Sony Pixel Power calrec Sony

Next-Gen Neural Networks: NVIDIA Research Announces Array of AI Advancements at NeurIPS

25/10/2023

NVIDIA researchers are collaborating with academic centers worldwide to advance generative AI, robotics and the natural sciences - and more than a dozen of these projects will be shared at NeurIPS, one of the world's top AI conferences.

Set for Dec. 10-16 in New Orleans, NeurIPS brings together experts in generative AI, machine learning, computer vision and more. Among the innovations NVIDIA Research will present are new techniques for transforming text to images, photos to 3D avatars, and specialized robots into multi-talented machines.

NVIDIA Research continues to drive progress across the field - including generative AI models that transform text to images or speech, autonomous AI agents that learn new tasks faster, and neural networks that calculate complex physics, said Jan Kautz, vice president of learning and perception research at NVIDIA. These projects, often done in collaboration with leading minds in academia, will help accelerate developers of virtual worlds, simulations and autonomous machines.

Picture This: Improving Text-to-Image Diffusion Models Diffusion models have become the most popular type of generative AI models to turn text into realistic imagery. NVIDIA researchers have collaborated with universities on multiple projects advancing diffusion models that will be presented at NeurIPS.

A paper accepted as an oral presentation focuses on improving generative AI models' ability to understand the link between modifier words and main entities in text prompts. While existing text-to-image models asked to depict a yellow tomato and a red lemon may incorrectly generate images of yellow lemons and red tomatoes, the new model analyzes the syntax of a user's prompt, encouraging a bond between an entity and its modifiers to deliver a more faithful visual depiction of the prompt.

SceneScape, a new framework using diffusion models to create long videos of 3D scenes from text prompts, will be presented as a poster. The project combines a text-to-image model with a depth prediction model that helps the videos maintain plausible-looking scenes with consistency between the frames - generating videos of art museums, haunted houses and ice castles (pictured above).

Another poster describes work that improves how text-to-image models generate concepts rarely seen in training data. Attempts to generate such images usually result in low-quality visuals that aren't an exact match to the user's prompt. The new method uses a small set of example images that help the model identify good seeds - random number sequences that guide the AI to generate images from the specified rare classes.

A third poster shows how a text-to-image diffusion model can use the text description of an incomplete point cloud to generate missing parts and create a complete 3D model of the object. This could help complete point cloud data collected by lidar scanners and other depth sensors for robotics and autonomous vehicle AI applications. Collected imagery is often incomplete because objects are scanned from a specific angle - for example, a lidar sensor mounted to a vehicle would only scan one side of each building as the car drives down a street.

Character Development: Advancements in AI Avatars AI avatars combine multiple generative AI models to create and animate virtual characters, produce text and convert it to speech. Two NVIDIA posters at NeurIPS present new ways to make these tasks more efficient.

A poster describes a new method to turn a single portrait image into a 3D head avatar while capturing details including hairstyles and accessories. Unlike current methods that require multiple images and a time-consuming optimization process, this model achieves high-fidelity 3D reconstruction without additional optimization during inference. The avatars can be animated either with blendshapes, which are 3D mesh representations used to represent different facial expressions, or with a reference video clip where a person's facial expressions and motion are applied to the avatar.

Another poster by NVIDIA researchers and university collaborators advances zero-shot text-to-speech synthesis with P-Flow, a generative AI model that can rapidly synthesize high-quality personalized speech given a three-second reference prompt. P-Flow features better pronunciation, human likeness and speaker similarity compared to recent state-of-the-art counterparts. The model can near-instantly convert text to speech on a single NVIDIA A100 Tensor Core GPU.

Research Breakthroughs in Reinforcement Learning, Robotics In the fields of reinforcement learning and robotics, NVIDIA researchers will present two posters highlighting innovations that improve the generalizability of AI across different tasks and environments.

The first proposes a framework for developing reinforcement learning algorithms that can adapt to new tasks while avoiding the common pitfalls of gradient bias and data inefficiency. The researchers showed that their method - which features a novel meta-algorithm that can create a robust version of any meta-reinforcement learning model - performed well on multiple benchmark tasks.

