SCROLL NEWS / DISCOVERY
Search headlines
Find the stories shaping the conversation.
Results for " API " 73,953 found 🔀 AI-powered Shuffle
🎥 “Salerno returns”: spine-tingling display, choreography’s viral 😍
Top-flight atmosphere at the Arechi Stadium for the Serie C playoff clash between Salernitana and Ravenna.Watch the full Serie BKT live on OneFootball for just €9.99 a month. Click here to buy the L...
Aspiring actress travels across the world to pursue entertainment career
Smashing Pumpkins Announce Rats in a Cage Tour to Celebrate ‘Mellon Collie and the Infinite Sadness’
"Staging a Mellon Collie-themed show is something we’ve discussed for over a decade, and finally the stars have aligned," says Billy Corgan
KC Concepcion switches to No. 1
Browns rookie receiver KC Concepcion sported No. 17 when at his introductory press conference and during rookie minicamp.
Bills news: Buffalo begins OTAs
Left guard Alec Anderson and punter Mitch Wishnowsky are among those looking to win a starting job with OTAs starting.
Could A Simple Lab Mistake Lead Scientists to Over-Estimate Microplastics?
While microplastics are a very real issue, one new study suggests that the numbers might not be quite as bad as we've feared.
Aaron Rodgers returns: Quarterback reunites with Mike McCarthy, signs with Steelers for 22nd season in NFL
Chicago Bears Over/Under Player Milestone Predictions (Part 1)
Our guy @GOOCH1701 sets a few fun Chicago Bears over/unders, and then gives his picks. Which way do you predict for these?
New MatterChat Model Helps AI to ‘See’ the Language of Science
From writing emails to generating computer code, much of the artificial intelligence prevalent in our daily lives has succeeded by mastering one domain: text. However, this leaves a major blind spot in the physical sciences, where models depend on the high-resolution, three-dimensional data of the physical world, like the intricate lattice of atoms in a crystal. Delivering on the promise of using AI for science requires teaching these data-driven text models to seamlessly “talk to” physics-based models. Now, a new AI framework from Lawrence Berkeley National Laboratory (Berkeley Lab), called MatterChat, solves this problem by creating a specialized “bridge.” It connects the conversational power of a Large Language Model (LLM) with a physics-based AI that models “interatomic potentials”: the complex physical forces between atoms. The resulting system already significantly outperforms general-purpose AI tools like GPT-4 at predicting material properties, and the team hopes it can accelerate scientific discovery by serving as a robust research partner that provides grounded insights and generates step-by-step instructions for synthesizing novel materials. A paper describing this work was recently published in Nature Machine Intelligence. “Traditional simulations can provide the physical rigor required for materials science, yet their computational cost remains prohibitive for high-throughput screening. Conversely, while LLMs excel at rapid knowledge synthesis, they inherently lack the ‘structural vision’ to interpret materials directly from their underlying atomic coordinates,” said Yingheng Tang, a postdoctoral researcher in Berkeley Lab’s Applied Math and Computational Research Division (AMCR) and lead author on the paper. “MatterChat was built to solve this dilemma, empowering LLMs with a structural ‘vision’ that allows researchers to leverage their full potential for solving complex, real-world materials challenges.” Empowering language models to solve complex challenges in materials science To build MatterChat, the Berkeley Lab team drew inspiration from technologies like Vision Question Answering (VQA) and Text-to-Image (T2I) generation. In these tasks, AI must translate high-level text concepts into visual images, or vice versa. Doing so requires developers to build tools that “bridge” two fundamentally different forms of data. The researchers adapted this concept to the physical sciences. With MatterChat, they created a “bridge model” that successfully connects an LLM’s general knowledge with the deep understanding of the atomic-scale world encoded in scientific interatomic potentials. Until now, researchers using LLMs to solve materials problems usually had to feed them raw data files as if they were just strings of text. It’s like asking an AI to understand a complex 3D engine based only on a parts list: the LLM can read the names, but it can’t “see” how the atoms fit together in space. MatterChat solves this by training a specialized AI bridge model, pre-trained on millions of crystal structures and an LLM, to align the LLM’s representation of the world with the interatomic potential’s representation of the world. The bridge model can translate physical insights into a format the LLM can actually understand. By giving the LLM these “scientific eyes”— a scientific “inductive bias” in the terminology of AI — the Berkeley Lab team has transformed it into a robust research tool capable of providing grounded scientific insights into complex materials challenges, such as predicting thermal stability or analyzing electronic band gaps. “We think of atoms as living in a physical space, but from a machine learning perspective, they are just vectors living in some very non-trivially structured manifold in a high-dimensional Euclidean