AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26119v1 Announce Type: new Abstract: Whether large language models can be prompted to generate rhetorical fallacies on demand, and whether current safety post-training constrains this behavior, has received less attention than the related question of detecting fallacies in existing text. We close this gap with DeflectBench, evaluating 23,990 generations from four frontier models across three deflection strategies (whataboutism, ad hominem, red herring), seven prompt framings, and 80 claims spanning four controversy levels. Refusal is governed primarily by request structure rather than claim content. Per claim refusal varies by only 11 percentage points across the 80 claims, while a single prompt frame change can swing within model refusal by nearly 1…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26118v1 Announce Type: new Abstract: Existing long-form factuality evaluation relies on the decompose-retrieve-verify pipeline. However, the pipeline suffers from noise from claim decomposition and fixed verification granularity, resulting in unreliable results. We propose ElementCheck, a complexity-aware framework that verifies long-form outputs via sentence elements. Instead of uniformly decomposing sentences into atomic sub-claims, ElementCheck extracts entity pairs that are explicitly linked through verifiable connections in the original sentence as elements, and organizes these into an element graph. The graph topology provides a structural signal for estimating sentence complexity, enabling direct verification for simple sentences and targeted…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26112v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference through a draft-then-verify paradigm. Building on this, tree-structured methods improve inference by organizing proposals into multiple candidate paths, increasing the accepted length. However, existing tree-structured methods use a single drafter for all drafting steps, creating a dilemma: a smaller drafter is fast but yields lower-quality trees, whereas a larger drafter improves tree quality but suffers from high latency. To address this, we propose TreeGraft, a multi-drafter framework in which drafters of different costs jointly construct a shared draft tree. TreeGraft uses the stronger drafter to rescore candidates by updating scores assigned by t…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26433v1 Announce Type: new Abstract: Data-driven prognostics and health management has emerged as a key enabler for Industry 4.0, yet the development of robust remaining useful life (RUL) estimation models is often limited by the scarcity of run-to-failure data. While federated learning offers a promising paradigm to collaboratively train predictive models without sharing sensor data, research efforts have operated so far in the absence of a common evaluation framework. To address this gap, this paper introduces FedCMAPSS, a benchmark for federated RUL estimation based on the commonly-used NASA C-MAPSS dataset. We define a set of five standardized tasks designed to simulate real-world industrial challenges, ranging from ideal IID settings to extreme…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26423v1 Announce Type: new Abstract: This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier's confident decisions can be trusted. This framework, the Latent Diagnostic Taxonomy, consists of (i) constructing a dimensionality-optimized classifier, in which the embedding dimensionality is empirically selected via cross-validated performance rather than fixed a priori, (ii) locating a relatively small set of latent support vectors (~ 29% of total training examples) representing influential prompts for identifying tokens that alter the classifier's predicted labels, and (iii) utilizing such tokens and their associated attack magnitudes for co…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26375v1 Announce Type: new Abstract: Standard machine-learning training minimizes a loss function over a dataset, but does not guarantee that the resulting model will satisfy predefined rules or constraints on its outputs. In many real-world applications, ranging from autonomous systems to network routing, such guarantees are essential. We propose CG4AI, a framework that builds a convex combination of AI models while enforcing linear constraints on the combined output. A master linear program (LP) determines the optimal mixture weights, while a pricing subproblem generates new models guided by LP dual variables, focusing attention on the most violated constraints. A cutting-plane procedure extends feasibility guarantees beyond the training set. We ap…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26332v1 Announce Type: new Abstract: Managed LLM services are now part of real production systems, but model selection and service planning still rely heavily on capability benchmarks that reveal little about operational behavior after deployment. We present Operational Embedding (OpEmbed), a framework for learning compact operational fingerprints of LLM cloud services from structured, privacy-preserving support-case metadata, without using case text. OpEmbed aggregates model--time windows into an eight-channel operational signature and learns a low-dimensional representation via temporal contrastive learning, cross-view reconstruction, and