Explore tools, prompts, skills, news and resources related to stream 第7页.
Prompt works related to stream 第7页
Latest articles, prompts, use cases and editorial content about stream 第7页
Thinking Machines released Inkling 2 Small, a 594B-total/17B-active multimodal MoE, trained from scratch in 68 hours on 8.4T tokens (NVFP4). It scores 31 on the Artificial Analysis Intelligence Index, beating many same-s...
Researchers introduce CardioCCC, a corpus of 508 cardiology case reports originally in Spanish and extended to Czech, Dutch, English, Italian, Romanian and Swedish via machine translation, annotation projection and clini...
A new arXiv paper identifies a mechanism called the Intrusion Pathway that explains why language models lose accuracy when prompts contain irrelevant, off-topic context. The authors localize the problem to a sparse set o...
Researchers propose a training-time approach for human-like navigation in multi-agent scenes, using world models as preference oracles to distill foresight into a fast policy. Two task-aligned world models score candidat...
ReferClaw is an agentic framework for egocentric AI assistants that resolves ambiguous user queries by asking clarifying questions before answering. It uses three cooperating agents to identify candidate interpretations,...
AWS announced general availability of Web Answer on Amazon Bedrock AgentCore, a managed tool that returns synthesized, source-cited answers from web sources with a single tool call. It replaces the custom search-retrieve...
Amazon Marketplace developed a multi-model fusion system on SageMaker AI to evaluate A+ Content quality holistically. The system renders full product pages as snapshots, uses a Vision-Language Model for semantic scoring,...
Baidu has released ERNIE 5.5 Flash Base, a 280-billion-parameter mixture-of-experts foundation model. It was pre-trained on 33.5 trillion tokens. Baidu shipped the model without fine-tuning so developers can adapt it for...
CompressionBench evaluates whether coding agents can autonomously compress pretrained LLMs within storage and time budgets. Across six agents and six model sizes, 29 of 36 submissions passed verification, achieving a 3.4...
NVIDIA introduces a framework adapting Cosmos world foundation models for real-time interactive simulation in Physical AI. It streams visual observations in response to actions and scene controls, supporting both action-...
SumOne is a standalone summarizer that compresses long-horizon agent histories via masked reconstruction, using a frozen reconstructor and GRPO to optimize without task-specific rewards. It reduces inference cost by ~78%...
A new study shows that encoder-based context compression systematically weakens refusal behavior in instruction-tuned language models, even when reconstruction fidelity is high. The effect persists across model families...
CARM is a statistical framework that adapts conformal risk control to temporal distribution shifts in Earth-observation super-resolution. It aggregates threshold proposals from experts with different update rates using a...
This paper describes a production pipeline for generating animated icons for Alexa+ devices from text descriptions, replacing a slow hand-drawn process. The authors focus on improving the critical image generation stage...
Ricursive Intelligence has released Ripple-65B Preview, a 65B dense open-weight model pretrained from scratch for agentic coding. It achieves 80.5 on Terminal-Bench 2.1, the top self-reported score among US open-weight m...
The podcast episode features Hugging Face's policy chief discussing the growing mainstream adoption of open source AI models by enterprises, governments, and startups. It explores how companies can capture value as...
U Mobile's Information Systems Division, with AWS and Axrail, built AiDaH, an agentic helpdesk on Amazon Bedrock AgentCore. It handles over 150 operational scenarios across six divisions, cutting trouble tickets by...
Indegene built a production-grade Data Quality Agent on AWS using Amazon Bedrock, Strands Agents, and AgentCore to generate context-aware data quality rules for life sciences data. The agent combines internal enterprise...
Basin2Vec is a self-supervised framework that learns compact basin representations from hydroclimatic and physiographic data without requiring observed streamflow. It outperforms fixed handcrafted attributes and general-...