Explore tools, prompts, skills, news and resources related to AI 第18页.
Prompt works related to AI 第18页
Latest articles, prompts, use cases and editorial content about AI 第18页
AURA 2.0 is a streaming video large language model that introduces Model-Initiated Conversation, allowing it to identify discussion-worthy topics in an evolving video stream and start interactions without a user query. I...
The paper introduces LEAD-RL, a joint main-agent/subagent training framework for multi-agent deep-research systems that uses contribution-aware credit assignment. A training-time rubric scores the research utility of eac...
Researchers introduce SeeEEG, which renders EEG signals as waveform or scalogram images so a frozen vision transformer can serve as an EEG encoder. Only the display parameters are learned, amounting to at most 1,113 trai...
Skill Adapter is a new system that enables LLM agents to personalize and route general-purpose skills in long-horizon tasks. It distills user-specific adjustments into Adapters linked to base skills, and a routing agent...
AnalogLayoutWorld is an open-source benchmark with 40 expert-reviewed tasks for end-to-end analog circuit layout generation from fixed transistor-level netlists. It integrates a design environment with physical and post-...
This paper tests whether language models can compile known game mechanics directly into neural network weights, without training, using 20 unpublished ARC-AGI-3-style game families. With a fixed 57k-parameter recurrent a...
GS Caltex connects no-code models built in Amazon SageMaker Canvas to production workflows in SageMaker Pipelines, reusing Data Wrangler preprocessing flows and registered models. The company reports deployment time drop...
The paper proposes a zero-or-T thinking paradigm in which a single model either answers from implicit computation in one forward pass without generating tokens or performs full autoregressive reasoning when the expected...
Lara Mini Base is a 7.2B-parameter mixture-of-experts model with 0.6B active parameters, trained from scratch on 6T tokens spanning English and 44 other languages, covering all 24 official EU languages. It supports 128k-...
The paper introduces S1-Evo, an attack framework targeting typed System-1 decision models used in LLM agents for routing, moderation, and authorization. S1-Evo perturbs untrusted fields through contract-aware evidence ch...
Mantis 2 is a foundation model for infectious disease forecasting that blends simulated outbreak data with observational training data. It can jointly forecast up to six variables sixteen weeks ahead and outperformed mac...
Kezek is a model that converts mono recordings of exactly two people into separate per-speaker tracks while preserving original timing, overlaps, and short replies. It uses a two-stage design: a two-voice activity model...
Researchers introduce SPADE, a framework that detects AI-generated text by measuring how well a prompt explains a candidate text using a Pointwise Mutual Information term. SPADE trains one soft prompt per class and predi...
Researchers show that bit-exact linguistic steganography fails when receiver hardware, precision, quantization, or scoring mode differs from the sender's setup. They introduce STEALTH, which uses keyed pseudorandom...
Researchers propose a multi-bit LLM watermarking scheme that maps an n-bit payload to a longer u-bit codeword and embeds it during generation via token-level logit biasing. Extraction matches the received bit sequence to...
The paper presents a systematic ten-step workflow for LLM-assisted formal verification of scientific algorithms in Dafny, covering formalization, contracts, invariant validation, proof construction, bottleneck profiling,...
AWS announces the availability of OpenFold3-preview on Amazon SageMaker JumpStart, enabling deployment of the open-source biomolecular structure prediction model with a few lines of code. The model predicts 3D structures...
AWS explains how AgentCore runtime's platformVersion "V2" replaces per-session container initialization with a build-once snapshot approach: the container is started, warmed until it passes its /ping healt...
AWS describes a deployable sample that routes coding-agent requests on Amazon Bedrock through LiteLLM and NVIDIA NeMo Switchyard. The sample offers Stage routing between a capable Claude model and a lower-cost Nemotron m...