RAG Evolution – A Primer to Agentic RAG

What is RAG (Retrieval-Augmented Generation)? Retrieval-Augmented Generation (RAG) is a technique that combines the strengths of large language models (LLMs) with external data retrieval to improve the quality and relevance of generated responses. Traditional LLMs use their pre-trained knowledge bases, whereas RAG pipelines will query external…

Samsung unveils Gauss2 AI model at SDC24 Korea

Samsung has revealed Gauss2, the second-generation proprietary AI model set to significantly enhance user experiences. Paul Kyungwhoon Cheun, President and CTO of the Device eXperience (DX) Division, commented: “Samsung Electronics is committed to developing cutting-edge software, including AI and data analytics, to enhance user experiences. “With…

Your child, the sophisticated language learner

As young children, how do we build our vocabulary? Even by age 1, many infants seem to think that if they hear a new word, it means something different from the words they already know. But why they think so has remained subject to inquiry among scholars for the last 40 years.

A new study carried out at the MIT Language Acquisition Lab offers a novel insight into the matter: Sentences contain subtle hints in their grammar that tell young children about the meaning of new words. The finding, based on experiments with 2-year-olds, suggests that even very young kids are capable of absorbing grammatical cues from language and leveraging that information to acquire new words.

“Even at a surprisingly young age, kids have sophisticated knowledge of the grammar of sentences and can use that to learn the meanings of new words,” says Athulya Aravind, an associate professor of linguistics at MIT.

The new insight stands in contrast to a prior explanation for how children build vocabulary: that they rely on the concept of “mutual exclusivity,” meaning they treat each new word as corresponding to a new object or category. Instead, the new research shows how extensively children respond directly to grammatical information when interpreting words.

“For us it’s very exciting because it’s a very simple idea that explains so much about how children understand language,” says Gabor Brody, a postdoc at Brown University, who is the first author of the paper.

The paper is titled, “Why Do Children Think Words Are Mutually Exclusive?” It is published in advance online form in Psychological Science. The authors are Brody; Roman Feiman, the Thomas J. and Alice M. Tisch Assistant Professor of Cognitive and Psychological Sciences and Linguistics at Brown; and Aravind, the Alfred Henry and Jean Morrison Hayes Career Development Associate Professor in MIT’s Department of Linguistics and Philosophy.

Focusing on focus

Many scholars have thought that young children, when learning new words, have an innate bias toward mutual exclusivity, which could explain how children learn some of their new words. However, the concept of mutual exclusivity has never been airtight: Words like “bat” refer to multiple kinds of objects, while any object can be described using countlessly many words. For instance a rabbit can be called not only a “rabbit” or a “bunny,” but also an “animal,” or a “beauty,” and in some contexts even a “delicacy.” Despite this lack of perfect one-to-one mapping between words and objects, mutual exclusivity has still been posited as a strong tendency in children’s word learning.

What Aravind, Brody, and Fieman propose is that children have no such tendency, and instead rely on so-called “focus” signals to decide what a new word means. Linguists use the term “focus” to refer to the way we emphasize or stress certain words to signal some kind of contrast. Depending on what is focused, the same sentence can have different implications. “Carlos gave Lewis a Ferrari” implies contrast with other possible cars — he could have given Lewis a Mercedes. But “Carlos gave Lewis a Ferrari” implies contrast with other people — he could have given Alexandra a Ferrari.

The researchers’ experiments manipulated focus in three experiments with a total of 106 children. The participants watched videos of a cartoon fox who asked them to point to different objects.

The first experiment established how focus influences kids’ choice between two objects when they hear a label, like “toy,” that could, in principle, correspond to either of the two. After giving a name to one of the two objects (“Look, I am pointing to the blicket”), the fox told the child, “Now you point to the toy!” Children were divided into two groups. One group heard “toy” without emphasis, while the other heard it with emphasis.