generational-ordinality regularization. Evaluated on more than 33,000 production support cases spanning seven L…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26324v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward hacking, in which the selected response exploits errors in the proxy reward model, and the absence of any privacy protection for the sensitive human preference data used to train that reward model. We show that a single intervention-adding calibrated noise to reward scores before selection-resolves both. Our first result, Private Best-of-N (PrivBoN), establishes that Gumbel noise at an appropriate scale simultaneously provides $\epsilon$-differential privacy and implements KL-regularized alignment. Whenever the privacy budget exceeds a critical threshold $\epsilon^*…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26309v1 Announce Type: new Abstract: Modern machine learning models rely on large amounts of labeled data. However, manual annotation of large-scale datasets is expensive and time-consuming. Label spreading is a semi-supervised learning technique that addresses this challenge by propagating information from a few labeled examples to a larger pool of unlabeled data. Despite its effectiveness, its application to large-scale, high-dimensional datasets is limited by computational costs and memory constraints. To address these limitations, we propose Algebraic Multigrid Acceleration for Efficient Label Spreading (AMELS), an efficient label spreading framework that improves scalability by fast construction of neighborhood graphs and the incorporation of al…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26288v1 Announce Type: new Abstract: Muon has emerged as a strong optimizer for the matrix-valued parameters in large language model pretraining, approximately orthogonalizing its momentum with a few Newton-Schulz iterations. Existing theory either replaces this iteration with the exact polar factor it approximates, or treats its finite depth as an approximation error, and thus the iteration Muon actually runs can only hurt the guarantees. We show that finite Newton-Schulz can instead be beneficial for nonsmooth nonconvex optimization. To this end, we analyze Muon through the online-to-nonconvex conversion, which views the update rule as an online learner and converts its regret bound into a stationarity guarantee. The finite Newton-Schulz iteration…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26233v1 Announce Type: new Abstract: Extreme compression of deep neural networks, up to full binarization, dramatically reduces memory footprint and arithmetic complexity, facilitating deployment on constrained edge hardware with field-programmable gate arrays (FPGAs) and microcontrollers. Although combining binarization with pruning promises additional efficiency gains, existing pruning strategies are ill-suited to binarized representations and rarely translate into meaningful hardware savings. We introduce a PyTorch-based, research-oriented framework that incorporates freezing and pruning mechanisms for designing and optimizing binarized neural networks. The framework enables rapid and reproducible evaluation of state-of-the-art approaches and the…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26222v1 Announce Type: new Abstract: Safety evaluation is critical for assessing whether aligned Large Language Models (LLMs) remain robust against jailbreak attacks. Existing automated testing methods, however, largely rely on response-level feedback: each candidate prompt typically requires generating a target-model response to evaluate its attack effectiveness. This process is expensive and, more importantly, provides only sparse guidance on strongly aligned models, where most candidates are rejected with the same failure outcome. This paper presents NeuronFuzz, a white-box fuzzing framework that exploits internal safety neurons as continuous execution feedback for LLM safety evaluation. A SafetyOracle converts safety-neuron activations into a con…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26132v1 Announce Type: new Abstract: Labeled property graphs combine relational structure with heterogeneous textual and categorical properties attached to both nodes and relationships. Conventional graph neural networks typically represent these properties as static feature vectors, limiting their ability to determine which semantic evidence should influence message propagation for a particular prediction target. We propose SLM-Conditioned Hierarchical Relation Routing, an architecture that integrates a small language model directly into graph message selection. A topology GNN provides a stable structural representation and prediction anchor. For each target node, incident messages combine the neighbor's structural state, node-property encoding, rel…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26150v1 Announce Type: new Abstract: Recent advancements in Large Language Models (LLMs) have created new opportunities to streamline and potentially automate many research processes, including systematic literature reviews (SLRs). This study reports an LLM pipeline development for extracting model-relevant information from 536 peer-reviewed agent-based modeling papers. We compare the results with those of a human-conducted SLR. Our results show paper-level accuracies of approximately 77.95% for