산업ENNVIDIA AI Blog
From Simulation to Production: How to Build Robots With AI
The latest open models and frameworks from NVIDIA bring together simulation, robot learning and embedded compute to accelerate cloudtorobot workflows.
AI 뉴스
AI 업계의 최신 소식을 빠르게 확인하세요.
산업ENThe Verge AI
DLSS 5: Has Nvidia’s AI graphics technology gone too far?
Nvidia has revealed a new “3D guided neural rendering model” called DLSS 5 that can change a game’s lighting and materials in realtime, and… many gamers aren’t happy.
연구ENArXiv AI
Neural-Symbolic Logic Query Answering in Non-Euclidean Space
arXiv:2603.15633v1 Announce Type: new Abstract: Answering complex firstorder logic FOL queries on knowledge graphs is essential for reasoning. Symbolic methods offer interpretability but struggle with incomplete graphs, while neural approaches generalize better but lack transparency.
연구ENArXiv AI
NextMem: Towards Latent Factual Memory for LLM-based Agents
arXiv:2603.15634v1 Announce Type: new Abstract: Memory is critical for LLMbased agents to preserve past observations for future decisionmaking, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations.
연구ENArXiv AI
AIDABench: AI Data Analytics Benchmark
arXiv:2603.15636v1 Announce Type: new Abstract: As AIdriven document understanding and processing tools become increasingly prevalent in realworld applications, the need for rigorous evaluation standards has grown increasingly urgent.
연구ENArXiv AI
The Comprehension-Gated Agent Economy: A Robustness-First Architecture for AI Economic Agency
arXiv:2603.15639v1 Announce Type: new Abstract: AI agents are increasingly granted economic agency executing trades, managing budgets, negotiating contracts, and spawning subagents, yet current frameworks gate this agency on capability benchmarks that are empirically uncorrelated with operational...
연구ENArXiv AI
Form Follows Function: Recursive Stem Model
arXiv:2603.15641v1 Announce Type: new Abstract: Recursive reasoning models such as Hierarchical Reasoning Model HRM and Tiny Recursive Model TRM show that small, weightshared networks can solve computeheavy and NP puzzles by iteratively refining latent states, but their training typically relies...
연구ENArXiv AI
CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems
arXiv:2603.15642v1 Announce Type: new Abstract: Large language model LLM agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns.
연구ENArXiv AI
GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater Infrastructure
arXiv:2603.15643v1 Announce Type: new Abstract: Green Stormwater Infrastructure GSI systems, such as permeable pavement, rain gardens, and bioretention facilities, require continuous inspection and maintenance to ensure longterm performance.
연구ENArXiv AI
Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents
arXiv:2603.15658v1 Announce Type: new Abstract: Memoryaugmented agents maintain multiple specialized stores, yet most systems retrieve from all stores for every query, increasing cost and introducing irrelevant context.
연구ENArXiv AI
DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
arXiv:2603.15661v1 Announce Type: new Abstract: Large Language Modelbased MultiAgent Systems MAS have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent, which behave benignly during routine operation and gradually accumulate...
연구ENArXiv AI
QV May Be Enough: Toward the Essence of Attention in LLMs
arXiv:2603.15665v1 Announce Type: new Abstract: Starting from first principles and a linguistic perspective centered on partofspeech POS and syntactic analysis, this paper explores and derives the underlying essence of the QueryKeyValue QKV mechanism within the Transformer architecture.