In the first version, “blicket” and “toy” plausibly refer to the same object. But in the second version, the added focus, through intonation, implies that “toy” contrasts with the previously discussed “blicket.” Without focus, only 24 percent of the respondents thought the words were mutually exclusive, whereas with the focus created by emphasizing “toy,” 89 percent of participants thought “blicket” and “toy” referred to different objects.

The second and third experiments showed that focus is not just key when it comes to words like “toy,” but it also affects the interpretation of new words children have never encountered before, like “wug” or “dax.” If a new word was said without focus, children thought the word meant the previously named object 71 percent of the time. But when hearing the new word spoken with focus, they thought it must refer to a new object 87 percent of the time.

“Even though they know nothing about this new word, when it was focused, that still told them something: Focus communicated to children the presence of a contrasting alternative, and they correspondingly understood the noun to refer to an object that had not previously been labeled,” Aravind explains.

She adds: “The particular claim we’re making is that there is no inherent bias in children toward mutual exclusivity. The only reason we make the corresponding inference is because focus tells you that the word means something different from another word. When focus goes away, children don’t draw those exclusivity inferences any more.”

The researchers believe the full set of experiments sheds new light on the issue.

“Earlier explanations of mutual exclusivity introduced a whole new problem,” Feiman says. “If kids assume words are mutually exclusive, how do they learn words that are not? After all, you can call the same animal either a rabbit or a bunny, and kids have to learn both of those at some point. Our finding explains why this isn’t actually a problem. Kids won’t think the new word is mutually exclusive with the old word by default, unless adults tell them that it is — all adults have to do if the new word is not mutually exclusive is just say it without focusing it, and they’ll naturally do that if they’re thinking about it as compatible.”

Learning language from language

The experiment, the researchers note, is the result of interdisciplinary research bridging psychology and linguistics — in this case, mobilizing the linguistics concept of focus to address an issue of interest in both fields.

“We are hopeful this will be a paper that shows that small, simple theories have a place in psychology,” Brody says. “It is a very small theory, not a huge model of the mind, but it completely flips the switch on some phenomena we thought we understood.”

If the new hypothesis is correct, the researchers may have developed a more robust explanation about how children correctly apply new words.

“An influential idea in language development is that children can use their existing knowledge of language to learn more language,” Aravind says. “We’re in a sense building on that idea, and saying that even in the simplest cases, aspects of language that children already know, in this case an understanding of focus, help them grasp the meanings of unknown words.”

The scholars acknowledge that more studies could further advance our knowledge about the issue. Future research, they note in the paper, could reexamine prior studies about mutual exclusivity, record and study naturalistic interactions between parents and children to see how focus is used, and examine the issue in other languages, especially those marking focus in alternate ways, such as word order.

The research was supported, in part, by a Jacobs Foundation Fellowship awarded to Feiman.

Save Now on PTZOptics PTZ Cameras with Black Friday Specials

Save up to $300 on select PTZOptics cameras and bundles to make sure your streaming or broadcasting setup is ready for everything 2025 has in store.
Whether you’re updating or expanding your studio or just dipping your toe into video production, we’ve got you covered. All PTZOptics products deliver industry-leading optics, control and connectivity; U.S.-based customer support; and award-winning warranties. Offer runs from November 20th – December 2nd, 2024 only!

Save $150 on Move 4K Cameras!
The Move 4K is the latest PTZ camera from PTZOptics, featuring auto-tracking for a more intelligent video production workflow. The Move 4K is capable of 4K at 60fps (1080p at 60fps over SDI), future-proofing your technology investment while still accommodating HD and Full HD video resolutions equipment. Available in gray and white.

Save $100 on Move SE Cameras!
Built on the award-winning PTZOptics camera line, the PTZ and auto-tracking features you love are now more within reach than ever. The PTZOptics Move SE combines HDMI, SDI, USB and IP outputs – with native NDI® now available – all into a single camera. Available in gray and white.

