/
Navigation
Chronicles
Browse all articles
Explore
Semantic exploration
Research
Entity momentum
Nexus
Correlations & relationships
Story Arc
Topic evolution
Drift Map
Semantic trajectory animation
Posts
Analysis & commentary
Pulse API
Tech news intelligence API
Browse
Entities
Companies, people, products, technologies
Domains
Browse by publication source
Handles
Browse by social media handle
Detection
Concept Search
Semantic similarity search
High Impact Stories
Top coverage by position
Sentiment Analysis
Positive/negative coverage
Anomaly Detection
Unusual coverage patterns
Analysis
Rivalry Report
Compare two entities head-to-head
Semantic Pivots
Narrative discontinuities
Crisis Response
Event recovery patterns
Connected
Search: /
Command: ⌘K
Embeddings: large
TEXXR

Chronicles

The story behind the story

days · browse · Enter similar · o open

Researchers from Apple and Columbia University released Ferret, an open source multimodal LLM that can recognize and describe any shape in an image, in October

VentureBeat Sharon Goldman

Context & Ripple Effects

Ferret marks an early Apple–Columbia research release focused on connecting language models to regions and shapes within images. Its open-source framing makes the work relevant beyond a single product or demonstration.

The work sits at the start of a visible progression in Apple’s multimodal research: later coverage moved from Ferret-UI’s understanding of mobile interface screens to the broader MM1 multimodal model series. That sequence matters because it shows visual grounding being developed into a more general model capability.

First-order effects

  • The release gives researchers and developers an inspectable open-source multimodal model for experiments involving image regions, shapes, and descriptions.
  • Apple and Columbia gain a public research reference point in multimodal AI, while Ferret’s capabilities become available for outside evaluation and follow-on work.

Second-order effects

  • The release creates a practical baseline for teams building visual-language systems, particularly where models must refer to parts of an image rather than only produce an overall caption.
  • Its research direction is reinforced by Apple’s subsequent UI-screen-focused Ferret-UI work, suggesting that visual grounding can be adapted to interface understanding as well as general image tasks.

Third-order effects

  • If this progression continues, multimodal models may increasingly be judged on whether they can ground responses in specific visual elements, not just identify broad image content.
  • Open research releases can accelerate common evaluation and experimentation around visual-language capabilities, even as companies differentiate through later model scale, deployment, and product integration.

The trend: Ferret is an early data point in the shift from text-first LLMs toward multimodal systems that can reason about and reference specific visual context.

