Archive
新模型、開放權重、多模態、語音、影像與模型架構。
AI 研究
LangChain rescored each of five weather-agent traces 100 times, observing lower score variance and per-call costs with Jev. A single human annotator, sampling settings, and hosted model versioning limit how the results can be interpreted.
最新模型
Xiaomi combines multiple types of agent tasks and tool frameworks in a single reinforcement learning run, using scorers to distinguish between solutions that have passed tests. The accompanying 9B distilled model is still an SFT checkpoint, so results from subsequent RL cannot be directly attributed to these weights.
GitHub Repo
Hugging Face reports Rust benchmarks showing encoding speeds 3 to 30 times those of v0.23 on a single thread on an M4 Max. Gains depend on the model and corpus, and existing Python workflows still need feature compatibility checks.
最新模型
The update adds training on long-running tasks and makes the Responses API automatically carry reasoning state across turns. Official evaluations use different reasoning effort levels, while the API and Cursor have separate billing thresholds for long contexts that need to be checked individually.
GitHub Repo
The new release removes local machine learning packages, with the project reporting that the slim image is about 89% smaller than the previous version. Restrictions on vector retrieval, document parsing, and storage backends mean existing deployments need to recheck their service dependencies.
最新模型
The new version combines text-to-image generation, editing with multiple reference images, and transparent layers, while reusing prefix caches to reduce redundant computation. Free use is limited to research and evaluation; commercial use requires separate permission.
最新模型
Laya uses a bidirectional encoder to produce option probabilities directly and has released weights, an SDK, and evaluation materials. The author's tests show potential for low latency, but Traditional Chinese accuracy, probability calibration, and model-switching costs still require separate validation.
GitHub Repo
A report with a minimal reproducer shows that a hybrid-attention model’s output can diverge on the next step even after prefill completes normally. Maintainers have yet to confirm the issue, underscoring the need to verify numerical consistency across multiple steps when optimizing GPU memory usage.
GitHub Repo
Cua assigns field matching and action selection to a small model, while application code determines execution order. Public evaluations remain limited to a few demonstration forms; generalization to Chinese and end-to-end workflow reliability still need validation.
推論系統
This local inference experiment compares reading option logits directly with generating JSON token by token, letting developers measure the cost of output formats. Results remain sensitive to quantization, browser behavior, and test order, and option probabilities cannot be treated directly as measures of reliability.
AI 安全
The team used agents to help build decompilation, static analysis, and formal verification tools, then applied them to an audit of the Miden virtual machine. The public code provides a starting point for reproducing the verification, but the proofs remain bounded by the semantic model and theorem assumptions.
GitHub Repo
The update maps decision answers to Pydantic models for classification and routing workflows. The serialization change requires migration testing, while Chinese-language accuracy and probability thresholds still need separate evaluation.