Leakage and Predictor Stability7h◆Self-Evolving In-Context Learning for Direct Pilot-to-Beamformer Design in MU-MISO Systems7h◆Are we Merging the Right Models? Impact of Expert Training Duration on Model Merging for LLMs7h◆AutoTrace: From Patches to Triggers via Agentic Interprocedural Exploration7h◆The Benjamini--Hochberg Procedure Can Fail to Control the FDR for Correlated Two-Sided Gaussian Tests7h◆Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel7h◆ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories7h◆MAGE: Understanding Stability-Performance Trade-offs in Multi-component Prompt Optimization7h◆Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction7h◆Label-Decoupled Style Augmentation for Domain Generalization in Multi-Label Remote Sensing Scene Classification7h◆Physically Consistent Parameter Inference: Transparent Machine Learning Emulation in High Energy Physics and Cosmology7h◆NetForge RL: A Multi-Agent Simulation Environment for Cyber Defense with Durative Actions7h◆PRIME: Protein Representation via Physics-Informed Multiscale Equivariant Hierarchies7h◆
News/Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimization
arxiv
PublishedJuly 14, 2026 at 4:00 AM

Breaking the Quality--Intelligibility Trade-off in Streaming Target Speaker Extraction via Deep-Feature-Anchored Preference Optimization

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

arXiv:2607.10191v1 Announce Type: cross Abstract: Generative streaming models for Target Speaker Extraction (TSE) commonly exhibit a quality--intelligibility trade-off, wherein naive optimization for perceptual audio quality tends to degrade speech intelligibility, and conversely. We reveal that thi

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
arxivLearning to Discretize: Diffusion-Based Adaptive Mesh with Spectral Guidance7harxivToward Trustworthy Autonomous Science: A Two-Year Community Roadmap7harxivReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams7harxivMirror Horizon: Viable Path Entropy as a Measure of Bounded Reflection7h
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