Archive
1537 technical news articles
代理工具
OmniScientist carries perception through hypothesis generation, experimentation, and writing instead of first compressing images, waveforms, or trajectories into text summaries. In blinded comparisons, the full system achieved an 85% win rate against a version that received only precomputed features, though evaluations still relied primarily on model judges.
推論系統
FlashDrive reuses video KV, drafts reasoning tokens in parallel, and caches the less-changing steps in flow matching. The paper reports a 4.7× speedup on an RTX PRO 6000 with virtually unchanged trajectory error, but the results remain limited to simulation and a single model stack.
LLMOps
The new release can copy a small sample of real requests to a candidate router, then use a blinded judge to compare responses without affecting production results. Complexity classification also no longer treats a fixed agent system prompt as a signal of each request’s technical difficulty.
推論系統
The new release adds support for the Kimi K3 text model, hybrid KDA/MLA attention, latent MoE, and tool-call parsing. The converter directly reorders the MXFP4 bit layout, eliminating the need to first expand the entire 2.8T-parameter model to BF16.
最新模型
The previous LoRA loading path did not verify whether a tensor’s offset plus its size exceeded the GGUF file bounds, allowing corrupted or incompletely downloaded adapters to appear to load successfully. b10451 now fails immediately and confirms that the tensor index actually exists.
代理工具
The new release provides scriptable model and sandbox testing tools, allowing multi-turn agent workflows to be reproduced in CI without calling model providers. The upgrade also adds compatibility with OpenAI Python 3 and HTTPX 2, while fixing issues involving interruption state, tool approvals, and sensitive error leakage.
GitHub Repo
NInfer’s Ampere branch fits Qwen3.8-27B, MTP3, paged KV, and compatible prefix reuse onto a single 24GB RTX 3090. The author measured aggregate eight-request decoding throughput of 165.33 tokens/s, though the results are limited to a fixed workload with short prompts and long outputs.
代理工具
StateBridge aligns the sending agent’s final-layer hidden states with the receiver’s embedding space and injects them directly as a continuous prefix. It matched or achieved the best result in 22 of 26 tests across four open models, but remains limited to same-model agents whose internal states are accessible.
推論系統
Community testing indicates that Apple Silicon inference frameworks still cannot reliably provide built-in MTP speculative decoding, hybrid-state prefix caching, and batched serving at the same time. The problem affects more than benchmarks: it can also force long-running coding agents to repay the prefill cost on every conversational turn.
AI 安全
A new open-source protocol lets agents create Ed25519 signatures and witnessed append-only records for memory, identity, and actions, while providing a zero-dependency offline verifier. It turns persistent-memory poisoning into a detectable integrity problem, but still cannot prove that a memory was originally true and has not yet become an IETF standard.
最新模型
Google is rolling out Gemini 3.7 Flash across its API, Antigravity, Android Studio, and enterprise agent platforms, offering a limited-time 50% discount to capture high-volume agent workloads. Early integrations show that multimodal input, tool calling, and cross-API formats are already supported, but reasoning parameters and cost data still pose migration pitfalls.
最新模型
Mistral OCR 4.1 focuses on six categories of document-parsing errors, including bounding box drift, missing blocks, merged references, and right-to-left tables. `mistral-ocr-latest` now points to the new version, so production pipelines relying on the floating alias may see output changes without code changes or version pinning.