AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00005v1 Announce Type: new Abstract: Peer review at major venues is under unprecedented submission pressure, motivating the use of large language models (LLMs) as review assistants. Existing LLM-based reviewers, however, face two structural limitations. First, they map manuscripts directly to reviews, leaving the underlying rubric implicit and entangling its derivation with the judgement. Second, the prevailing paradigms each capture only half of a good review: training-free agents gather broad evidence but produce undirected critiques, while training-based reviewers inherit human discriminative judgement together with its noise and uneven coverage. We introduce RubricReviewer, a fully rubric-driven framework that addresses both limitations. It makes…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00004v1 Announce Type: new Abstract: Grading natural-language mathematical proofs is a recurring cost in evaluating math-reasoning systems, and frontier LLM judges are expensive. We ask whether cheap open-weight models can serve as reliable judges given a candidate proof, a ground-truth proof, and a human-grading rubric. On a 200-instance validation sample of IMO-GradingBench, three cheap judges (GPT-OSS 120B, DeepSeek-V4 Flash, Gemma-4 31B) agree with human pass/fail decisions at rates statistically indistinguishable from Claude Opus 4.7 and Gemini 3.1 Pro, at up to $100\times$ lower cost. We had expected a majority vote of the three to be the best budget option; it matched the frontier but did not improve on its strongest member. Extending to the f…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00212v1 Announce Type: new Abstract: Spatial atomic layer deposition (SALD) is a leading atmospheric-pressure, high-throughput route to industrial ALD, but design and control are limited by the cost of predicting surface coverage: high-fidelity CFD is far too slow for operating-window scans, while analytic models miss transport modulation such as the gas curtain. We present a physics-chemistry-informed neural network (PCINN), a hybrid surrogate with CFD-level accuracy at real-time speed: a query returns coverage in about 7 ms, roughly 5x10^4 times faster than a CFD solve, reaching a test R^2_log = 0.998 (leave-one-out R^2_raw = 0.974) from only 30 training cases spanning four orders of magnitude in coverage. The architecture is not a black box: a sma…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00198v1 Announce Type: new Abstract: Environmental time-series causal discovery requires expert decisions about method choice, conditional-independence tests, lag horizons, sample-size adequacy, multiple-testing control, and evidence interpretation. Applied inconsistently across datasets, these choices yield graphs that cannot be compared, reproduced, or audited. We present AutoCause, an open-source Python workflow that records each decision, derives defaults from an extended causal-audit module, and admits domain-informed overrides. The workflow wraps four established causal-discovery methods from three families, adds non-causal reference models, and grades links by method-count support. On 145 datasets from DGP-Atlas, TimeGraph, and a topology-deri…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00175v1 Announce Type: new Abstract: Deep reinforcement learning (RL) agents achieve strong performance by optimizing scalar reward functions. However, once deployed, the policies of these RL agents are often rigid and costly to adapt to new performance criteria. For instance, an agent trained to maximize expected cumulative reward may not accommodate previously unknown stakeholder preferences. Existing approaches to achieve fairness, a type of preference, in RL typically assume that such preferences are known a priori and require complete retraining of the policy under a fairness-oriented metric. Inspired by inference-time alignment in large language models, we investigate the problem of steering a pretrained RL policy toward welfare-based fairness…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00152v1 Announce Type: new Abstract: Predicting the magnitude of a CRISPRi perturbation's transcriptomic effect on held-out target genes is an important open problem in single-cell biology. Recent work has documented that simple baselines often match or exceed deep perturbation predictors on related protocols. We study this phenomenon on the Virtual Cell Challenge (VCC) benchmark under a strict held-out target-gene split, identify the specific low-dimensional signal that drives the gap, and characterize how it transfers across cell types. The target is the log Anderson-Darling distance from non-targeting controls, which is strongly predictable from four deterministic scalar functions of the 2,000-dimensional input. A deep MLP encoder with direct acce…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00144v1 Announce Type: new Abstract: Membership inference (MIA) on language models is usually summarised by an aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines separate members from non-members from surface text alone. We study black-box, sampling-based training-data leakage through a probabilistic lens, treating N samples from p(.|x) as an estimate of the output distribution and casting leakage signals as functionals of it. We extend the blind-baseline critique into the sampling regime: on WikiMIA a blind bag-of-words classifier reaches AUC 0.97 (TPR 0.90 at 5% FPR) and sampling adds nothing, while on an IID Pile split (MIMIR) neither self-concentration nor gold-continuation recovery significantly beats a blind base…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00135v1 Announce Type: new Abstract: Design and architectural archives encode expert human knowledge in graphical formats, providing a critical testbed for design-inspired Machine Learning (ML) challenges absent with typical computer vision benchmarks. Building on JONES-19, a small-size image dataset based on The Grammar of Ornament (London, 1857), we evaluate the discriminative performance of Convolutional Neural Networks (CNNs) in two model training strategies: (a) ImageNet pretraining for domain-general "visual common sense," and (b) learning from scratch on the design data in JONES-19. We find that while domain-general priors improve discriminative performance, learning from scratch augmented with repeated local sampling (multi-crop) effectively…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00129v1 Announce Type: new Abstract: Knowledge distillation (KD) is a widely utilized technique for transferring knowledge from a large model (the teacher) to a smaller model (the student). Owing to its flexibility and broad applicability, KD has been extensively applied in the compression of server-side models to meet the Quality of Service (QoS) requirements of client users. Despite significant advancements, the performance of distillation is substantially compromised when a large disparity exists between the capabilities of the server and the requirements of the client. To alleviate this problem, we propose a novel distillation approach, named Progressive$^2$, which operates through the combination of a progressively stronger teacher and a progres…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00107v1 Announce Type: new Abstract: Agentic systems must repeatedly decide whether to answer directly, decompose a task, invoke a tool, execute code, delegate to a specialist, verify an intermediate result, or recover from failure. These meta-decisions affect not only task success but also operating cost and latency, yet they are often embedded inside an orchestration framework and evaluated only through aggregate task accuracy. We present MetaRoute-Bench, an open, inspectable framework for comparing meta-decision policies under a shared execution model. The initial benchmark contains 180 synthetic task profiles spanning data analysis, research, and document processing, eight routing policies, and 30 paired random seeds. Across 43,200 traces, a task…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00106v1 Announce Type: new Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it. A controller may answer directly, decompose a request, retrieve evidence, execute code, delegate to a specialist, or verify an intermediate result. Existing routing work largely selects model endpoints, retrieval depth, or tools in isolation. We introduce an executable benchmark and a budget-aware meta-router that composes heterogeneous operations from raw task text. The benchmark contains 216 training, 72 development, 108 held-out test, and 108 locked lexical-shift challenge tasks across data analysis, frozen-corpus research, and document processing. Outcomes are machine checked after opera…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2608.00019v1 Announce Type: new Abstract: Deploying large language models (LLMs) for operations research (OR) tasks remains challenging because correctness depends on a coherent modeling process, not merely a correct final answer. Standard autoregressive generation operates on a myopic policy, which sometimes fails to anticipate whether a partial formulation can be validly extended into a globally consistent optimization model. Consequently, locally plausible steps may propagate into catastrophic downstream formulation or solver code errors. To address this, we propose an uncertainty-aware, training-free inference framework for OR mathematical modeling. Without updating model parameters, our method evaluates intermediate candidate steps using short lookah…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The Senate Commerce Committee is poised to consider the Youth AI Privacy Act, a bill that would require AI companies to create kids-only privacy rules and implement so-called “safe design features,” which would—like thr…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Qwen is so back!

