·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Meta rolls out a new AI creator assistant on Facebook41m◆What to expect from WWDC 2026: Siri’s highly anticipated revamp and Apple Intelligence updates42m◆Is Silicon Valley ready to put robots in people’s homes? Hello Robot is.2h◆TSMC struggles to keep up with AI demand: ‘We can only support so much’2h◆Apple touts $1.4 trillion in App Store billings and sales, 90% without a commission3h◆Elon Musk is steamrolling Wall Street to become a trillionaire3h◆How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent4h◆Let us filter AI slop, you cowards4h◆EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios4h◆AI leaders call for tougher protections against AI-aided bioweapons5h◆How Endava is redesigning software delivery around AI agents5h◆Task-Seeded Synthetic Q&A Generation for Nemotron Pretraining5h◆How courts are coping with a flood of AI-generated lawsuits6h◆Amazon develops a warehouse robot that workers can speak to7h◆Dreaming: Better memory for a more helpful ChatGPT8h◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning13h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning13h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models13h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents13h◆Why Muon Outperforms Adam: A Curvature Perspective13h◆Meta rolls out a new AI creator assistant on Facebook41m◆What to expect from WWDC 2026: Siri’s highly anticipated revamp and Apple Intelligence updates42m◆Is Silicon Valley ready to put robots in people’s homes? Hello Robot is.2h◆TSMC struggles to keep up with AI demand: ‘We can only support so much’2h◆Apple touts $1.4 trillion in App Store billings and sales, 90% without a commission3h◆Elon Musk is steamrolling Wall Street to become a trillionaire3h◆How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent4h◆Let us filter AI slop, you cowards4h◆EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios4h◆AI leaders call for tougher protections against AI-aided bioweapons5h◆How Endava is redesigning software delivery around AI agents5h◆Task-Seeded Synthetic Q&A Generation for Nemotron Pretraining5h◆How courts are coping with a flood of AI-generated lawsuits6h◆Amazon develops a warehouse robot that workers can speak to7h◆Dreaming: Better memory for a more helpful ChatGPT8h◆SFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning13h◆Optical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning13h◆Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models13h◆Temporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents13h◆Why Muon Outperforms Adam: A Curvature Perspective13h◆
News/GazeQwen: Lightweight Gaze-Conditioned LLM Modulation for Streaming Video Understanding
arxiv
PublishedMarch 30, 2026 at 4:00 AM

GazeQwen: Lightweight Gaze-Conditioned LLM Modulation for Streaming Video Understanding

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

arXiv:2603.25841v1 Announce Type: cross Abstract: Current multimodal large language models (MLLMs) cannot effectively utilize eye-gaze information for video understanding, even when gaze cues are supplied via visual overlays or text descriptions. We introduce GazeQwen, a parameter efficient approach

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
arxivSFMambaNet: Spectral-Frequency Enhanced Selective State Space Model for Correspondence Pruning13harxivOptical-Guided Neural Collapse for SAR Few-Shot Class Incremental Learning13harxivDynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models13harxivTemporal Order Matters for Agentic Memory: Segment Trees for Long-Horizon Agents13h
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