space; and, of course, the same is true for the sentences and paragraphs that we use to express our ideas about those atoms,” said co-author Michael Mahoney, Berkeley Lab’s Scientific Data Division (SDD) AI Initiative Research Lead. “The bridge model basically gets those two structures to ‘talk with’ each other.” As a proof-of-concept of this general approach, the team trained their bridge model on a dataset curated by pairing nearly 143,000 stable atomic structures from the Materials Project with their corresponding physical properties. This training data was automatically assembled using the Materials Project’s API and deliberately enriched with properties fundamental to microelectronics design — like formation energy and bandgap — allowing MatterChat to learn the complex patterns connecting a material’s atomic blueprint to its functional performance. To validate their model, the researchers benchmarked MatterChat against a suite of other AI systems, from general-purpose LLMs to other specialized scientific AI methods. The results show that MatterChat consistently outperformed its competitors across a range of tasks. The model was more accurate in classifying material types and demonstrated superior precision in predicting numerical properties. For example, it excelled at predicting a material’s bandgap, a property critical for designing new electronics from high-capacity energy storage to next-generation computer chips. “Our design is significantly more efficient because we don’t have to build a massive AI model from the ground up,” said co-author Zhi (Jackie) Yao, a research scientist in Berkeley Lab’s AMCR. “Instead, we take two powerful, pre-trained models — a structural encoder for materials physics and an open-source LLM — and use them off-the-shelf. The only component we actually train is the lightweight ‘bridge model’ that translates between them. It’s the difference between building an entire car factory and simply designing a smart adapter that connects a world-class engine to a world-class navigation system. This approach is not only computationally efficient, but also makes the system modular, so we can easily upgrade components or adapt the bridge for other scientific domains in the future.” Crucially, this modular design highlights exactly how institutions like Berkeley Lab and the Department of Energy are carving out a highly valuable niche in the booming AI landscape. Rather than competing with Silicon Valley tech giants to build ever-larger language models from scratch, the lab is focusing on the specialized connective tissue that makes commercial AI useful for hardcore science. Because the bridge model approach underlying MatterChat is forward-compatible, it is perfectly positioned to leverage these parallel tracks of innovation. As Mahoney pointed out, “We expect that industry will continue to develop improved LLMs, and we expect domain scientists and facilities will continue to generate new data. An important part of scientific machine learning is not simply to solve problems on today’s data, but instead to develop general methods that will be forward-compatible with orders of magnitude more data, whether from scientific domains or from LLMs.” According to Yao, the MatterChat project, which was initially developed and enhanced with funding from a Berkeley Lab Laboratory Directed Research & Development (LDRD) Program, will now expand its capabilities. In a collaboration with Fermilab, MatterChat is already contributing to a U.S. Department of Energy Genesis Mission project — called Accelerating eXtreme Environment Specs-to-Silicon (AXESS) — that aims to speed up the development of next-generation, high-speed, radiation-hardened detectors for challenging particle physics experiments by using advanced 3D integrated circuits (chiplets) and AI-driven data analysis. In addition to the LDRD support, the team also credits supercomputing resources at the National Energy Research Scientific Computing Center (NERSC), located at Berkeley Lab, with MatterChat’s success. “We are incredibly grateful to NERSC; this research simply would not have happened without access to the Perlmutter supercomputer through their AI for Science program,” said Tang. Wenbin Xu, a NERSC postdoctoral fellow at the time, was also a major co-author of the work, as was Benjamin Erichson, a research scientist in Berkeley Lab’s SDD, highlighting the benefits of AMCR-SDD collaboration on AI for science. ### Lawrence Berkeley National Laboratory (Berkeley Lab) is committed to groundbreaking research focused on discovery science and solutions for abundant and reliable energy supplies. The lab’s expertise spans materials, chemistry, physics, biology, earth and environmental science, mathematics, and computing. Researchers from around the world rely on the lab’s world-class scientific facilities for their own pioneering research. Founded in 1931 on the belief that the biggest problems are best addressed by teams, Berkeley Lab and its scientists have been recognized with 17 Nobel Prizes. Berkeley Lab is a multiprogram national laboratory managed by the University of California for the U.S. Department of Energy’s Office of Science. DOE’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States, and is working to address some of the most pressing challenges of our time. For more information, please visit energy.gov/science.