Another by an NVIDIA researcher and university collaborators tackles the challenge of object manipulation in robotics. Prior AI models that help robotic hands pick up and interact with objects can handle specific shapes but struggle with objects unseen in the training data. The researchers introduce a new framework that estimates how objects across different categories are geometrically alike - such as drawers and pot lids that have similar handles - enabling the model to more quickly generalize to new shapes.

Supercharging Science: AI-Accelerated Physics, Climate, Healthcare NVIDIA researchers at NeurIPS will also present papers across the natural sciences - covering physics simulations, climate models and AI fo
LINK: https://blogs.nvidia.com/blog/2023/10/25/neurips-ai-research/...
See more stories from nvidia

Most recent headlines

06/10/2025

France Tlvisions Wins Prestigious 2025 EBU Technology & Innovation Award in Groundbreaking Collaboration with Dalet

France T l visions, France's leading broadcaster, has received the 2025 EBU ...

04/09/2025

Monumental Sports & Entertainment and Dalet Win Prestigious 2025 NAB Show Project of the Year Award

Monumental Sports & Entertainment (MSE), in collaboration with Dalet, has been a...

16/06/2025

Give Me the Backstory: Get to Know Carmen Emmi, the Writer-Director of Plainclothes

By Bailey Pennick One of the most exciting things about the Sundance Film Festi...

16/06/2025

Spotify's Brian Berner on Creativity, Connection, and What's Next for Advertisers at Cannes Lions

The Cannes Lions International Festival of Creativity is officially underway for...

16/06/2025

Francophone Content on Spotify Continues to Thrive Around the World

On Spotify, francophone content continues to cross borders at an unprecedented rate. In 2024 alone, more than 123 million listeners worldwide streamed audio con...

16/06/2025

Tegna Announces Major Expansion of Local News Programming

TYSONS, Va. Tegna Inc. is embarking on a notable expansion of their already substantial local news programming by launching live and on-demand, local newscasts ...

16/06/2025

Netflix Expands Programmatic Ad Sales with Yahoo DSP

Netflix has announced that it is expanding its global programmatic ad offerings by partnering with Yahoo DSP. This will enable brands to buy Netflix advertising...

16/06/2025

Sub51 & Soundtrax announce Drop Pad 3

Instrument now boasts full NKS support Sub51 and Soundtrax have just announced the launch of an updated and improved version of their innovative sample-base...

16/06/2025

Roku, Amazon Team Up to Dominate CTV Ad Market

NEW YORK In a landmark agreement to overtake the burgeoning connected TV (CTV) advertising market, Amazon Ads and Roku today announced a new integration that gi...

16/06/2025

EdgeBeam Wireless Names Conrad Clemson CEO

ATLANTA, BALTIMORE, CINCINNATI and IRVING, Texas The four major broadcast groups behind the ATSC 3.0-based EdgeBeam Wireless datacasting joint venture today nam...

16/06/2025

Amazon MGM Studios to Deploy Avid Tools on AWS

BURLINGTON, Mass. Avid today announced an extended agreement with Amazon MGM Studios to integrate Avid's Media Composer and Avid NEXIS on Amazon Web Service...

16/06/2025

Maxon Epic Sale Drops June 16

Maxon, maker of powerful, approachable software for creators working in 2D and 3D design, motion graphics, visual effects, gaming and more, today announced the ...

16/06/2025

Alfalite launches Skypix a new ceiling-mounted Led panel...

Alfalite, the only European manufacturer of LED displays, announces the launch of SKYPIX RGBW & IM, a new series of ceiling-mounted LED panels designed specifi...

16/06/2025

ALM/Busy Circuits launch Pip Filter & LFO

Two new compact 4HP modules introduced ALM/Busy Circuits have just announced the launch of two new Eurorack modules, the Pip Filter and Pip LFO, both of whi...

16/06/2025

VEON Announces USD 35 Million Share Buyback

16 Jun 2025 VEON Announces USD 35 Million Share Buyback Announcement marks the third phase of USD 100 million share buyback program Dubai, June 16, 2025: VEON...