GPT-4.1 and 81.67% for GPT-5.0. Field-level accuracy ranges from 32.40% to 100.00%, with more complex or subjective fields performing less reliably. Importantly, we find that agreement between LLMs is a potential indicator of output quality: low agreement may…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26149v1 Announce Type: new Abstract: Multi-table learning remains a major challenge in machine learning for healthcare and other complex information systems. Relational data combine several sources of complexity, including large data volume, high-dimensional variables, high-cardinality categorical features, complex inter-table dependencies, and repeated temporal observations. We introduce the Relational Hypergraph Transformer (RHT), a unified architecture that represents relational databases as hypergraphs, learns pentadimensional embeddings (PentE), and performs sparse relational attention with complexity proportional to the average relational degree rather than the square of the number of entities. We formally define the architecture, derive the co…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26145v1 Announce Type: new Abstract: Our research focuses on evaluating literature reviews generated in short and long context settings of large language models (LLMs) to investigate the impact of context window on the quality of AI-generated literature reviews and the role of AI in supporting literature review writing. Twenty AI-generated literature reviews based on research sources from Semantic Scholar and Arxiv were evaluated by two researchers across 15 dimensions. Our findings reveal that AI-generated literature reviews require human oversight to meet academic publishing standards. As context windows increase, LLMs can incorporate broader information and maintain coherence across longer inputs, but they also exacerbate issues such as content re…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26134v1 Announce Type: new Abstract: Energy forecasting aims to maximize accuracy to ensure energy efficiency by reducing energy waste, an objective that applies equally to on-device forecasting for mission-critical edge environments, including military systems. However, this paper identifies the Accuracy-Efficiency Paradox: high-precision energy forecasting models can ironically trigger a net energy deficit. This stems from both edge AI's inference energy consumption and battery aging. We propose a Total Cost of Ownership (TCO) framework for energy forecasting, designed to minimize net energy loss. This framework treats not only inference energy consumption but also battery aging as a unified form of energy loss, as degradation represents a physical…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26116v1 Announce Type: new Abstract: Existing methods for exploring cellular automata and other complex systems mostly operate in open loop: they set initial conditions, execute a full simulation, and observe the outcome, without intervening during execution. We introduce a closed-loop framework based on autotelic reinforcement learning, in which an agent autonomously samples diverse goals and learns a goal-conditioned policy to intervene in a complex system through minimal, local perturbations. We instantiate this framework on Lenia, a continuous cellular automaton known for life-like self-organizing patterns, in an agentic system we call CARL, and demonstrate three capabilities. First, CARL discovers stable solitons across a wide range of Lenia upd…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26114v1 Announce Type: new Abstract: Calculation-intensive financial question answering requires exact reasoning over structured rates, temporal conditions, numerical formulas, and rule-based constraints. Although Large Language Models (LLMs) perform strongly on natural language tasks, they often produce numerically incorrect yet plausible answers when solving multi-step financial calculations. To address this limitation, we introduce CIFQA (Calculation-Intensive Financial Query Answering), a deterministic tool-grounded multi-agent LLM framework for financial question answering. CIFQA separates language understanding from numerical execution by assigning specialized agents to query interpretation, routing, parameter extraction, computation planning,…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26113v1 Announce Type: new Abstract: We present PICasso, an AI-assisted framework for automated synthesis, verification, and optimization of photonic integrated circuits (PICs) from natural-language specifications. PICasso couples a structured NL -> YAML -> GDS generation pipeline with PDK aware knowledge injection, automated placement and routing, DRC/LVS validation, and SAX-based photonic simulation. To systematically evaluate AI-driven photonic design, we introduce PIC-Set, a benchmark of 36 parameterized PIC design tasks spanning core photonic primitives and multi-component circuits. Using PIC-Set, we benchmark several state-of-the-art Large Language Models (LLMs) under a unified evaluation protocol, including new metrics such as structural and f…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26111v1 Announce Type: new Abstract: Battery Prognostics and Health Management (BPHM) is critical for ensuring the safe, reliable, and cost-effective operation of batteries across electric vehicles, grid storage, and consumer