AI · អត្ថបទ
MIT and IBM Team Probes Gaps in Multimodal AI Understanding
MIT News ·

មើលត្រួសៗ
MIT and IBM researchers are studying where today's multimodal AI models fall short, even when they handle text, images, and sound fluently. Their team, co-led by MIT's Jim Glass, builds new benchmarks and training methods that need less labeled data. This Q&A walks through how the project started and how it has evolved.
ចំណុចសំខាន់ៗ
- The team found that big multimodal models often look more capable than they really are.
- They build benchmarks to test these weaknesses and techniques that work with limited labeled data.
- The project began by teaching models to match sounds and pictures without any text.
- Later work extended this to general audio and video, including masking and reconstruction training.
ហេតុអ្វីវាសំខាន់
Multimodal AI is spreading into everyday tools, so knowing its real limits matters for how much people can trust it.
ប្រភពដើម
Q&A: Enabling more human-like interactions and understanding in multimodal foundation models
MIT News · Nov 21, 06:00 KST
Read on MIT News ↗AI summarized the original article. Check the original for accuracy. Copyright belongs to MIT News.
បន្ថែមពីវិស័យនេះ
- Designers Say Ssense's Website Shows Their Clothes Inaccurately
Designer Reese Cooper noticed his RCOS puffer coat looked distorted on the luxury retailer Ssense's website, with a chest hook drawn far too large. Ssense said some site images came from a "virtual try-on" program, though it would not say whether that program uses AI.
The New York Times · Nov 21, 06:16 KST - Korean Firms Build Three-Way AI Push: Anthropic Stake, HBM Chips, Claude Rollout
Korean companies are expanding their roles in the global AI market around Anthropic's IPO. SK Telecom earned large paper gains from an early investment, while Samsung Electronics and SK hynix are strengthening chip supply ties. Samsung SDS and LG CNS are bringing Anthropic's Claude model into the business AI market.
뉴스웨이 · Nov 21, 06:10 KST - Leaky AI Supply Chain Exposes Secret User Data at Alarming Rate
A research test sent nearly two million prompts with fake but working secrets through a network of AI services to see where they ended up. Many of the secrets were stolen, and attackers used them to reach cloud accounts. The results point to weak protection of customer data along the chain.
Ars Technica · Nov 21, 05:59 KST - OpenAI Shows How to Claim a Shopify Store in ChatGPT
This video shows how to claim your business in ChatGPT by connecting your Shopify store. You can start in Business Hub or the Shopify App Store. After connecting, you can manage your business information to control how your store appears in ChatGPT.
OpenAI 공식 YouTube · Nov 21, 05:48 KST