Communication Techniques For Virtual Teams

Text alone won’t get you into Google’s AI Overviews. Today’s AI models summarize blended content: text, images, tables, and videos. And they favor the sources that give them more formats to work with. Here’s how to prep your content for multimodal visibility: 👇 1. Use descriptive alt text Avoid keyword-stuffing. Just describe the image naturally: ✅ alt="red brick greenhouse with sliding door" ❌ alt="greenhouse greenhouse greenhouse" 2. Rename your image files AI reads filenames too. Use hyphenated keywords like: ‘bamboo-planter-lobby.jpg’ instead of ‘IMG_2312.JPG’ 3. Embed HTML tables Don’t use images of charts. Use real tables with <table> tags so AI can parse the data. 4. Transcribe your videos Add readable transcripts below videos to boost accessibility and visibility. 5. Add captions and context Label your visuals and describe what they show. Helps both AI and users. 6. Revisit high-traffic pages Start with the pages that already rank well. Add visuals, charts, or short embedded videos to give them an edge.

Happy Friday, this week in #learnwithmz lets discuss 𝐌𝐮𝐥𝐭𝐢𝐦𝐨𝐝𝐚𝐥 𝐌𝐨𝐝𝐞𝐥𝐬 [My Prediction] Imagine a future where for example, for dinner, you simply tell a system what you’d like to eat. You can visually and verbally confirm the items and ingredients, and the system customizes the order based on your past preferences and interactions. Best part? It places the order 𝐫𝐞𝐥𝐢𝐚𝐛𝐥𝐲 without you searching/clicking on a single screen. It sounds wild, but it’s not far off! Multimodal models (MM-LLMs) are changing the way we interact with technology by integrating multiple types of data, such as text, images, and audio, into a single model. These models are not only enhancing our understanding of complex data but also opening up new possibilities for innovation. 𝐍𝐨𝐭𝐚𝐛𝐥𝐞 𝐌𝐨𝐝𝐞𝐥𝐬 - Microsoft's OmniParser: (https://lnkd.in/gRNsYHDk) OmniParser uses two sequential models: 1. Object Detection: A fine-tuned YOLOv8 model detects interactable regions on a UI screen. This allows the Set of Marks approach, where a multimodal LLM like GPT-4V is fed a screenshot with bounding boxes marking these regions, rather than just the screenshot alone. 2. Image Captioning: A fine-tuned BLIP-2/Florence-2 model generates descriptions for each detected region. This way, GPT-4V receives not just the screenshot with marked regions, but also captions that explain the function of each region. This combination enhances the model's understanding and interaction capabilities. - Apple's Ferret-UI: (https://lnkd.in/gg5UDE_P) A cutting-edge model that enhances user interfaces by processing multimodal inputs efficiently. It utilizes two pre-trained large language models, Gemma-2B and LLaMa-8B, to enable the model to comprehend and analyze screenshots of user interfaces and classify widgets. - OpenAI GPT-4o: (https://lnkd.in/grhpWDB6) OpenAI's GPT-4o is optimized for performance and supports text and image processing. It accepts as input any combination of text, audio, image, and video and generates any combination of text, audio, and image outputs. 𝐅𝐮𝐫𝐭𝐡𝐞𝐫 𝐑𝐞𝐚𝐝𝐢𝐧𝐠 - MM-LLMs: Recent Advances in MultiModal Large Language Models: A comprehensive survey on the latest developments in multimodal models: https://lnkd.in/g39QDuaG - Awesome-Multimodal-Large-Language-Models: A curated list of resources and projects on GitHub: https://lnkd.in/gHkh6EmD What use cases could you imagine with these Multimodal Models? Share your thoughts in the comments! Follow + hit 🔔 to stay updated. #MachineLearning #AI #DataScience #TechTrends #ML #Multimodal #MMLM P.S. 1st image is generated via Bing Copilot Microsoft Designer 2nd Image is Apple's Ferret-UI (Source: https://lnkd.in/gTJ5sNd2)

