·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Perplexity trusts GPT-6 Astra with end-to-end systems-1953m◆Trump is giving data centers a pass to pollute45m◆OpenAI just wants to win4h◆TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents11h◆Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation11h◆SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models11h◆Towards a Deterministic Math Solver for Clinical Language Models11h◆Demystifying the Privacy-Utility Trade-off in LLM Interactions11h◆Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks11h◆Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language11h◆Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks11h◆Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge11h◆The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures11h◆Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows11h◆Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents11h◆DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat11h◆Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning11h◆Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration11h◆DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks11h◆Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks11h◆Perplexity trusts GPT-6 Astra with end-to-end systems-1953m◆Trump is giving data centers a pass to pollute45m◆OpenAI just wants to win4h◆TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents11h◆Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation11h◆SPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models11h◆Towards a Deterministic Math Solver for Clinical Language Models11h◆Demystifying the Privacy-Utility Trade-off in LLM Interactions11h◆Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks11h◆Automating Quadratic Unconstrained Binary Optimization (QUBO) Formulation Generation from Natural Language11h◆Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks11h◆Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge11h◆The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures11h◆Decoupling Readiness from Release for Tail-Aware Scheduling of Agentic LLM Workflows11h◆Grounding Agent Memory: Environment-Probing Curation for Enterprise Agents11h◆DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat11h◆Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning11h◆Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration11h◆DeFiFusion: Combining Transaction Events with Smart Contracts to Detect Price Manipulation Attacks11h◆Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks11h◆
News/X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
arxiv
PublishedSeptember 12, 2026 at 4:00 AM
—neutral

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

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

arXiv:2609.11412v1 Announce Type: cross Abstract: Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks perturbs the embeddings consumed by the decoder and can cause deletion and premature end-of-sequence errors. We introduce X-AuT, a pr

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
arxivTeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents11harxivNatural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation11harxivSPECTRA: Band-Routed Embedding and Stage-Wise LoRA for Cross-Sensor Fine-Tuning of Geospatial Foundation Models11harxivTowards a Deterministic Math Solver for Clinical Language Models11h
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