Autocomplete That Sees What You See (Router-Suggest)

Kari Jaaskelainen

12 Jan 2026 — 1 min read

What’s the big idea?

Today’s autocomplete guesses from text alone. The authors add visual context—images, screenshots, shared canvases—so assistants can predict what you’ll type next more accurately in live chats.

How it works

MAC: a new task that completes characters using partial text + visuals.
New benchmarks adapted from MMDialog and ImageChat.
Router-Suggest: a controller that routes each keystroke to either a fast text model or a vision-language model; includes a lightweight version for tight compute.

Why it matters

2.3×–10× faster than the best vision-language model, with strong accuracy.
User study: multimodal models save typing and boost satisfaction in multi-turn chats.

Think smarter design tools, more helpful healthcare chats, and assistants that truly see your context.

Paper: https://arxiv.org/abs/2601.05851v1

Paper: https://arxiv.org/abs/2601.05851v1

Register: https://www.AiFeta.com

#AI #Autocomplete #Multimodal #VisionLanguage #Chatbots #HumanComputerInteraction #UIUX #HealthcareTech #DesignTools #NLP

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added