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Genspark has open sourced GenOffice under the Apache License 2.0. It is an AI-native office suite for macOS and Windows, covering Docs, Sheets, Slides and PDF as five Electron apps over one shared engine layer. The notable engineering claim is a byte-preserving round trip: only edited paragraphs are regenerated as OOXML and spliced back into the original file, so untouched blocks keep their original bytes and layout survives in Word. Sheets pairs the open-source Univer core with an in-house Rust xlsx sidecar. AI calls route through a signed-in Genspark account and consume credits. The repository labels this an Alpha. The post Genspark Open Sources GenOffice: A Free, Ad-Free AI Office Suite for macOS and Windows with Docs, Sheets, Slides, PDF appeared first on M…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Benzi is a compiler + runtime tracer + harness and AI agent built to understand code from ground up. Challenging traditional RAG and embedding space approaches, Benzi aims to write code as cleanly as it understands it.…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discussion | Link

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Matchflo - AI Resume Tailor ATS Score, Fix & Cover Letters Only for Mac Free · In‑App Purchases Age Rating 4+ Years Category Productivity Developer Jamieson Rothwell Language EN English Size 15.7 MB Mac New: Interview P…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：AI Manhwa Generator for Comics AI Manhwa Generator Use the AI manhwa generator to turn your story into full-color manhwa and webtoons with consistent characters, editable panels, and speech bubbles. Consistent character…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：▓▒░ ⌁ ░▒▓

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Model prices just dropped: save up to 80% — see pricing Text, image, and video models. One API. Access Top AI Models in One API Access leading text, image, and video models through one API and save 20–80% on costs. Swit…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：If you want to know what the ninth circle of Hell is like, join a dating site. I didn’t want to join a dating site, for I am happily ensconced, but I joined one in the interests of research because something very dark i…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The Opportunity We are looking for a Full-Stack AI Engineer, Clinical Systems to help build the intelligence layer at the center of the Alnu Health platform. You will own systems that transform clinically reviewed knowl…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：a technical framework for bring-your-own-cloud Zero Trust, in someone else’s cloud. The ten commandments of building platforms that deploy and operate software inside customer-owned environments: no shared perimet…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Notifications You must be signed in to change notification settings Fork 0 Star 1 BranchesTags Open more actions menu Folders and files NameName Last commit message Last commit date Latest commit History 4 Commits 4 Com…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译： Gas Town was intended to be reusable, but I only ever wound up using it to build itself. Gas Town fell apart at the seams with Opus 4.7. Up through 4.6 it was working brilliantly. With 4.7 we saw the introduction of the "just two more things" tic, which prevented Opus from ever converging on being ready to do real work—it always wanted to fiddle with Gas Town itself. The Opus tic never went away, so Gas Town effectively burned down. It had other problems, too, but 4.7 was the final straw. — Steve Yegge, The Shape of Things to Come Tags: steve-yegge, coding-agents, generative-ai, ai, llms

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Artificial intelligence is reshaping everything from chips and cloud to everyday software, even as investors weigh inflation data, energy costs and shifting rate expectations across the US, Europe and emerging markets.…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Notifications You must be signed in to change notification settings Fork 0 Star 21 BranchesTags Open more actions menu Folders and files NameName Last commit message Last commit date Latest commit History 208 Commits 20…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Modal’s Function Call data path is now >50ms faster. Our new routing layer is geographically distributed, so you can further reduce your network overhead.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Explore new education plugins for ChatGPT Work and Codex that help K–12 teachers, college educators, and students learn, teach, research, and build.