WeWorkBuddy

Home / Browse

All stories

Browse every indexed public story, including items outside the main categories.

18978 public stories

V2EX ·

[分享创造] 开源 AI 错题本:支持拍照识别、国内大模型直连(DeepSeek/MiniMax)、组卷打印与安卓单机版

大家好,分享一个最近持续在打磨的开源项目: Smart Wrong Notebook (智能错题本) 。 这个项目 fork 自 wttwins/wrong-notebook 。最初是因为家里有整理错题和复习的需求,在实际高频使用的过程中,发现传统的错题整理方式(无论是手抄、剪贴,还是单纯拍照存进相册/笔记软件)很容易陷入几个痛点: 「只存不练」变成电子垃圾场 :拍了一堆错题存进去,但做题和复习还是习惯在纸上写算;缺少针对性的变式题生成和抽题组卷打印,做完之后也没法把纸面结果回填到系统里追踪到底掌握了没有。 拍出来的卷子配图糊、有手写批注 :手机拍的试卷往往带阴影和手写痕迹,直接打印效果很差;几何、物理题光看文字解析又不够直观。 模型配置与部署门槛高 :不少开源 AI 工具默认只对接海外接口,国内网络环境配置繁琐;而且并不是每个家庭都有常开的 NAS 或服务器,有时候只想在安卓平板或电脑上装个安装包直接用。 围绕这几个实际痛点,我在这段时间里对项目做了比较彻底的改造和扩展,目前已经完成了从「拍照识别 → 动态讲解 → 举一反三 → 组卷打印 → 作答回填」的完整闭环,并且把安装方式覆盖

V2EX ·

[分享创造] [分享创造] 整理了一批图片转可编辑 PPT 的成品素材,放出来求建议

最近把手上做过的图整理成了一个小素材库:24 页精选,覆盖科研学术、项目汇报、年终总结、规划路线图、图表分析、团队人物、目录页;每页都有原图和可编辑的 PPTX ,另外整理了 222 页的目录。 先放几张成品预览,都是渲染出来的 PPTX 页面,不是原图贴图。每组第一张如果是「原图」,后面就是对应的成品。 科研学术 · 新拟态风研究框架(原图) 科研学术 · 新拟态风研究框架(成品) 科研学术 · 漏斗结构多模态轻量化模型(成品) 项目汇报 · 项目启动演示文稿(成品) 年终总结 · 数据可视化模板(成品) 规划路线图 · 程序员技能树成长时间轴(成品) 图表分析 · 竞品分析矩阵(成品) 团队人物 · 商务风卡片式人物介绍(成品) 目录页 · 极简风图标模块结构(成品) 目前的效果与边界: 文字和简单形状为主的页面最稳定:标题、标签、卡片、箭头都能单独选中,改字、改色、挪位置不用回到原图; 写实插画、照片、地图占比高的页面:照片按区域裁切回贴,能移动、能替换,但不是矢量; 超大图、长条图仍不稳定:建议先裁关键区域,或者按页拆开处理。 验收三个动作:双击文字有光标、选中箭头或卡片有控制

GitHub Discovery ·

t3dotgg/tstack

The agent skills I use every day. Works with Claude Code and Codex.

V2EX ·

[程序员] Gemini 4 Argon 进一步降智

前情提要: https://v2ex.com/t/1251363 Antigravity 官方客户端,今天上午进一步降智,已经到了这种程度: 会编造一些非常简单的内容,例如弄错项目的快捷键,明明已经有一个单独的简短清晰的快捷键文档,正常智力不太可能弄错。 会编造一些无关操作,缺乏逻辑。例如给一个已经非常明确且稳定重现的 Bug 的解决方案,非要在方案里添油加醋一些无关重现操作干扰阅读。 第一次出现完全不遵守规定的情况。提交文档,但提交信息不规范,被提交信息检查脚本拦截。之前也出现过类似情况,但会修改提交信息以符合规范,但这次直接不提交了。 这是目前发现的 3 点。而且思考链路依旧很长,依旧很耗时,产出一坨了。

V2EX ·

[程序员] DeepSeek 智谱 KIMI ,哪个有可能成为中国的巨无霸科技公司?