Discussion

  • @carnage4life Dare Obasanjo on threads
    When I say Apple and Amazon should delete the code for Alexa and Siri then replace it with ChatGPT, this is what I'm talking about.
  • @oracleclyde @oracleclyde on threads
    Apple is going to integrate AI into their phones, and with their custom neural chips that excel at running machine learning, their new LLM will be integrated into your phone and will be local, not run on the cloud.  I expect that will satisfy a lot of security and privacy conscio…
  • @luokai @luokai on threads
    🧵2/2 They have proposed an inference cost model that coordinates with the behavior of flash memory usage, guiding optimization in two key areas: reducing the amount of data transferred from flash memory and reading data in larger, more continuous blocks. …
  • @ma.bali Marco Bambili on threads
    #news Apple has created a methodology for using Large Language Models (LLM) on iPhones.  OpenAI's ChatGPT or Google's Bard are models that use a lot of memory, a real challenge for mobile devices.  Apple researchers addressed the problem by leveraging flash memory. …
  • @luokai @luokai on threads
    While Apple may be behind in the race for LLM, they are certainly catching up.  Apple is sure to take a different path from other LLM companies, focusing on how to distill LLM and run it effectively on the iPhone. …
  • @jamiebykovbrett Jamie Bykov-Brett on threads
    Apple's dive into open source AI with ‘Apple Ferret’ is a game-changer!  🚀 In just a year, LLMs run on phones, opening a universe of possibilities.  Imagine AI decentralized right in your pocket—fewer data centers, more power to individuals.  It's no surprise giants like Google a…
  • @luokai @luokai on threads
    🧵3/5 In everyday life, possible applications of Ferret include: - Assisting visually impaired individuals: By accurately describing the location and shape of objects in the surrounding environment.  - Education and research: Helping students and researchers analyze image data, pr…
  • @cspenn Christopher Penn on threads
    “Apple is missing the boat on generative AI!” says the tech crowd.  MLX.  Dynamic caching in M3.  ANE everywhere.  Pooled memory in the SOC for CPU and GPU.  SLM instead of LLM.  And now this paper: https://arxiv.org/...  (h/t @sung.kim.mw ).  Do you see where Apple is going? …
  • @luokai @luokai on threads
    Apple is sure to make LLM a major upgrade for Siri on the iPhone.  Their recently announced method, LLM in a flash, is the best evidence.  LLM in a flash: Efficient Large Language Model Inference with Limited Memory.  Apple's approach is to store model parameters on flash memory …
  • @loganthorneloe Logan Thorneloe on x
    @_akhaliq @Gradio I'm glad Apple seems to be further ahead in ML than we thought
  • @rohanpaul_ai Rohan Paul on x
    @_akhaliq @Gradio ml-ferret can very well be Apple's answer to a multimodal LLM rivaling Google's Gemini
  • @8teapi @8teapi on x
    🍎 leaks the future Ready to have a touch and talk assistant on your phone? > you point to something on your phone, ask a question, your phone responds > you ask your phone something, it pulls up an image, and tells you the answer while circling things you should note [image]
  • @zhegan4 Zhe Gan on x
    🎁🎁 Ferret is a multimodal LLM that is able to refer and ground, and is now open-sourced. Find out our code and checkpoints below: https://github.com/.... Merry Christmas and Happy new year! work led by @XyouH @HaotianZhang4AI @yinfeiy
  • @openmedfuture Bart de Witte on x
    @DrTBehrens ... With the advancement of Edge AI technology becoming a reality, Microsoft's reported annual spending of $50 billion on data centers needs to be re-examined. This spending pattern may need to be adjusted as more AI compute moves from traditional data centers to edge…
  • @drtbehrens Dr. Tristan Behrens on x
    @sharongoldman ... could really change the AI landscape. If they would integrate LLMs on the operating systems level, it would start a new era of AI augmented human productivity and creativity!
  • @openmedfuture Bart de Witte on x
    I somehow missed this. @Apple joined the open source AI community in October. Ferret's introduction is a testament to Apple's commitment to impactful AI research, solidifying its place as a leader in the multimodal AI space. Way to go @Apple - ps: I'm looking forward to the day..…
  • @aaronp613 Aaron on x
    In a CNBC interview published yesterday with Apple's Johny Srouji and John Ternus, the interviewer asks: “Critics have been surprised that Apple appears to be falling behind when it comes to Al, how do you respond?” They both chuckle and say “Not too worried.” [image]
  • @erogol @erogol on x
    FERRET: Advanced Multimodal LLM for spatial image references (Apple) - Hybrid Regions with discrete and continuous features. - GRIT Dataset: 1.1M samples for spatial accuracy. - SOTA in spatial understanding - Open-vocabulary, adaptable to varied inputs https://arxiv.org/...
  • @dazzagreenwood @dazzagreenwood on x
    LLLMs (L = “local") are the killer app for catalyzing people caring about collecting their own personal data (as they create it and getting it back from others under CCPA and GDPR type access rights) so they can start getting amazing value for their own lives from their own data.
  • @_akhaliq @_akhaliq on x
    Apple releases Ferret Refer and Ground Anything Anywhere at Any Granularity @Gradio demo: https://github.com/... An End-to-End MLLM that Accept Any-Form Referring and Ground Anything in Response [image]