16/06/2025

Summer Sale: Big Discounts on Ivory II Pianos - Now Through June 30th!

Save 40% or More on All Ivory II Collections!From now through June 30th, enjoy huge savings on all Ivory II Piano Collections. Our biggest discounts ever are be...

16/06/2025

Behind The Broadcast Booth, Ep. 3: Golf. My Future. My Game. Founder and CEO Craig Kirby Talks Advocacy in Sports and More

Behind The Broadcast Booth, Ep. 3: Golf. My Future. My Game. Founder and CEO Cra...

16/06/2025

The REMI Revolution Is Here: How Remote Production Technology in Esports Pioneers a New Age of Broadcast

The REMI Revolution Is Here: How Remote Production Technology in Esports Pioneer...

16/06/2025

From Super Bowl to Indy 500, New Orleans Artist Frenchy' Captures Energy of Sports Production on Canvas

From Super Bowl to Indy 500, New Orleans Artist Frenchy' Captures Energy of...

16/06/2025

NFL Films Enhances Post Studio With Dolby Atmos Audio

NFL Films Enhances Post Studio With Dolby Atmos Audio Forty-three channels of audio enable the facility to migrate to immersive By Dan Daley, Audio Editor Mo...

16/06/2025

SVG New Sponsor Spotlight: Storj's David Colantuoni on Expanding Cloud-Based Storage to Live Sports Production

SVG New Sponsor Spotlight: Storj's David Colantuoni on Expanding Cloud-Based...

16/06/2025

Grass Valley 4K Cameras Head to Greece for View Master Events' New OB Truck

Grass Valley 4K Cameras Head to Greece for View Master Events' New OB Truck By Ken Kerschbaumer, Editorial Director Monday, June 16, 2025 - 2:33 pm Pri...

16/06/2025

WWF and Sky Kids launch Wear it Wild with Ready Eddie Go!

Monday 16 June 2025 Families and children are invited to dress up, have fun and raise money to protect nature WWF UK and Sky Kids are teaming up to launch Wea...

16/06/2025

The Rohde & Schwarz R&S M3AR radio family reaches 10,000 unit milestone, demonstrating commitment to innovation and quality

The Rohde & Schwarz R&S M3AR radio family reaches 10,000 unit milestone, demonst...

16/06/2025

FOX Advertising Launches Enhanced Brand Storytelling Program with Strategic Investment in The Lighthouse

FOX Advertising Launches Enhanced Brand Storytelling Program with Strategic Inve...

16/06/2025

Run With Ray in Cork, Waterford, Kilkenny, Drogheda and Dublin as The Ray D'Arcy Show hits the road

Run with Ray is back! RT Radio 1's The Ray D'Arcy Show hits the road th...

15/06/2025

Music Production for Women free in-person workshops

July 2025 in Dublin, Berlin, Amsterdam & London Photo: Thea Martre Music Production for Women (MPW) have announced that they will be running a series of fo...

15/06/2025

Jason's Piano & API Drums instruments from Sulcata Sound

Composer/producer launches free virtual instruments Sulcata Sound is the latest venture of Jason Graves, a two-time British Academy Award-winnning composer,...

14/06/2025

Pluto TV Adds All Womens Sports Network's FAST Channel

NEW YORK Pluto TV and the All Womens Sports Network have launched a free ad-supported streaming TV (FAST) AWSN channel in the U.S., Canada, the U.K. and the Nor...

14/06/2025

Scripps Inks Multiyear Agreement for WNBA Games on Ion

NEW YORK and CINCINNATI E.W. Scripps has announced a new, multiyear agreement with the WNBA that will continue Ions regular-season coverage of the league on Fri...

14/06/2025

NAB Highlights Hidden Importance of Spectrum in Major Sports Broadcasting

WASHINGTON The National Association of Broadcasters highlighted the hidden importance of spectrum in the production of major sporting events and described wha...

14/06/2025

1.0 Sunset, BPS and NextGen Broadcast's Potential Dominate ATSC Meeting

WASHINGTON Sunsetting ATSC 1.0, expanding business opportunities for NextGen Broadcast and increasing international adoption of the ATSC 3.0 standard were top o...

