lab NVIDIA Research · 2h ago · research

AITE framework autonomously discovers wireless algorithms via LLM-driven search

from English

Researchers introduce The AI Telco Engineer (AITE), a framework that uses large language model-driven evolutionary search to autonomously design algorithms for complex communication problems while navigating performance-complexity tradeoffs.

AITE designs an equalizer for orthogonal time-frequency space (OTFS) systems, outperforming best-known solutions and reducing computational latency by a factor of 3.6 compared to the strongest baseline.
The framework constructs a receiver algorithm for orthogonal frequency-division multiplexing (OFDM) systems using a custom constellation and operating without pilots, discovering the first explicit, explainable algorithms that achieve performance parity with state-of-the-art neural receivers.

These results demonstrate the strong potential of LLM-driven evolutionary search for the autonomous discovery of next-generation wireless communications algorithms.

Importance 1/3 Trust 3/3 NVIDIA Research NVIDIA AI agents Research paper

Read original

arxiv arXiv cs.LG · 15d ago

NVIDIA introduces ARDY for real-time interactive human motion generation

NVIDIA researchers present ARDY, a streaming generation framework designed to enable high-fidelity 3D human motion synthesis in real-time interactive applications. The system bridges the gap between offline precision and online speed by combining explicit root features with latent body embeddings.

arxiv arXiv cs.AI · 16h ago

AREX introduces recursively self-improving deep research agents

Researchers introduce AREX, a family of Recursively Self-Improving (RSI) deep research agents designed to address the discovery-verification asymmetry in complex queries. AREX alternates between an inner loop that gathers evidence and constructs provisional answers, and an outer loop that audits constraints to guide targeted refinement.

arxiv arXiv cs.CL · 2d ago

Solar Open 2 Technical Report

The Solar Open 2 Technical Report introduces Solar Open 2, a 250B-A15B Mixture-of-Experts language model designed for long-horizon agentic tasks. It achieves a 1M-token context window through a hybrid attention stack and is trained using efficient initialization from Solar Open 1 and curated high-value data.

lab NVIDIA Research · 2d ago · 1 view

NVIDIA introduces CTRL-G for controllable generative graphics in games

NVIDIA has introduced CTRL-G (Controllable Generative Graphics for Games), a framework designed to address the challenge of controlling generative AI systems within interactive game environments.

media Hugging Face Forums · 3d ago

SEMA explores non-transformer AI architecture using Vector Symbolic Architecture

SEMA is an experimental AI architecture that investigates whether language understanding and reasoning can emerge from explicit semantic structure rather than next-token prediction. It serves as a non-parametric, instance-based reasoning system utilizing Vector Symbolic Architecture (VSA/HDC) over content-addressable memory.