Save $250 on Move SE Producer Bundle!
The Producer-SE bundle, featuring three award-winning 20X Move SE cameras, delivers precise, lifelike 1080p quality from a distance with auto-tracking capabilities. The PT-JOY-G4 joystick controller simplifies setup and offers intuitive control. With versatile output options—SDI, HDMI, USB, NDI® HX2, and IP—the Move SE cameras provide unmatched flexibility and performance.
Save $300 on Move 4K Producer Bundle!
Capture ultra-high-definition 4K with three award-winning 20X Move 4K cameras, featuring advanced auto-tracking and native NDI® HX3 for top performance. The SuperJoy controller enhances production with superior control. The fusion of 4K video clarity with the advanced SuperJoy controller offers unmatched video production prowess, meeting the demands of professionals.

Save $150 on Link 4K Cameras!
With Dante AV-H™ and the latest in auto-tracking capabilities, the Link 4K fits easily into even the most complex Dante design or workflow. The Link 4K combines broadcast quality with Dante’s simple discovery, set up and management, simplifying and professionalizing any video production installation. Available in gray and white.

Save $50 on Studio Pro Cameras!

The Studio Pro is an excellent addition to any video system, especially if you already have a PTZ camera. Use PTZ cameras for dynamic, action-focused shots, and rely on the Studio Pro to deliver stable cutaways or close-ups. Its versatile design accommodates various filming scenarios, capturing subjects within 30 feet with exceptional clarity.

Boost your ROI: The impact of chatbots on marketing – AI News

Discover how chatbots for marketing can boost your ROI with enhanced engagement and instant customer responses. What are chatbots? Chatbots are automated software applications designed to simulate human conversation. They interact with users through text or voice, providing immediate responses and performing various tasks. AI chatbots…

NDI Discussion on BirdDog’s New X Series of PTZ Cameras

Gary will joined in studio with BirdDog’s very own Dan Miall to discuss all things NDI with BirdDogs new line of PTZ cameras. This will include the BirdDog X1, X1 Ultra, X4 Ultra and the X5 Ultra. Learn how BirdDog is paving the way with NDI HX 3 and with truly wireless NDI workflows.

NDI November is a month of live webinars highlighting the exciting technology for Video and Audio over IP. Join us as we welcome guests from the top NDI partners in the industry including case studies, installation success stories, product spotlights and more. One registration gains you access to all 3 webinars PLUS a chance to win one of our amazing NDI prizes!

[embedded content]

MAKI Ultra Box Camera
This powerhouse combines lightning-fast autofocus and 4K60, capturing every moment with precision. Side-mounted physical buttons provide seamless control, keeping you focused on creativity. With BirdDog’s HALO Tally system, you’ll easily see which camera is live. Choose between 12x and 20x zoom models to suit your shooting needs.

X1 PTZ Camera
Unlock a new level of content creation with the X1—a versatile PTZ camera offering smooth, precise movement and HD-quality imaging with 20x optical zoom. Seamlessly integrating into any workflow with support for NDI, baseband video, and Wi-Fi, the X1 includes advanced features like AI tracking, Halo Tally, built-in NDI|HX decoding, and an industry-first E-Ink display, delivering high-end capabilities in an accessible package. Bring the X-factor to your next project!
X1 Ultra PTZ Camera
Unlock a new level of content creation with the X1 Ultra, a PTZ camera that combines smooth, controllable movement with high-quality 4K imaging. With versatile integration options like NDI, baseband video, and wireless Wi-Fi connectivity, the X1 Ultra fits seamlessly into any workflow. Key features include AI tracking, Halo Tally, built-in NDI|HX decoding, and an industry-first E-Ink display. Plus, enjoy the power of 12x optical zoom, making the X1 Ultra the smart choice for those ready to elevate their content.
X5 Ultra PTZ Camera
The X5 Ultra transforms demanding productions into a breeze, offering top-tier capability, quality, and performance to elevate your PTZ experience. Its advanced motor drive ensures ultra-precise, smooth movements with natural acceleration and deceleration, while BirdDog’s Halo tally system enhances audience engagement. With built-in NDI® decoding*, 12G-SDI connectivity, dual e-ink displays for effortless branding, and a powerful Sony 4K60 image sensor, the X5 Ultra delivers the highest performance NDI® | HX3 for any production.
X4 Ultra PTZ Camera
The X4 Ultra is the ultimate all-in-one live production camera, offering top-tier image quality and seamless connectivity. With a 4-hour battery and Wi-Fi 6, it captures shots in places cables can’t reach. Use it solo or manage up to four cameras wirelessly, streaming smoothly via NDI|HX3 with our receiver. Plus, it’s equipped with 3G-SDI, NDI, HDMI, USB-C, RTMP, and RTSP connections. Flexible and versatile, it’s ready for any shot—just pick it up and go.