14/06/2025

Samba TV and Acxiom Announce Massive 40-market Global Expansion

SAN FRANCISCO Samba TV and Acxiom have announced that they will dramatically expand their longstanding relationship....

14/06/2025

MPW announce free in-person workshops

July 2025 in Dublin, Berlin, Amsterdam & London Photo: Thea Martre Music Production for Women (MPW) have announced that they will be running a series of fo...

14/06/2025

San Francisco State University's School of Cinema Uses Blackmagic Design

San Francisco State University's School of Cinema Uses Blackmagic Design Brie Clayton June 13, 2025 0 Comments More than 40 Blackmagic Design came...

14/06/2025

Boris FX Mocha Pro Adds New AI Tools To Tackle VFX Tasks Fast

Boris FX Mocha Pro Adds New AI Tools To Tackle VFX Tasks Fast Jessie Electa Petrov June 13, 2025 0 Comments The 2025.5 release helps artists work more...

14/06/2025

AJA Debuts DRM2-Plus Mini-Converter Frame at InfoComm 2025

AJA Debuts DRM2-Plus Mini-Converter Frame at InfoComm 2025 Brie Clayton June 13, 2025 0 Comments Next-gen frame addresses diverse rackmount needs wit...

13/06/2025

Prime Minister: A Behind-the-Scenes Look at a Leader Who Champions Kindness

(L-R) Lindsay Utz, Michelle Walshe, and The Right Honourable Dame Jacinda Ardern attend the 2025 Sundance Film Festival premiere of Prime Minister at Eccles T...

13/06/2025

Materialists' Director Celine Song Reveals the Inspirations Behind the Film's Soundtrack

Photo credit: Atsushi Nishijima If you're a true lover of rom-coms, chances...

13/06/2025

Pure Drama and Fierce Rivalries set to dominate the world's most iconic sporting event

Pure Drama and Fierce Rivalries set to dominate the world's most iconic spor...

13/06/2025

Press Release: NFVF Opens Call for Public Film Screenings on GBV Awareness as South Africa Confronts Ongoing Femicide Crisis

Johannesburg, 12 June 2025 - The National Film and Video Foundation (NFVF), an a...

13/06/2025

Central Texas Storm Knocks out KTXS Tower, Severely Damages Building

ABILENE. Texas A severe storm knocked down the tower and severely damaged the news studio and main facility of Sinclair-owned KTXS here on Sunday, June 8....

13/06/2025

Berklee's Music Business/Management Department Recognized by the Music Biz Association

Berklee's Music Business/Management Department Recognized by the Music Biz A...

13/06/2025

ATSC Honors Aldo Cugnini, Clarence Hau

WASHINGTON The ATSC, the Broadcast Standards Association, honored veteran technologist Aldo Cugnini and Clarence Hau, Senior Vice President of Standards, Policy...

13/06/2025

ESPN Doubles Down on Immersive Fan Experience for UFL Championship

(Editor's note: The 2025 UFL Championship Game between the D.C. Defenders and Michigan Panthers kicks off Saturday, June 14, at 8 p.m. Eastern. The game wil...

13/06/2025

Soulyft Audio release Chime

New iPad/iPhone synth App announced Following on from last year's release of Gradient Synth - which reached #6 on the App Store's Paid Music charts ...

13/06/2025

HBO Max Plans July Launches in 12 New Markets

LONDON Warner Bros. Discovery has announced that HBO Max will launch direct-to-consumer in multiple new countries this July as the streamer becomes available in...

13/06/2025

Verbit Launches Speaker Identification for Live ASR Broadcast Captions

AI voice transcription and captioning platform Verbit has added a new feature to its Captivate ASR solution the ability to identify specific features in automat...

13/06/2025

FCC's Anna Gomez Meets with TV Networks, Studio Execs and Unions

WASHINGTON Federal Communications Commission member Anna Gomez has wrapped up two weeks in California visiting broadcasters, television studio executives, enter...