electronics. Conventional BPHM approaches, including physics-based models and task-centric deep learning methods, face challenges in computational efficiency and parameterization, cross-domain generalization, dependence on extensive labeled run-to-failure data, and model interpretability. Recent Large Models (LMs), built upon Transformer architectures and self-supervised pre-training, offer a transformative new paradigm to overcome these long-standing bottlenecks. This review provides the first comprehensive survey of LM applica…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26109v1 Announce Type: new Abstract: Machine-learning models can predict ICU mortality accurately, but feature-attribution methods alone rarely provide the clinical narrative needed for bedside use. Large language models (LLMs) may bridge this gap, and multi-step agentic pipelines are a plausible extension because they separate data interpretation, guideline checking, and final explanation. This revised feasibility study preserves the original standalone-versus-agentic comparison while making the main clinical findings more explicit. Using the retained local eICU Demo artifact set (2,353 ICU stays; 8.1\% mortality), XGBoost achieved an AUROC of 0.855 (95\% CI 0.796--0.906) and an AUPRC of 0.332 (95\% CI 0.217--0.494). On a stratified 38-case explanat…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.26107v1 Announce Type: new Abstract: Predicting students' academic risk in online education is crucial for enabling timely interventions that can improve retention and learning outcomes. However, existing models often suffer from limited early detection capability and insufficient interpretability, leading to a "black-box" trust crisis that hinders their adoption in real-world pedagogical settings. To address these challenges, we propose EduRiskX, a neuro-symbolic framework that integrates a temporal Transformer-based predictor with F-Logic symbolic reasoning. The neural component models longitudinal student activity sequences using temporal attention, class-weighted loss, and dynamic weekly truncation. Acting as a data-driven expert system, an F-Log…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Uh oh! There was an error while loading. Please reload this page. Notifications You must be signed in to change notification settings Fork 0 Star 3 BranchesTags Open more actions menu Latest commit History 100 Commits 1…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Please stop flooding our projects with AI slop to furnish your CV | neilalexander.dev Neil Home Blog GitHub Please stop flooding our projects with AI slop to furnish your CV 30 June 2026 by Neil Successful contributions…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Anthropic ​argued designation as ‘supply chain risk’ could cost the company billions ‌of dollars in lost business ‌and reputational harm A US federal judge ruled Thursday that sanctions imposed in February by the Trump administration against AI giant Anthropic were illegal, finding that the government had punished the artificial intelligence company for publicly criticising the Pentagon. “The empty invocation of national security is not a blank check to punish and retaliate against government critics,” Judge Rita Lin said in a 59-page decision. Continue reading...

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：National cabinet met on Wednesday to discuss the federal government’s plan for new AI datacentre development. Queensland and the Northern Territory have won a carve-out so that theirs can be powered by coal and gas – rather than renewables. Meanwhile, the fight between the West Australian premier Roger Cook and the Productivity Commission over his state’s generous GST deal persists. And federally, migration arrival numbers continue to spur debate across the political parties. To discuss this week’s mix of politics and policy, political editor Tom McIlroy speaks to the CEO of the Grattan Institute, Dr Aruna Sathanapally, and economics editor Patrick Commins Read more: Albanese backs down on states powering AI datacentres using renewable energy In this hour of ne…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：H3 Max · Post-trained video model MiniMax H3 MaxAI Video Generator Turn a written shot or a still image into a 5-15 second video. H3 Max is tuned for stronger prompt understanding, polished aesthetics, and rapid creativ…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：On Thursday, a judge ruled that the Pentagon's blacklisting of Anthropic earlier this year was unconstitutional, delivering the AI lab a win in a monthslong rollercoaster of a battle with the Trump administration. The lawsuit, filed in March in a California district court, accused the Trump administration of unlawfully retaliating against Anthropic for setting "red lines," or unacceptable military use cases of its AI technology. "The empty invocation of national security is not a blank check to punish and retaliate against government critics," Judge Rita F. Lin, a district judge in the northern district of California, wrote in the ruling … Read the full story at The Verge.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Hi HN! I wanted to share with you a chess analysis tool that I was building for the past week. First of all I want to explain what is the problem that I'm trying to solve: Chess Engines such as stockfish are superior fo…