Cowboys schedule includes seven standalone games
The Cowboys have a lot of standalone games in 2026.
Pickleball, dining and entertainment come together at the Crush Yard
The Crush Yard pickleball bar and lounge in Brentwood combines indoor pickleball with dining and entertainment, featuring eight courts and a full‑service restaurant.
Which young Penguins players could break out in 2026-27?
Looking at some young Pittsburgh Penguins players that could take a big step forward next season.
With potential split from CSC on the table, college sports leaders struggling to find solutions to money problems — 'The Big Ten and SEC should break away and do their own deal'
Scientists May Have Found the Blueprint of the Human Body at the Bottom of the Ocean
Scientists discovered that the brainless sea anemone build their bodies with a technique common in bilaterians... which is what humans are.
Ohio State football is high up on CBS Sports' post-spring college football rankings ahead of a notable team
Spring football has been over for a few weeks for the Ohio State Buckeyes.
Grading the Washington Commanders offseason: Did Washington get better?
The health of Jayden Daniels may still be the key for Washington.
Fantasy Baseball Hitter Waiver Wire: 'Take a flyer on Bolte — because it could hit big'
Vikings Add Playmaker to Summer Roster
The Minnesota Vikings have a full roster entering the summer, filling out the 90-man depth chart with an extra wide […]
USA TODAY Sports feature story looks at evolution of Lincoln Riley
A major USA TODAY Sports feature story offers a compelling look inside the workings of Lincoln Riley and Chad Bowden's USC football operation
Potential federal college sports reform could reshape Florida football
Proposed federal reforms surrounding NIL, transfers and NCAA authority could significantly impact Florida and other SEC football programs.
ESPN expects a breakout season for Raiders RB Ashton Jeanty
ESPN is predicting a breakout season for Las Vegas Raiders running back Ashton Jeanty
The Odds: Rep. Massie’s reelection bid
Cavaliers vs. Knicks: Who has the edge with NBA Finals on the line? Series keys, schedule and prediction
Vikings Front Office Power Struggle & 2026 Schedule Traps
Vikings GM fit-in drama, 2026 schedule traps & AP Ring of Honor fight
UnitedHealth Group stock slides after Berkshire Hathaway exits position in the health insurer
UnitedHealth stock tumbled after Berkshire Hathaway revealed it sold its entire state of health insurer
Lululemon calls founder’s ideas ‘misguided’ in public letter
Lululemon has publicly rejected founder Chip Wilson’s ideas to fix the struggling athleisure brand with some strongly worded criticisms of its former leader.
Trump drops lawsuit against IRS amid talks of establishing a $1.8 billion fund for allies
President Donald Trump is dropping his $10 billion lawsuit against the Internal Revenue Service, according to court documents, a signal that the administration is preparing to go forward with a plan to set up $1.8 billion fund that would compensate those who believe they were subject to unfair investigations under previous administrations.
Bleacher Report's Kristopher Knox predicts another rough Browns season
Despite a remade offense one analyst believes not much will change for Cleveland in 2026.
Kentucky football is predicted to get a big recruiting win
The Kentucky Wildcats are poised to add another top 2027 talent, gaining a prediction for a four-star cornerback.
Pete Crow-Armstrong gets into heated exchanges with fans during tense Cubs-White Sox series
Why the Broncos don't let players wear these 6 jersey numbers
The Broncos only have three officially retired jersey numbers, but they also hold back three other numbers.
