·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Apple Intelligence approved for launch in China with Alibaba and Baidu51m◆Claude can now use your 1Password credentials for you1h◆Google ordered to open Android and Search to rivals in Europe2h◆Newer Models, Same Advantage2h◆Computer cops3h◆Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling10h◆SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests10h◆MASPRM: Multi-Agent System Process Reward Model10h◆Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization10h◆A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping10h◆FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy10h◆Cortical-SSM: A Deep State Space Model for Motor Imagery Decoding from EEG Signals10h◆Avoiding unsafe sets when training with Langevin Dynamics10h◆Set-shifting Behavioral Test for Harnessed Agents10h◆AIMO Interpretability Challenge10h◆The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI10h◆The Refusal Residue: When Probes Catch Alignment Faking and When They Don't10h◆Beyond the $d^{2.5}$-mixing bound for Dikin walks on polytopes10h◆ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL10h◆Post-Training Pruning for Diffusion Transformers10h◆Apple Intelligence approved for launch in China with Alibaba and Baidu51m◆Claude can now use your 1Password credentials for you1h◆Google ordered to open Android and Search to rivals in Europe2h◆Newer Models, Same Advantage2h◆Computer cops3h◆Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling10h◆SemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests10h◆MASPRM: Multi-Agent System Process Reward Model10h◆Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization10h◆A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping10h◆FastCentNN: Accelerating Centroid Neural Network with Entropy Proxy10h◆Cortical-SSM: A Deep State Space Model for Motor Imagery Decoding from EEG Signals10h◆Avoiding unsafe sets when training with Langevin Dynamics10h◆Set-shifting Behavioral Test for Harnessed Agents10h◆AIMO Interpretability Challenge10h◆The Perplexity Trap: When Patent Law Makes Human Writing Look Like AI10h◆The Refusal Residue: When Probes Catch Alignment Faking and When They Don't10h◆Beyond the $d^{2.5}$-mixing bound for Dikin walks on polytopes10h◆ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL10h◆Post-Training Pruning for Diffusion Transformers10h◆
News/On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR
arxiv
PublishedMarch 31, 2026 at 4:00 AM

On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR

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

arXiv:2603.27981v1 Announce Type: new Abstract: Automatic speech recognition (ASR) has advanced rapidly in recent years, driven by large-scale pretrained models and end-to-end architectures such as SLAM-ASR. A key component of SLAM-ASR systems is the Whisper speech encoder, which provides robust aco

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
arxivMulti-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling10harxivSemaDiff: Identifying Semantic-Changing Commits with Generated Code and Tests10harxivMASPRM: Multi-Agent System Process Reward Model10harxivDelving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization10h
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