3 Questions: Claire Wang on training the brain for memory sports

On Nov. 10, some of the country’s top memorizers converged on MIT’s Kresge Auditorium to compete in a “Tournament of Memory Champions” in front of a live audience.

The competition was split into four events: long-term memory, words-to-remember, auditory memory, and double-deck of cards, in which competitors must memorize the exact order of two decks of cards. In between the events, MIT faculty who are experts in the science of memory provided short talks and demos about memory and how to improve it. Among the competitors was MIT’s own Claire Wang, a sophomore majoring in electrical engineering and computer science. Wang has competed in memory sports for years, a hobby that has taken her around the world to learn from some of the best memorists on the planet. At the tournament, she tied for first place in the words-to-remember competition.

The event commemorated the 25th anniversary of the USA Memory Championship Organization (USAMC). USAMC sponsored the event in partnership with MIT’s McGovern Institute for Brain Research, the Department of Brain and Cognitive Sciences, the MIT Quest for Intelligence, and the company Lumosity.

MIT News sat down with Wang to learn more about her experience with memory competitions — and see if she had any advice for those of us with less-than-amazing memory skills.

Q: How did you come to get involved in memory competitions?

A: When I was in middle school, I read the book “Moonwalking with Einstein,” which is about a journalist’s journey from average memory to being named memory champion in 2006. My parents were also obsessed with this TV show where people were memorizing decks of cards and performing other feats of memory. I had already known about the concept of “memory palaces,” so I was inspired to explore memory sports. Somehow, I convinced my parents to let me take a gap year after seventh grade, and I travelled the world going to competitions and learning from memory grandmasters. I got to know the community in that time and I got to build my memory system, which was really fun. I did a lot less of those competitions after that year and some subsequent competitions with the USA memory competition, but it’s still fun to have this ability.

Q: What was the Tournament of Memory Champions like?

A: USAMC invited a lot of winners from previous years to compete, which was really cool. It was nice seeing a lot of people I haven’t seen in years. I didn’t compete in every event because I was too busy to do the long-term memory, which takes you two weeks of memorization work. But it was a really cool experience. I helped a bit with the brainstorming beforehand because I know one of the professors running it. We thought about how to give the talks and structure the event.

Then I competed in the words event, which is when they give you 300 words over 15 minutes, and the competitors have to recall each one in order in a round robin competition. You got two strikes. A lot of other competitions just make you write the words down. The round robin makes it more fun for people to watch. I tied with someone else — I made a dumb mistake — so I was kind of sad in hindsight, but being tied for first is still great.

Since I hadn’t done this in a while (and I was coming back from a trip where I didn’t get much sleep), I was a bit nervous that my brain wouldn’t be able to remember anything, and I was pleasantly surprised I didn’t just blank on stage. Also, since I hadn’t done this in a while, a lot of my loci and memory palaces were forgotten, so I had to speed-review them before the competition. The words event doesn’t get easier over time — it’s just 300 random words (which could range from “disappointment” to “chair”) and you just have to remember the order.

