2026年9月14日 技术热点总结

项目简介：A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.

技术栈：Python、ai、ai-token-monitor、claude-code、token-optimization、token-usage

核心介绍：tokentab reads the session logs that Claude Code, Codex, Cursor and Gemini CLI already leave on disk and adds up token usage and cost – broken down by model, by project, by day, and by the kind of work each session was doing. It runs entirely locally: no account, no API key, nothing leaves your machine.

项目数据：⭐ 830 Stars，🍴 212 Forks

技术栈：JavaScript

核心介绍：.—————————————————————. ‘—————————————————————‘ Engineering workflow skills for AI coding agents. Viserys is a self-contained pack of Markdown workflows, reviewer personas, and validation scripts. It gives an agent a consistent process across the full development lifecycle instead of letting it improvise on every task. DEFINE -> PLAN -> BUILD -> VERIFY -> REVIEW -> SHIP

项目数据：⭐ 628 Stars，🍴 0 Forks

Image tokenizers define the “visual language'' of unified multimodal models, yet are commonly studied through isolated metrics or generation-/understanding-only evaluations. These evaluations do not fully capture how visual tokens behave when modeled jointly with text. We build a controlled pure-autoregressive testbed and track task-specific validation losses during multimodal continual pretraining across text, image, text-to-image (T2I), and image-to-text (I2T) prediction. We examine how these losses scale and relate to downstream performance, then use them to study multimodal learnabilit…

Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on rare entities, but prior work measures rarity primarily through popularity-based metrics such as pageviews. We broaden this view using knowledge-graph structural metrics that capture how well an entity is documented and connected. These metrics identify many rare entities that popularity metrics miss. Across the resulting rare-entity slices, state-of-the-art accuracy drops by 15.4-39.9%, showing that different rarity definitions expose different failure modes. To address …

Reasoning language models have made substantial advances on a variety of complex tasks, yet their capabilities remain overwhelmingly English-centric: models primarily reason in English regardless of the language they are prompted in. This is inaccessible for non-English-speaking users, risks losing the intent of the original question, and forgoes knowledge more readily expressed in the target language. In this work, we advance L2 reasoning, the ability of a model to reason consistently in the language of the user's prompt, thus building an in-language bridge between the prompt and the answe…

In systems built on Robot Operating System 2 (ROS 2) and using Data Distribution Service (DDS), a single network-impaired or throttled subscriber on a RELIABLE topic can cause backpressure that degrades throughput and latency for all other subscribers, including safety-critical ones sharing the publisher, because the publisher's DDS writer can no longer accept new samples. We present Adaptive Bridge, a proxy-based layer that decouples critical subscribers from degraded or noncritical ones, thereby isolating the critical path through topic splitting and dynamic rate control. The proxy acts a…

Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict reference-equivalence to a designated formalization. We formalize this vulnerability as Verdict-Preserving-Unfaithfulness (VPU): a failure mode where an incorrect encoding executes successfully and matches the expected verdict. We theoretically prove that structural, verdict-only verification heuristics are mathematically bounded to chance-level detection on these deceptively valid traces. To resolve this, we introduce Ge…

As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identifies weaknesses but also guides authors toward concrete revisions. We study this as Actionable Peer-review Generation and decompose it into two subtasks: diagnostic claim generation and revision suggestion generation. We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans. Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can theref…