Archive
新模型、開放權重、多模態、語音、影像與模型架構。
最新模型
Moonshot AI has officially released the Kimi K3 weights and technical report. The model features native vision, a one-million-token context window, and activates 16 of 896 experts for each token. The open weights finally make the company’s capability claims reproducible, but more than 1 TB of low-precision weights still put full deployment beyond ordinary workstations.
最新模型
Laguna S 2.1 uses sliding-window attention, attention gating, and an FP8 KV cache to reduce long-context costs, targeting self-hosted agentic coding. The model comes with weights at multiple precision levels and complete evaluation trajectories, but its million-token capability, performance comparisons, and single-machine feasibility still depend heavily on the quantization format and runtime environment.
推論系統
Researchers enabled agents to predict and pre-execute their own next tool calls during inference, replacing an external draft model with shared weights and a shared KV cache. Joint reinforcement learning raised average Hit@1 to 61.2 and 66.3 for two Qwen 4B models, respectively, though the paper has yet to quantify end-to-end speedups in real-world parallel deployments.
最新模型
Shieldstral unifies content moderation as a binary question-answering task whose criteria can be specified in natural language, allowing the same model to switch standards based on the product context. The paper reports average F1 scores of 84.9% for text and 83.8% for multimodal content, but the model weights and complete inference package have not yet been released.
AI 安全
The first large-scale study of MCP clients found that official SDKs and file-based configuration have become mainstream, but only 37.2% of applications require blocking approval. The protocol has standardized communication formats, but permissions, configuration, and human oversight have yet to converge into consistent application-layer practices.
代理工具
Surge AI has released 65 long-horizon agent tasks requiring models to follow changing policies spanning 20 to 124 pages while working across email, chat, calendars, and enterprise tools. The best configuration passed only 36.2% of tasks under strict scoring, which requires every rule to be satisfied simultaneously—showing that a large context window does not guarantee sustained compliance.
代理工具
Amazon Science has released PatientAgentBench, which tasks medical agents with completing multi-turn primary care workflows using synthetic medical records and stateful tools. The largest performance gap among the ten models appears in triage decisions, showing that answering medical questions correctly is not enough to prove that an agent can execute workflows safely.
最新模型
A new study restricted LoRA to the early, middle, or late blocks of Transformers and found that different learning objectives exhibit reproducible “adaptation geometries.” The findings elevate adapter placement from an implementation detail to a design variable for controlling knowledge transfer and side effects.
最新模型
An experiment spanning 44 language models found that merely adding “respond in JSON” reduced answer diversity, without schema enforcement or constrained decoding. The findings remind developers that structured output is not just a serialization layer—it may also change the answers models actually choose.
開發者平台
GitHub Models will discontinue all services on July 30. Existing customers will lose access to the model catalog, Playground, inference APIs, and BYOK endpoints. Migrating to Microsoft Foundry is not simply a matter of changing URLs: teams must also revalidate identity and access, model versions, billing, and output compatibility.
推論系統
The open-source NInfer uses custom quantization, weight layouts, fused kernels, and an MTP draft path to sustain long-context decoding at about 543 tokens per second for Qwen3.6-35B-A3B on a single RTX 5090. Its speed comes from deep specialization for the model and GPU, but it currently supports only two checkpoints, lacks continuous batching, and has yet to be independently benchmarked under identical conditions.
SpecBox 根據串流 token 推測即將使用的工具，讓沙箱啟動與模型推論重疊，並以相依圖預取後續執行環境。論文報告其 P99 端到端延遲最高改善 2.9 倍、峰值記憶體降低 45.9%，但目前仍是研究原型，尚無公開程式碼或獨立重現結果。