Q: What is your approach to improving memory?

A: The whole idea is that we memorize images, feelings, and emotions much better than numbers or random words. The way it works in practice is we make an ordered set of locations in a “memory palace.” The palace could be anything. It could be a campus or a classroom or a part of a room, but you imagine yourself walking through this space, so there’s a specific order to it, and in every location I place certain information. This is information related to what I’m trying to remember. I have pictures I associate with words and I have specific images I correlate with numbers. Once you have a correlated image system, all you need to remember is a story, and then when you recall, you translate that back to the original information.

Doing memory sports really helps you with visualization, and being able to visualize things faster and better helps you remember things better. You start remembering with spaced repetition that you can talk yourself through. Allowing things to have an emotional connection is also important, because you remember emotions better. Doing memory competitions made me want to study neuroscience and computer science at MIT.

The specific memory sports techniques are not as useful in everyday life as you’d think, because a lot of the information we learn is more operative and requires intuitive understanding, but I do think they help in some ways. First, sometimes you have to initially remember things before you can develop a strong intuition later. Also, since I have to get really good at telling a lot of stories over time, I have gotten great at visualization and manipulating objects in my mind, which helps a lot. 

A nonflammable battery to power a safer, decarbonized future

Lithium-ion batteries are the workhorses of home electronics and are powering an electric revolution in transportation. But they are not suitable for every application.

A key drawback is their flammability and toxicity, which make large-scale lithium-ion energy storage a bad fit in densely populated city centers and near metal processing or chemical manufacturing plants.

Now Alsym Energy has developed a nonflammable, nontoxic alternative to lithium-ion batteries to help renewables like wind and solar bridge the gap in a broader range of sectors. The company’s electrodes use relatively stable, abundant materials, and its electrolyte is primarily water with some nontoxic add-ons.

“Renewables are intermittent, so you need storage, and to really solve the decarbonization problem, we need to be able to make these batteries anywhere at low cost,” says Alsym co-founder and MIT Professor Kripa Varanasi.

The company believes its batteries, which are currently being tested by potential customers around the world, hold enormous potential to decarbonize the high-emissions industrial manufacturing sector, and they see other applications ranging from mining to powering data centers, homes, and utilities.

“We are enabling a decarbonization of markets that was not possible before,” Alsym co-founder and CEO Mukesh Chatter says. “No chemical or steel plant would dare put a lithium battery close to their premises because of the flammability, and industrial emissions are a much bigger problem than passenger cars. With this approach, we’re able to offer a new path.”

Helping 1 billion people

Chatter started a telecommunications company with serial entrepreneurs and longtime members of the MIT community Ray Stata ’57, SM ’58 and Alec Dingee ’52 in 1997. Since the company was acquired in 1999, Chatter and his wife have started other ventures and invested in some startups, but after losing his mother to cancer in 2012, Chatter decided he wanted to maximize his impact by only working on technologies that could reach 1 billion people or more.

The problem Chatter decided to focus on was electricity access.

“The intent was to light up the homes of at least 1 billion people around the world who either did not have electricity, or only got it part of the time, condemning them basically to a life of poverty in the 19th century,” Chatter says. “When you don’t have access to electricity, you also don’t have the internet, cell phones, education, etc.”

To solve the problem, Chatter decided to fund research into a new kind of battery. The battery had to be cheap enough to be adopted in low-resource settings, safe enough to be deployed in crowded areas, and work well enough to support two light bulbs, a fan, a refrigerator, and an internet modem.

At first, Chatter was surprised how few takers he had to start the research, even from researchers at the top universities in the world.

“It’s a burning problem, but the risk of failure was so high that nobody wanted to take the chance,” Chatter recalls.