豆包和千问就不讨论了,背后的公司已经是超级巨无霸。 现在标题里面的三个公司,哪个最有潜力最有可能成功突破为令人瞩目的巨无霸科技公司,为什么? 我个人觉得 deepseek 可能性较大,另外两家虽然也有极强的技术能力,但是似乎节奏没有 ds 看起来那么有规划和目标,当然平常我用 ds4.1f 也更多。更深入的分析暂时没思考,就是 1024 来了,忽然想起的一个问题

arXiv ·

baseVultra: Compact Nonlinear Recurrence with Reallocated Capacity

arXiv:2610.30154v1 Announce Type: new Abstract: Nonlinear recurrent networks remain useful for streaming sequence modeling, yet gated cell design is still dominated by LSTM and GRU. We study whether recurrent computation can be reallocated away from gate transforms and toward candidate generation. We propose baseVultra, a compact recurrent cell that concentrates the dense recurrent budget on a single H x H candidate-generation matrix, while replacing recurrent gate matrices with O(H) diagonal in

arXiv ·

Lighthouse: On Building a Trustworthy Digital Assistant for Exploring History with Civil Rights Archives

arXiv:2610.30158v1 Announce Type: new Abstract: Artificial intelligence (AI), as a decision-support aid, provides new tools for studying history effectively using multimodal data, including text, images, and audio. We present, to our knowledge, the first digital assistant named Lighthouse--commonly called a chatbot--for exploring the Civil Rights period of the United States using data from South Carolina. From an AI perspective, the system's novelty lies in its guiding design principles of (a) f

arXiv ·

TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents

arXiv:2610.30161v1 Announce Type: new Abstract: Many Indian banks serve customers through FAQ pages and scripted chatbots. Assistants based on language models could respond faster and carry out requests such as blocking a card, but only if they give correct information and follow the bank's rules. These rules prescribe a procedure, a set of required steps, such as obtaining a closure quote before closing a deposit. Adapting models to this domain requires measuring how well they follow the proced

arXiv ·

FusionEval: Benchmarking Model Fusion for Large Language Models

arXiv:2610.30162v1 Announce Type: new Abstract: Model fusion aims to integrate the capabilities of multi-expert models into a single model. Existing evaluations offer limited coverage of reasoning with long chains of thought and tool use, while strong average performance can mask substantial losses in individual expert capabilities. We introduce FusionEval, a benchmark that provides controlled expert pools, integrates fusion methods with and without additional training, and offers a unified eval

arXiv ·

Measuring Research Progress and Linguistic Inclusion in Low-Resource Languages

arXiv:2610.30296v1 Announce Type: new Abstract: Large Language Models (LLMs) have accelerated research on low-resource and multilingual NLP, but their effectiveness in creating an equitable landscape remains unmapped. We analyze 1,158 peer-reviewed open-access papers published between 2020 and 2025, examining research attention to low-resource languages (LRLs) and representation across language and speaker populations. To assess linguistic inclusion beyond publication counts, we introduce the Li

arXiv ·

AQL-Lite: Enabling Efficient Knowledge Acquisition for Arabic LLMs via Data-Centric Continual Pretraining

arXiv:2610.30344v1 Announce Type: new Abstract: Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality Language), a time- and resource-efficient framework for adapting a multilingual LLM to Modern Standard Arabic (MSA). AQL-Lite couples a quality-first curation pipeline (structural cleaning, heuristic and model-based filtering, MSA selection, and deduplication) w

arXiv ·

Consistency Is Not Validity: Self-Rewarded Moral Argumentation Makes Language Models Decisive but Pliable

arXiv:2610.30349v1 Announce Type: new Abstract: LLMs are increasingly consulted for moral judgment. We aim to improve performance on such tasks by rewarding good arguments, on the premise that arguing well increases the likelihood of judging well. We train a reinforcement learning policy initialized from a state-of-the-art language model in a self-judged tournament with masked thinking: the generated arguments are judged pairwise on argument quality by the policy itself. As an empirical basis, w