Aaron Rodgers has reported to the Steelers facility
Ranking the NFL's Christmas games for the 2026 season
The NFL’s 2026 Christmas schedule features rivalry games, playoff rematches, and several potential postseason previews.
⛳️ Y! Sports AM: Everybody loves Aaron
Aaron Rai outclassed the field to win the PGA Championship.
What’s top of mind for your business owner clients right now
Drawing on findings from the 2026 Principal® Business Owner Insights survey, this panel discussion covers the evolving priorities shaping financial planning decisions.
New TV shows to watch this week: Tune in to 'Dutton Ranch' on the Paramount Network, stream 'The Other Bennet Sister' on BritBox and catch 'Mr. Bigstuff' on Hulu
"Yellowstone" gets another spinoff — and "Pride and Prejudice" fans are in for a treat.
24 days to the World Cup: The Italy legend now leading Uzbekistan
Cannes fashion in pictures: Kristen Stewart brings her edge, Bella Hadid does Hollywood glamour, Cate Blanchett goes backless and more unmissable moments
The Cannes Film Festival has always been about more than movies — and these stars prove it.
McFarlane on Alonso appointment, player fitness and Spurs
Chelsea interim boss Calum McFarlane has been speaking to the media before Tuesday's Premier League game against Tottenham at Stamford Bridge (kick-off 20:15 BST). Chelsea announced former Real Madrid boss Xabi Alonso as their new manager on Sunday.
Brian Kemp passed on a Georgia Senate run. Then he threw himself in the middle of the GOP primary
Brian Kemp may not be running for US Senate — but the Georgia governor is campaigning like his name is on the ballot.
Lululemon takes battle with Chip Wilson public, calls founder 'misguided' and 'outdated'
Lululemon responded publicly to founder Chip Wilson's campaign in a letter to shareholders, where it urged them to vote in its favor at its annual meeting.
Target RWE and NoviSci Rebrand as Pedestal Health and Headwater Science
DURHAM, N.C., May 18, 2026--Target RWE and NoviSci, two leaders in evidence generation, today announced they will rebrand as Pedestal Health and Headwater Science. These two distinct companies will work to build a modern evidence-generation engine for life sciences organizations, navigating the most complex and consequential research challenges.
Why Teams Don’t Just Lose—They Change
Today’s guest column is from professors John Cairney and Rick Burton. With spring here, we thought we’d look at what sports leaders can learn from fishing—or more accurately, from a particular fish, a glass wall and what happens when the environment thwarts an organization’s best attempts to reach a goal To borrow from behavioral science, …
Leeds 1-0 Brighton
Brighton looked dangerous when attacking and so did we. Looked like a 0-0 then Dominic Calvert-Lewin capitalised on a Brighton error and we won the game. Mark: Leeds' never-say-die approach is just awesome.
Baidu beats first-quarter forecasts as AI business drives strong growth (BIDU)
Baidu (NASDAQ:BIDU) shares climbed more than 2% in premarket trading on Monday after the Chinese technology group delivered first-quarter revenue and earnings ahead of market expectations, supported by rapid expansion in its AI-related operations. AI-powered business becomes major revenue contributorThe company reported quarterly revenue of 32.
Arsenal Women to let England youth international leave for US
Arsenal midfielder and England youth international Laila Harbert is on the verge of joining American club San Diego Wave.
Wolves 1-1 Fulham
The so-called best players could not hack it in the Premier League so we will sell them and buy real quality to play in the Championship. If Mr Edwards can't design and motivate the team that will most likely form the nucleus of next season's offering, how do we think the results will be any different in the Championship? Fulham were stringing passes together when attacking but we struggled.
Democrats, Tiffany face tricky politics after killing tax relief bill
Democratic lawmakers and Republican governor candidate Tom Tiffany face tricky messaging after working to kill a bill to aid taxpayers and schools.
Inside Amer Sports: Retail excellence in Shanghai
“Inside Amer Sports” is a new video series offering a behind-the-scenes look at the people, places, and experiences shaping Amer Sports around the world.
The Bear’s Den, May 18, 2026
The Chicago Bears are offseasoning hard right now, and so are we. Join us for the ride.
