Explore tools, prompts, skills, news and resources related to GitHub 第12页.
Latest articles, prompts, use cases and editorial content about GitHub 第12页
Researchers introduce ID-WM, a hierarchical world model that decouples state-space reachability from local control to improve long-horizon planning. A high-level model samples feasible transitions, while a low-level inve...
Deep Principle has released Hydrogen-1.0, a 753B-parameter open-weight scientific model built by post-training Z.ai's GLM-5.3 on domain data, laboratory records, and discovery trajectories. It reports a 38.3% score...
Goldman Sachs is withdrawing AI coding tools such as Claude Code and GitHub Copilot from traders and bankers, limiting access to engineers only. The bank cites productivity and risk management as reasons for the reversal...
This post presents a solution for ingesting web content into Amazon Bedrock Knowledge Bases using Crawl4AI, an open-source Python crawler, when the built-in Web Crawler connector lacks control over content extraction. Th...
Researchers propose SecPO, a principled adversarial training pipeline for defending LLM agents against prompt injection attacks. They introduce a SecPO loss that approximates an idealized injection-invariant reference mo...
Circle K built an automated incident triage system using Amazon Bedrock, reducing mean triage time from 45–60 minutes to under 15 minutes. The system uses agentic AI to investigate alerts, gather context from logs, AWS r...
AWS presents a multi-agent system for aerospace part substitution evaluation, combining Amazon Nova Multimodal Embeddings, Amazon Bedrock AgentCore, and the Strands Agents SDK. The system routes queries across three spec...
This post demonstrates how to use sequence-level knowledge distillation (SeqKD) to fine-tune a smaller student model (Qwen3.5-4B) to replace a frontier teacher (GLM-5.3) for a shopping agent, reducing cost and latency. I...
Researchers propose a framework to align multimodal large language models with human cognitive structure by using a behavior-derived semantic embedding space of 66 dimensions from 4.7 million human Odd-One-Out judgments....
Geo-FSRL introduces a selection principle for stochastic policies in few-step flow models, minimizing conditional KL divergence for velocity-output updates. It derives a closed-form optimizer within a coefficient-preserv...
A sponsored MIT Technology Review piece from HPE argues that per-token pricing misleads when teams deploy agentic coding tools, since agents can consume 10 to 50 times more tokens than simple chat prompts. It recommends...
The paper introduces SWIFT, a sparse tuning framework that combines block-diagonal sparse updates for local feature mixing with a fixed deterministic scattering permutation that routes mixed outputs across feature groups...
EvoMCP is a framework that enables Model Context Protocol (MCP) agents to improve through a closed loop of task evolution, trajectory evolution, and supervised fine-tuning. It assesses the student's capabilities fro...
CryoAtlas is a rigorously curated dataset and unified benchmark for density-guided atomic model building of protein chains from cryo-EM maps. It provides 17,809 map-model-sequence entries, including a curated training sp...
BULLPEN is a new framework that extends EmbedLLM to profile large language models by jointly encoding answer text, correctness, and question features. It adds 20 behavioral, style, and provenance benchmarks and achieves...
DeepSeek's Harness team released dsh-superagent, an MIT-licensed research prototype that acts as a proactive coding agent for GitHub repositories. It uses a router-worker architecture where a long-running router dis...
Nace AI released Drex Max v1, a dense 27B decision model, as open weights under the Nace.AI Open RAIL-M license. It returns option probabilities in a single forward pass for choice, yes/no and ordinal questions, targetin...
Factory has released Droid 1.0, a model-independent coding agent harness that enables programmatic tool calling by default. Its Script tool runs JavaScript in a sandbox, coordinating multiple tool calls while returning o...