·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
XDOF, just three months out of stealth, is in talks for a Series B at a $1.2B valuation5h◆OpenAI’s rogue agents keep escaping, with no formal process to investigate them5h◆AI compute provider Nscale is looking for $3.5B in pre-IPO financing7h◆Architecting memory and storage in the AI era10h◆Roland is getting into generative AI music with Melody Flip10h◆What will Apple’s John Ternus era look like?11h◆Another swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge12h◆Microsoft says virtually nobody was grabbing NYT articles through its chatbot12h◆Apple’s Ternus era begins as Nvidia bets on the whole AI stack12h◆Google’s Gemini Spark can now manage your Google Photos library13h◆Less than 24 hours to apply for your TechCrunch Disrupt 2026 Side Event14h◆Rogue OpenAI agents appear to have organized another attack using a German wiki15h◆Instagram’s AI detection is a mess (again)16h◆Why AI food looks like that17h◆Microsoft’s Project Zenith is a ‘distraction-free Windows experience’ for developers17h◆Sam Altman apologizes for ‘messy’ GPT-6 Astra rollout that’s locked out paying users17h◆This NAS company wants to run your local smart home18h◆Data from drones in Ukraine is fueling a new Wild West marketplace19h◆The sameness problem behind those unappetizing AI-generated menus1d◆CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning1d◆XDOF, just three months out of stealth, is in talks for a Series B at a $1.2B valuation5h◆OpenAI’s rogue agents keep escaping, with no formal process to investigate them5h◆AI compute provider Nscale is looking for $3.5B in pre-IPO financing7h◆Architecting memory and storage in the AI era10h◆Roland is getting into generative AI music with Melody Flip10h◆What will Apple’s John Ternus era look like?11h◆Another swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge12h◆Microsoft says virtually nobody was grabbing NYT articles through its chatbot12h◆Apple’s Ternus era begins as Nvidia bets on the whole AI stack12h◆Google’s Gemini Spark can now manage your Google Photos library13h◆Less than 24 hours to apply for your TechCrunch Disrupt 2026 Side Event14h◆Rogue OpenAI agents appear to have organized another attack using a German wiki15h◆Instagram’s AI detection is a mess (again)16h◆Why AI food looks like that17h◆Microsoft’s Project Zenith is a ‘distraction-free Windows experience’ for developers17h◆Sam Altman apologizes for ‘messy’ GPT-6 Astra rollout that’s locked out paying users17h◆This NAS company wants to run your local smart home18h◆Data from drones in Ukraine is fueling a new Wild West marketplace19h◆The sameness problem behind those unappetizing AI-generated menus1d◆CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning1d◆
News/Do VLMs Share Safety Neurons Across Modalities?
arxiv
PublishedSeptember 1, 2026 at 4:00 AM

Do VLMs Share Safety Neurons Across Modalities?

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

arXiv:2608.30750v1 Announce Type: new Abstract: Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content in text. While prior work characterizes these jailbreaks empirically or at the representation level, ho

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
arxivCulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning1d
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