Multimodal CX refers to a customer experience strategy that integrates multiple modes of interaction—text, voice, video, touch, gesture, and even image recognition—into a seamless, unified customer journey. It’s about letting customers engage with a brand through whatever combination of channels or inputs feels most natural to them—and ensuring those modes work together intelligently. 🔍 Example (The Seamless Journey) Imagine a traveler interacting with an airline: • They speak to a voice assistant to change a flight. • They text a chatbot to confirm luggage options. • They tap through the app to choose a seat. All three interactions are connected, context-aware, and synchronized—so the system “remembers” what the customer already said or did, regardless of mode. 💡 Why It Matters Multimodal CX is the next evolution beyond omnichannel: • Omnichannel = consistent brand experience across channels. • Multimodal = fluid experience across input types (voice, text, image, etc.), powered by AI. It’s especially relevant now because AI and large multimodal models (like GPT-5) can process text, voice, and visual data together—making it possible for brands to build truly conversational, intuitive customer experiences. 🚀 In Practice This is happening today: • Retail: Scan an item, ask questions via voice, and get personalized styling advice via chat. • Travel: Show a photo of damaged luggage to an airline chatbot and get compensation automatically. • Banking: Use facial ID, voice commands, and chat messaging in the same secure flow. What new revenue streams are unlocked when your CX can see, hear, and read? #MultimodalCX #CustomerExperience #CXStrategy #AI #DigitalTransformation #ThoughtLeadership

How AI Models Process Text and Images Together? 👀 Attention across multimodality in models is all about how models combine and reason over different kinds of data like text, images, audio, or video inside the transformer architecture. Since transformers were originally built for text, multimodal extensions had to figure out how to align and fuse very different inputs. Broadly, there are two main strategies: 1. Unified Embedding (Concatenation) Approach 👉 Each modality (say, text and image) is first turned into embeddings of the same size.  👉 So while text tokens represent words/subwords, image tokens represent visual patches/features. Both end up as vectors of the same dimension. 👉 Once both are in the same embedding space, the model treats them like one long sequence and processes them with standard self-attention. 👉 Attention doesn’t care if a token came from text or image, it just looks at relationships across the whole sequence. Advantage: Simple, minimal architectural changes. Limitation: Long image sequences blow up the context window and can be computationally heavy. Example: Fuyu, Molmo, Pixtral. 2. Cross-Modality Attention Approach 👉 Instead of dumping all embeddings into one sequence, each modality is encoded separately. 👉 The text sequence is processed normally, but at certain layers, it can “look at” image features via cross-attention: - Queries (Q) come from one modality, say, text. - Keys (K) and Values (V) come from another modality, say, image. 👉 This way, text tokens can selectively pull in relevant visual information without being flooded by raw image tokens. Advantage: More efficient, keeps text-only performance intact. Limitation: Requires modifying the LLM architecture. Example: LLaMA 3.2 multimodal, NVLM-X, Aria. #MultiModality #LLM #AI

A challenge with AI is the division of labor between language-based systems that analyze text and sensor-based systems like computer vision that visualize our environment. #Multimodal AI trains algorithms in a fused way that allows us to manage complex AI tasks as a single workstream. Multimodal AI refers to systems capable of processing and integrating multiple types of data—such as text, images, audio, video, and sensor data—to generate comprehensive insights and perform complex tasks. Unlike traditional #AI, which specializes in one modality, multimodal AI combines these capabilities, allowing machines to "see," "hear," "read," and "understand" across various formats simultaneously. For federal leaders, it means AI can operate in environments that mirror the multifaceted, real-world challenges agencies face. For example, it can be used in the aftermath of natural disasters to analyze satellite imagery, combine it with real-time social media data and audio reports from first responders, and rapidly generate actionable maps of affected areas. One well-known multimodal AI algorithm is Contrastive Language-Image Pre-Training (CLIP), which is a key algorithm used in generating AI art. CLIP jointly trains image and text data using two neural networks called transformers, each acting as an encoder. These encoders code data into a latent space representing the features of the image and text separately. The dataset's class names (e.g., dog, cat, car) form potential text pairings to predict the most likely image-text pairs. CLIP is trained to predict if an image and text are paired in its dataset. The image encoder calculates the image's feature representation, while the text encoder trains a classifier specifying the visual concepts in the text. The key takeaway is that CLIP "jointly trains" or fuses by integrating two data types into a single training pipeline, unlike unimodal algorithms trained independently. Booz Allen is working to identify innovative applications for this technology. For example, we supported the National Institutes of Health (NIH) in developing cancer pain detection models fusing facial imagery, three-dimensional facial landmarks, audio statistics, Mel spectrograms, text embeddings, demographic, and behavioral data. For law enforcement and telemedicine, we created an acoustic #LLM tool enabling automated detection and analysis of multi-speaker conversations. We also published original research on multimodal AI algorithms that trained visible and long-wave infrared for applications in telemedicine and automated driving. Multimodal AI is no longer a vision of the future—it’s a capability ready to address today’s challenges. Federal leaders must think strategically about how to leverage this transformative technology to drive their missions forward while ensuring governance frameworks keep pace with innovation.