arXiv ·

CiteAnchor: Source-Aware Grounding for Hallucinated Citation Detection and Resolution

arXiv:2610.30355v1 Announce Type: new Abstract: Hallucinated citations make it harder to trace sources and verify the evidence behind scientific claims. Detecting them is difficult because bibliographic records can be incomplete or differ across source types and publication versions. A plausible match alone neither validates the citation nor establishes its underlying source. We introduce CiteResolve, a benchmark of 423 real-world hallucinated citations annotated for source recoverability. We fu

arXiv ·

Climbing the Ladder: Automating Data Pipelines and Reproducing Baselines in Low-Resource Settings

arXiv:2610.30374v1 Announce Type: new Abstract: The massively multilingual translation systems that now include Sicilian learned it from noisy, non-standardised web text. To obtain better translation quality, we redevelop the small neural machine translation (NMT) system that Wdowiak customized for Sicilian. We rebuild on maintained software the extraction of the parallel text from the PDFs of the bilingual journal Arba Sicula, whose sentences are aligned by a language-agnostic sentence encoder

arXiv ·

MemPlan: Memory-Conditioned PDDL Planning for Partially Observable Text Environments

arXiv:2610.30379v1 Announce Type: new Abstract: LLM agents are flexible in language interaction, but using them as long-horizon planners is costly and prone to hallucinated or invalid actions. This paper targets a different role for LLMs: constrained bridges between language and symbolic planning. We propose MemPlan, a memory-conditioned PDDL planning framework for partially observable interactive text environments. MemPlan keeps the PDDL domain fixed and reconstructs the PDDL problem at each st

arXiv ·

SIM-UT: A User Simulation based Evaluation Framework for Medical Triage Chatbots

arXiv:2610.30412v1 Announce Type: new Abstract: LLM-based chat agents are increasingly used for complex, multi-turn, multilingual medical triage in low- and middle-income countries (LMICs), yet evaluation methods focus on single-turn, English-only benchmarks that primarily test the chatbots' knowledge. In practice, users are often confused, overwhelmed, or emotionally vulnerable, giving unclear, misspelled single-word answers or long messages in regional dialects, and the context of a conversati

arXiv ·

Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models

arXiv:2610.30435v1 Announce Type: new Abstract: Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search agents often lack search-state awareness, i.e., the ability to recognize what information has been obtained and what remains missing, leading to hallucinated reasoning and prematurely terminated search. To address this limitation, we propose Self-Assessment Reinforcement Learning (

arXiv ·

Rethinking the Evaluation of LLM Fact-Checkers

arXiv:2610.30504v1 Announce Type: new Abstract: Large language models (LLMs) are widely used to answer factual questions, but their answers can contain errors and must be fact-checked claim by claim. Yet the resulting score depends on three design decisions: which questions the claims answer, under what conditions each claim is judged, and which sources count as evidence. No existing benchmark specifies all three. We introduce JSFactCheckBench, a Japanese benchmark that specifies all three, with

arXiv ·

Behind Aggregate Scores: What Systematically Varying Arena-Hard's LLM Judge Reveals

arXiv:2610.30512v1 Announce Type: new Abstract: LLM judges are used to determine which of two answers is better. Trusting these verdicts requires knowing how repeatable they are and how much they depend on the judge's instructions. We show that similar aggregate scores can conceal substantial changes in individual verdicts, both when the same setup is repeated and when the instructions change. Using 500 Arena-Hard v2.0 prompts with two models' answers held fixed, we run GPT-4.1 as the judge unde

arXiv ·

Protegrity-PII Technical Report

arXiv:2610.30518v1 Announce Type: new Abstract: We present Protegrity-PII, a new PII decision model for structured and unstructured text. Protegrity-PII achieves a typed recall of 0.915 with a precision of 0.907 on a new benchmark we propose, PII-SCOPE. Our model processes text in 0.49 seconds per million characters at \$0.0005 per million characters on a single RTX 6000 using batched inference. Due in part to the expansive nature of the entity type taxonomy used in training, Protegrity-PII achi