He finally found his partners in Varanasi, Rensselaer Polytechnic Institute Professor Nikhil Koratkar and Rensselaer researcher Rahul Mukherjee. Varanasi, who notes he’s been at MIT for 22 years, says the Institute’s culture gave him the confidence to tackle big problems.

“My students, postdocs, and colleagues are inspirational to me,” he says. “The MIT ecosystem infuses us with this resolve to go after problems that look insurmountable.”

Varanasi leads an interdisciplinary lab at MIT dedicated to understanding physicochemical and biological phenomena. His research has spurred the creation of materials, devices, products, and processes to tackle challenges in energy, agriculture, and other sectors, as well as startup companies to commercialize this work.

“Working at the interfaces of matter has unlocked numerous new research pathways across various fields, and MIT has provided me the creative freedom to explore, discover, and learn, and apply that knowledge to solve critical challenges,” he says. “I was able to draw significantly from my learnings as we set out to develop the new battery technology.”

Alsym’s founding team began by trying to design a battery from scratch based on new materials that could fit the parameters defined by Chatter. To make it nonflammable and nontoxic, the founders wanted to avoid lithium and cobalt.

After evaluating many different chemistries, the founders settled on Alsym’s current approach, which was finalized in 2020.

Although the full makeup of Alsym’s battery is still under wraps as the company waits to be granted patents, one of Alsym’s electrodes is made mostly of manganese oxide while the other is primarily made of a metal oxide. The electrolyte is primarily water.

There are several advantages to Alsym’s new battery chemistry. Because the battery is inherently safer and more sustainable than lithium-ion, the company doesn’t need the same safety protections or cooling equipment, and it can pack its batteries close to each other without fear of fires or explosions. Varanasi also says the battery can be manufactured in any of today’s lithium-ion plants with minimal changes and at significantly lower operating cost.

“We are very excited right now,” Chatter says. “We started out wanting to light up 1 billion people’s homes, and now in addition to the original goal we have a chance to impact the entire globe if we are successful at cutting back industrial emissions.”

A new platform for energy storage

Although the batteries don’t quite reach the energy density of lithium-ion batteries, Varanasi says Alsym is first among alternative chemistries at the system-level. He says 20-foot containers of Alsym’s batteries can provide 1.7 megawatt hours of electricity. The batteries can also fast-charge over four hours and can be configured to discharge over anywhere from two to 110 hours.

“We’re highly configurable, and that’s important because depending on where you are, you can sometimes run on two cycles a day with solar, and in combination with wind, you could truly get 24/7 electricity,” Chatter says. “The need to do multiday or long duration storage is a small part of the market, but we support that too.”

Alsym has been manufacturing prototypes at a small facility in Woburn, Massachusetts, for the last two years, and early this year it expanded its capacity and began to send samples to customers for field testing.

In addition to large utilities, the company is working with municipalities, generator manufacturers, and providers of behind-the-meter power for residential and commercial buildings. The company is also in discussion with a large chemical manufacturers and metal processing plants to provide energy storage system to reduce their carbon footprint, something they say was not feasible with lithium-ion batteries, due to their flammability, or with nonlithium batteries, due to their large space requirements.

Another critical area is data centers. With the growth of AI, the demand for data centers — and their energy consumption — is set to surge.

“We must power the AI and digitization revolution without compromising our planet,” says Varanasi, adding that lithium batteries are unsuitable for co-location with data centers due to flammability risks. “Alsym batteries are well-positioned to offer a safer, more sustainable alternative. Intermittency is also a key issue for electrolyzers used in green hydrogen production and other markets.”

Varanasi sees Alsym as a platform company, and Chatter says Alsym is already working on other battery chemistries that have higher densities and maintain performance at even more extreme temperatures.

“When you use a single material in any battery, and the whole world starts to use it, you run out of that material,” Varanasi says. “What we have is a platform that has enabled us to not just to come up with just one chemistry, but at least three or four chemistries targeted at different applications so no one particular set of materials will be stressed in terms of supply.”