Your stunning destination video means nothing if AI can't understand it. Here's what most travel brands are missing: AI search isn't just reading text anymore. It's natively multimodal - pulling from video, audio, images, and their transcripts simultaneously. The Multimodal Reality When someone asks AI "What's it like to experience the Northern Lights in Iceland," the system isn't just scanning blog posts. It's analyzing your destination videos, processing audio from your guides, and understanding the emotions in your imagery. Think in Content Clusters Stop creating isolated pieces. Your content strategy needs clusters: that epic drone footage, the audio narration explaining the phenomenon, the guide's transcript, and the written description - all working together to paint the complete picture. The Citation Problem Here's the kicker: Google might reconstruct your beautiful content without citing you if it's not in the format they prefer. Your 4K Northern Lights video could become someone else's AI answer if you don't have the supporting multimodal elements. The Fix Every piece of visual content needs machine-readable companions. Transcripts for videos. Alt text that tells stories. Audio descriptions that capture the experience. Structured data that connects it all. Travel is inherently experiential. Your content strategy should be too. #travelmarketing #multimodal #AIcontent #videomarketing #digitalmarketing

Think about your last conversation: How much did you say without words? Meet Darren Cosker, whose research at Microsoft focuses on capturing the nuance of real-time, multimodal communication. Before joining Microsoft, Darren was a professor at the University of Bath, where he founded the Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA). His goal is to make the conversations we have with AI feel as fluid, responsive, and natural as those we have with colleagues. Human communication is inherently multimodal. We speak with our faces, our tone, our gestures. Yet most AI systems rely on transcripts or audio alone. Darren is changing this by designing models that integrate speech, vision, and context to infer sentiment, engagement, and turn-taking in real time. He’s bringing “soft skills” to AI, enabling agents to know when to speak, when to listen, and how to adapt to group dynamics. You can see the impact of Darren’s research in products like Teams, where multimodal communication is key to a good meeting, and Mesh (https://lnkd.in/gsFFqyzJ), where AI avatars enable richer, more personal collaboration. Darren’s research includes years of pioneering work in human motion and facial synthesis. For example, he and his team developed neural networks that predict full-body motion from minimal signals, enabling avatars that move naturally even with incomplete data (https://lnkd.in/gt5iJnGp). His advances in speech-driven facial animation (https://lnkd.in/gQYf-TJi; https://lnkd.in/gV3N9cH2) capture individual speaking styles and subtle idiosyncrasies, bringing expressive realism to virtual communication. Darren is fascinated by how realism, embodiment, and perception intersect. He has shown that people feel stronger ownership and self-identification when inhabiting photorealistic, personalized avatars (https://lnkd.in/gKTYe4KZ). Earlier work revealed how subtle facial motion cues shape trust and cooperation, findings that continue to inform how AI can read and respond to human emotion in socially intelligent ways (https://lnkd.in/ghPfDd5A). Today, Darren’s work connects these scientific insights with the speed and liveness required for true conversational AI. If you’re not yet following Darren’s research, I highly recommend checking it out!   #AIInnovators #AppliedResearch #MultimodalAI #LeadingLikeAScientist