Bengals News (5/18): Schedule Strength
The Bengals look like they could be in a good spot after some big initial tests.
🚨 José Mourinho and Real Madrid: it’s all done! (reports)
Official announcement imminent.José Mourinho is indeed set to become Real Madrid’s next manager.Fabrizio Romano reported this Monday morning that everything has been finalized between the Madrid cl...
Trump has only one real option to slash gas prices
The energy crisis is a financial nightmare for Main Street and a political nightmare for the White House.
Trump’s MAGA Supreme Court lawyer breaks tradition, but the justices embrace it
Over the past year, US Solicitor General D. John Sauer has been pushing the boundaries of the law at the Supreme Court with a delivery that is quickfire, confrontational and imbued with MAGA attitude.
Patriots assistant coach participating in NFL accelerator program
Terrell Williams will be among 16 coaches participating in the revived program.
49ers News: One week closer
Your daily San Francisco 49ers news for Monday, May 18th, 2026
Europe’s poverty divide: Which cities and regions are most at risk?
The share of people at risk of poverty or social exclusion in Europe varies not only across countries but also across capital cities and regions. Euronews Business takes a closer look at these gaps.
Kyowa Hakko highlights Cognizin citicoline’s science-backed cognitive health benefits
Kyowa Hakko USA is spotlighting citicoline’s benefits for cognitive performance and long-term brain health through multiple complementary mechanisms. The supplier will exhibit its citicoline ingredient Cognizin at this week’s Complementary Medicines Australia (CMA) Innovation Day 2026 in Sydney, Australia (May 21). CMA Innovation Day is one of Australia’s annual industry gatherings for the nutraceuticals supply chain, showcasing the latest innovations shaping the market for vitamins, minerals, and supplements in Australia and the Asia-Pacific region.
Watch: Ligue 1 match abandoned after ultras storm the pitch
The Ligue 1 match between Nantes and Toulouse was abandoned after fans invaded the pitch and threw flares after just 22 minutes of play.
Total team effort lifts Hillsdale boys track to regional championship
In front of a home crowd, the Hillsdale varsity boys track and field team used a true team effort to win a region title. Jonesville boys took second.
‘It’s not supposed to look like you’re going to dive in’: Historians criticize Trump’s Reflecting Pool makeover as group sues
Workers with boots dyed an “American Flag Blue” have painted over about two-thirds of the iconic Lincoln Memorial Reflecting Pool, covering the dull gray with bright azure following a directive by President Donald Trump to expedite the pace of the project.
Exeter batteries drained in Harlequins loss
Exeter boss Rob Baxter says his side looked like a team in need of a rest during their 41-24 defeat by Harlequins.
O'Neill urges Celtic to move quick on manager
Celtic manager's advice to club, Hearts boss on title pain and Aberdeen defender linked with move.
Stories, scheduling & spectacle - five takeaways from 2025-26 WSL
With the 2025-26 season in the books, BBC Sport answers five pertinent questions from the Women's Super League.
Rasmus Hojlund: Napoli striker seals permanent switch in style
Manchester United had two players in loan action on Sunday.To find out where all of Manchester United’s loanees are plying their trade this season, click here.Rasmus HojlundThe Dane helped Napoli se...
Don Mattingly Reveals Strategy Again Paul Skenes After Phillies Win
We have to give credit where credit is due, and that's exactly what the Philadelphia Phillies deserve.
David Bednar Stat is Very Concerning for Yankees' Future
It's been an ugly past week or so for the New York Yankees, a very concerning sign for a team that was one of the best in Major League Baseball prior to this. Now sitting at 28-19, the Yankees are 3-7 over their last 10 games and are three games behind the first-place Tampa Bay Rays in the American League East.
Are the Knicks and Cavs really the best the East has to offer to the Thunder or Spurs?
Could Aday Mara fill Hawks’ longstanding need in the middle?
As the NBA Draft approaches, the Atlanta Hawks may have a chance to address one of their biggest long-term needs by selecting one of the fastest-rising prospects in the class: Aday Mara. Mara has rapidly become one of the fastest-rising names in this year’s draft class following an impressive NCAA Tournament run and eye-opening performances at the NBA Combine. Atlanta’s need at center has become increasingly clear over the past few seasons.
