·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Neil Rimer thinks the AI money is coming back out2h◆The Steering Budget: Examples beat Knobs2h◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs2h◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination2h◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models2h◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation2h◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System2h◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets2h◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility2h◆Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation2h◆LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks2h◆OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios2h◆When AI Blurs the Boundaries of Contribution: An Empirical Study of Authorship Calibration2h◆Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents2h◆Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors2h◆ANet Patu-1: The Value of Connection in the Agent Network2h◆Automatically Evolving Prompt Guidelines for Task-Specific Optimization2h◆MAPS: Modeling Co-Existing Subjective Perspectives and Shared Meaning in Multi-Agent Cognitive Dialogue2h◆Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation2h◆Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions2h◆Neil Rimer thinks the AI money is coming back out2h◆The Steering Budget: Examples beat Knobs2h◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs2h◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination2h◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models2h◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation2h◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System2h◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets2h◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility2h◆Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation2h◆LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks2h◆OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios2h◆When AI Blurs the Boundaries of Contribution: An Empirical Study of Authorship Calibration2h◆Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents2h◆Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors2h◆ANet Patu-1: The Value of Connection in the Agent Network2h◆Automatically Evolving Prompt Guidelines for Task-Specific Optimization2h◆MAPS: Modeling Co-Existing Subjective Perspectives and Shared Meaning in Multi-Agent Cognitive Dialogue2h◆Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation2h◆Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions2h◆
News/When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech
arxiv
PublishedJuly 16, 2026 at 4:00 AM
—neutral

When Audio Separation Hurts Zero-Shot ASR: Evaluating SAM-Audio with Whisper on Bengali and English Speech

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

arXiv:2603.04710v2 Announce Type: replace-cross Abstract: Recent advances in automatic speech recognition (ASR) and speech enhancement have strengthened the common belief that cleaner audio should lead to more accurate transcription. In this work, we examine whether this assumption holds for modern

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
arxivThe Steering Budget: Examples beat Knobs2harxivPolestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs2harxivRxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination2harxivWhen a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models2h
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