arXiv ·

IFC-MCQ: Automatically Generating Multiple-Choice Benchmarks for Evaluating LLM Agents on IFC Data Retrieval

arXiv:2610.30533v1 Announce Type: new Abstract: Industry Foundation Classes (IFC), the standard for building information exchange in architecture, engineering, and construction (AEC), is increasingly queried through large language models (LLMs) using natural language. Evaluating these systems at scale is difficult because free-text answers require costly human or LLM-based review. We propose IFC-MCQ, a method that automatically generates multiple-choice benchmarks from IFC files for exact option

arXiv ·

What the Specification Did Not Say: Specification-Oracle Gaps in Test-Graded Coding-Agent Benchmarks

arXiv:2610.30635v1 Announce Type: new Abstract: Coding-agent benchmarks often describe a task in natural language but grade it with tests taken from the upstream project. Passing those tests can require information the description never states: a constant's name, a module path, an exact message. We call this a specification-oracle gap: where it exists, a benchmark also measures whether an agent reproduces upstream implementation details. We formalise the gap, including the inconsistencies that c

arXiv ·

Compiling Autoregressive LLM Control into Policy-Exact Parallel Inference for Hierarchical RAG

arXiv:2610.30664v1 Announce Type: new Abstract: Large language models increasingly act as controllers in structured decision pipelines, yet their decisions are still executed by autoregressive text decoding. Hierarchical RAG is one such setting: at each frontier of a document tree, an LLM commits to $b$ of $k$ sections under an input-dependent action grammar, executed as either failure-prone free-form JSON or reliable but strictly serial grammar-constrained generation. We show that this serializ

arXiv ·

Spectral Smoothing and Spiking Perturbations Reconfigure Capability Profiles and Selective Task Performance in Large Language Models

arXiv:2610.30676v1 Announce Type: new Abstract: Singular-value spectra encode important structure in transformer feed-forward projections, yet their causal role in downstream behavior remains underexplored. We study post-hoc spectral smoothing and spiking interventions on the up_proj and down_proj matrices. Positive perturbation stretches deviations from the geometric mean, making large singular values larger and small ones smaller (spiking), and vice versa. The intervention preserves singular v

arXiv ·

WikiOriginQA: Automated Construction of a QA Dataset with Knowledge Origins for Analyzing Cultural Bias

arXiv:2610.30677v1 Announce Type: new Abstract: Existing datasets on cultural knowledge have been typically created by human annotators familiar with each culture. However, the process requires considerable human effort, presenting a significant challenge to scalability. To address this challenge, we introduce WikiOriginQA, a QA dataset automatically constructed by objectively representing the origins of knowledge through the creation dates of different Wikipedia language editions. Experimental

arXiv ·

Direct cueing of word identity through word duration: evidence from Mandarin homophones

arXiv:2610.30682v1 Announce Type: new Abstract: While there is increasing evidence that words are stored in the mental lexicon with some phonetic detail, there are open questions about exactly which phonetic details are stored and whether they are functionally relevant for spoken word recognition. Word-level phonetic cues, such as word duration, provide an appropriate test case. Across languages, including Mandarin Chinese, high frequency words are shorter than low frequency words. Using a homop

arXiv ·

From Clinical Judgment to Checkable Rules: Clinician-Led Guardrails for Mental-Health Chatbots

arXiv:2610.30690v1 Announce Type: new Abstract: Large language models (LLMs) deployed in mental-health contexts can be evaluated for safety failures, but the resulting judgments are often difficult to inspect or explain. Common approaches to improving safety rely on prompt engineering, LLM-as-a-Judge, and Constitutional AI. In this work, we describe a clinician-led alternative in which two clinicians define, finalize, and adjudicate the four safety checks of a rule base, which is formally verifi