←Search results

Search “NVIDIA”

By relevance · Total 2019 results Clear search

Wednesday

  5. SiliconANGLE

    Arda Industries raises $232 million to make production lines easier to adjust with AI

    Arda Industries officially launched with $232 million in funding, led by Accel, Altimeter, Founders Fund and Khosla Ventures, with participation from XYZ Venture Capital, 8VC, SVAngel and Felicis. The company's co-founder and CEO is Bob McGrew, former Chief Research Officer at OpenAI. Its platform lets users upload product blueprints and then automatically plan production lines, determine which robots to use and generate visual work instructions. Its current customers are concentrated in defense and data center electronics; Anduril uses it to optimize production lines. The company's long-term plan is to enter the consumer electronics market and develop AI agents that can adapt to new equipment within days.

    Arda Industries officially launched with $232 million in funding, led by Accel, Altimeter, Founders Fund and Khosla Ventures, with participation from XYZ Venture Capital, 8VC, SVAngel and Felicis. The company's co-founder and CEO is Bob McGrew, former Chief Research Officer at OpenAI. Its platform lets users upload product blueprints and then automatically plan production lines, determine which robots to use and generate visual work instructions. Its current customers are concentrated in defense

    Matched fieldsBody

    #hot-signal#Industry news#Agents
  8. SiliconANGLE

    ASI Completes $325 Million Series C Funding at a $3 Billion Valuation

    AI infrastructure management software company ASI has completed a $325 million Series C funding round at a $3 billion valuation, led by Spark Capital with participation from Citadel Securities, Andreessen Horowitz and others. ASI, formerly known as Air Space Intelligence, builds models that simulate physical reality for the aviation, defense and energy industries, with customers including the FAA, United Airlines, Delta Air Lines, the U.S. Army and National Grid USA. In June of this year, ASI signed an $875 million multi-year contract with the FAA; its software was deployed last month at Washington Dulles International Airport and is planned to expand to major U.S. airports.

    AI infrastructure management software company ASI has completed a $325 million Series C funding round at a $3 billion valuation, led by Spark Capital with participation from Citadel Securities, Andreessen Horowitz and others. ASI, formerly known as Air Space Intelligence, builds models that simulate physical reality for the aviation, defense and energy industries, with customers including the FAA, United Airlines, Delta Air Lines, the U.S. Army and National Grid USA. In June of this year, ASI si

    Matched fieldsBody

    #hot-signal#Industry news#English text is being prepared.
  13. The Decoder

    Sam Altman Reportedly Presented Three AI Safety Endgame Options to Employees

    The Information, citing people familiar with the matter, reported that OpenAI CEO Sam Altman last week internally proposed three AI safety paths: establishing a regulatory body modeled on the International Atomic Energy Agency (IAEA), a lab merger plan known as the Demis Plan, and a single-developer compute monopoly plan known as the Eliezer Plan. Altman also complained that there are too few speed-limit proposals for AI development, while noting that OpenAI cannot afford to fall behind in the competition, and plans to decide on an IPO path within a year. The United States currently relies on voluntary pre-review of new models, and in June imposed export controls on Anthropic on the grounds that the Fable model posed a jailbreak risk.

    The Information, citing people familiar with the matter, reported that OpenAI CEO Sam Altman last week internally proposed three AI safety paths: establishing a regulatory body modeled on the International Atomic Energy Agency (IAEA), a lab merger plan known as the Demis Plan, and a single-developer compute monopoly plan known as the Eliezer Plan. Altman also complained that there are too few speed-limit proposals for AI development, while noting that OpenAI cannot afford to fall behind in the c

    Matched fieldsBody

    #ai-vertical#Safety / alignment#OpenAI#Industry news
  14. Latent Space

    SF Compute CEO Evan Conrad on Programmable Data Centers and the Compute Market

    SF Compute CEO Evan Conrad said on the Latent Space podcast that the compute market must first achieve physical delivery—that is, actually delivering usable GPU compute—before discussing financialization; otherwise, market manipulation and basis risk are likely to arise. He said SF Compute has already put 5% of its capacity on the order book, and that customers who spend $100 to buy capacity can on average recover $25 by reselling it, with hundreds of millions of dollars in trading volume already completed. He also said the company does not hold hardware in order to remain neutral, and that it already supports customers in partitioning InfiniBand fabric online themselves.

    SF Compute CEO Evan Conrad said on the Latent Space podcast that the compute market must first achieve physical delivery—that is, actually delivering usable GPU compute—before discussing financialization; otherwise, market manipulation and basis risk are likely to arise. He said SF Compute has already put 5% of its capacity on the order book, and that customers who spend $100 to buy capacity can on average recover $25 by reselling it, with hundreds of millions of dollars in trading volume alread

    Matched fieldsBody

    #newsletter#Industry news#English text is being prepared.#English text is being prepared.

Tuesday

  1. Unite.AI

    Tsinghua Team Proposes PPMem: Using Planar Primitives to Build Persistent Memory for AI Video World Models

    A team from Tsinghua University has proposed PPMem, which replaces the previous SPMem's volumetric 3D memory with planar primitives to store explored scenes for video world models. Each planar primitive is parameterized by only 7 numbers (center depth, two rectangular extents, and a rotation quaternion), making it orders of magnitude more compact than per-pixel representations. When the camera returns to a previously visited location, the stored planes are projected back into the field of view to guide the generation of new frames, reducing the spatial information that must be retained and processed and preventing familiar objects from changing or disappearing upon revisits.

    A team from Tsinghua University has proposed PPMem, which replaces the previous SPMem's volumetric 3D memory with planar primitives to store explored scenes for video world models. Each planar primitive is parameterized by only 7 numbers (center depth, two rectangular extents, and a rotation quaternion), making it orders of magnitude more compact than per-pixel representations. When the camera returns to a previously visited location, the stored planes are projected back into the field of view t

    Matched fieldsBody

    #hot-signal#Papers/Research#Video#Multimodal
  3. Zyphra Research

    Zyphra Inference Wave 2: Accelerating MoE and Long-Context Inference Serving on MI355X

    Zyphra has released ZOE, its second-generation inference optimization, which on AMD Instinct MI355X reduces GLM-5.3's time to first token (TTFT) at 512K context from 178.8 seconds to 64.6 seconds (2.8x), and from 42.3 seconds to 11.8 seconds (3.6x) at 90% prefix cache hit rate. Its CSA top-K selection HIP kernel raises DeepSeek-V4-Pro's single-user decode throughput at 1M context from 43.5 to 61.1 tokens/s (1.40x). AMD MXFP4 quantization of GLM-5.3 shrinks the model from 756 GB to 410 GB, with benchmark scores such as AIME25 within 3 points of FP8.

    Zyphra has released ZOE, its second-generation inference optimization, which on AMD Instinct MI355X reduces GLM-5.3's time to first token (TTFT) at 512K context from 178.8 seconds to 64.6 seconds (2.8x), and from 42.3 seconds to 11.8 seconds (3.6x) at 90% prefix cache hit rate. Its CSA top-K selection HIP kernel raises DeepSeek-V4-Pro's single-user decode throughput at 1M context from 43.5 to 61.1 tokens/s (1.40x). AMD MXFP4 quantization of GLM-5.3 shrinks the model from 756 GB to 410 GB, with b

    Matched fieldsBody

    #lab#Product updates#Reasoning#English text is being prepared.