Mystery grows around absent congressman facing tough reelection
Tom Kean Jr.’s months-long absence from Capitol Hill is the talk of the town in Washington. Where is the man? No one is saying
Trump’s vendettas deliver, but at what cost to the GOP?
President Donald Trump is lining up new targets after felling yet another Republican critic in a retribution campaign that he finds deeply satisfying but that comes with widening political risks for his party.
“Obviously a disappointing series right here. Fell …
“Obviously a disappointing series right here. Fell …
Jarrett Allen said that #Cavs owner Dan Gilbert sent …
Jarrett Allen said that #Cavs owner Dan Gilbert sent …
There's Always Stuart Skinner: Oilers UFA Market Looks Slim
Stan Bowman might need to find a starting goaltender this summer, but the UFA market has looked him dead in the eyes and shrugged.
Cavaliers owner Dan Gilbert reportedly sent 25 bus loads of Cleveland fans to Detroit for Game 7 romp over Pistons
Gilbert is doing his best to mitigate Detroit's home-court advantage for Sunday's Game 7 against the Pistons.
1 Key Offensive Area Baltimore Orioles Must Improve In
The Orioles have a clear flaw that's holding them back.
MN Capitol deadline: Lawmakers rush to finish business before session ends
The clock is ticking at the Minnesota State Capitol as lawmakers race to pass several high-profile bills before the legislative session ends at midnight.
Spurs vs. Thunder: Who wins epic West showdown with NBA Finals on the line? Series keys, schedule and prediction
Pistons' refusal to swing big culminates with embarrassing Game 7 loss at home
NBA reveals Cavs vs. Knicks Eastern Conference Finals schedule
The Eastern Conference Finals start Sunday afternoon.
Cavaliers crush Pistons to reach conference finals: Instant takeaways
The Cleveland Cavaliers dominated the top-seeded Pistons in Detroit in Game 7 of their playoff series and will meet the New York Knicks next.
Cavs dominate Game 7, punch ticket to Eastern Conference Finals
The Cavs hammered Detroit and secured a rematch with New York.
Thailand to Pare 7,000 Business Rules to Lure Foreign Investment
Prime Minister Anutin Charnvirakul’s government plans a sweeping reform of more than 7,000 business regulations, aiming to cut bureaucratic hurdles and accelerate investment as it tries to compete for global capital.
Every Florida State player drafted by the Golden State Warriors
Let's take a look at every player who has been drafted by the Warriors out of Florida State.
Cowboys Content Corner: Year 2 offense? Ezeiruaku gains, new schedule
A look at the latest content creators efforts to keep the fanbase informed.
'Work when nobody's looking': How Aaron Rai parlayed two gloves, iron covers and a dream into a PGA Championship
Texans RB Drops Honest Opinion on David Montgomery
Woody Marks envisions a "party" in the backfield as he embraces a dual-threat partnership with Detroit’s former star to ignite Houston's postseason push this fall.
Reflecting On The Buffalo-Canadiens Game
Stars at the ACM Awards do the iconic 'Let's Go Girls' by Shania Twain
Shania Twain hosted the 2026 Academy of Country Music Awards in Las Vegas. Watch stars say her iconic line on the red carpet.
2026 ACM Awards winners: Ella Langley wins Song of the Year, as Avery Anna, Tucker Wetmore win New Artist categories
The 2026 ACM Awards nominations are dominated by women including Megan Moroney, Miranda Lambert, Ella Langley and Lainey Wilson, while Morgan Wallen's Male Artist of the Year snub and Zach Top's break...
Patriots WR Kayshon Boutte isn't participating in offseason workouts
USC baseball drops thrilling series at Oregon
It was a thrilling few days up in Eugene, as the Trojans and Ducks battled it out in three incredible games
Kate Martin scores first points with Sparks
After being held scoreless in her Sparks debut, Kate Martin got on the board on Sunday night.
A’s Bullpen, Defense Collapse in Series-Deciding Loss to Giants
Late-inning surge by Giants spoils A’s Comeback bid in rubber-match