AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27501v1 Announce Type: new Abstract: Mathematical reasoning has seen rapid progress in large language models (LLMs), yet existing methods optimize predominantly for final-answer correctness, raising the question whether models truly internalize mathematical concepts or merely memorize solution patterns. In human mathematics education, example-based reasoning such as constructing counterexamples to test theorem boundaries reflects deep conceptual understanding, but remains underdeveloped in current LLMs. Enhancing this capability through preference optimization presents two key challenges: (1) the model's limited example-based reasoning ability makes constructing effective preference pairs inherently difficult; and (2) capability acquisition is progre…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27481v1 Announce Type: new Abstract: Knowledge-intensive multi-hop question answering requires systems to select evidence and compose dependent facts, yet multilingual benchmarks usually translate an entire example into one language. This hides failures at language boundaries inside the reasoning chain. We introduce XHotpotQA, a controlled benchmark for cross-lingual knowledge composition over mixed-language evidence. Each instance is modeled as an evidence-dependency graph whose question, bridge evidence, answer-bearing evidence, and distractors have explicit language assignments. The audited resource contains 15,661 training and 7,405 validation instances, with sentence-level support supervision and supplied distractors. In validation, 99.81% of it…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27470v1 Announce Type: new Abstract: Entity Disambiguation (ED) is a key task for constructing and using knowledge graphs. State-of-the-art neural approaches commonly model ED as a single task, although it consists of two distinct subproblems: retrieving candidate entities and selecting the correct one given context. Dual-encoder models optimize for both within a shared embedding space, forcing representations to balance high-recall retrieval with fine-grained selection, and they require trained retrievers, which are costly to maintain as knowledge graphs change. While recent work has begun to combine retrievers with LLM-based selectors, the interplay between the two stages has not been studied systematically. In this paper, we present a systematic c…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27467v1 Announce Type: new Abstract: We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participated in Subtasks 2 (evidence identification), 3 (answer generation), and 4 (answer-evidence alignment). For Subtasks 2 and 3, we propose an answer-first pipeline in which the model generates candidate answers citing specific note sentences before classifying the full evidence set, exploiting the asymmetry between judging relevance in the abstract versus relative to a generated answer. For Subtask 4, we apply self-consistency voting over five independent model calls, retaining links by vote threshold. Our pipeline ranked third on evidence identification (Strict Micro 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:2608.27466v1 Announce Type: new Abstract: Web content extraction is essential for reliable LLM data pipelines, yet existing methods often struggle to jointly satisfy accuracy, scalability, and adaptability. General-purpose extractors can be applied broadly, but they are often brittle on publisher-specific layouts and richer extraction targets such as metadata, images, and tables. Direct LLM-based extraction offers greater flexibility, but incurs substantial cost and latency at scale, while manually engineered publisher-specific parsers can achieve high accuracy but require substantial human effort to build and maintain. We introduce PACE, an agentic framework for learning publisher-specific extraction configurations from representative pages and user requ…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27465v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according to the user's emotional state has become an important safety problem. We test whether emotional expression increases a model's endorsement (encouragement to proceed) when a user, holding the same objective information, is overconfident about a premature decision (e.g., quitting a stable job on weak evidence). As a key control, we include a no-emotion multi-turn (neutral) condition that holds factual content and the number of conversational turns constant, isolating the effect of emotion from that of conversation length. We exposed six commercial models (top-tier an…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27462v1 Announce Type: new Abstract: Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextual hints, making its detection in online content review challenging. While existing PLM- or LLM-based methods perform well, they typically apply a single reasoning process to all samples. This overlooks fine-grained linguistic nuances and causes unnecessary computation for simpler cases. We observe that online hate speech is not monolithic but manifests in varied forms. We therefore define three fine-grained categories: Shallow, Targeted, and Context-Dependent. Accordingly, we propose Fine-grained Adaptive Implicit Hate speech Detection (FAID), a novel framework tha…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27461v1 Announce Type: new Abstract: Relational reasoning requires the process of perceptual understanding, comparing, and integrating the underlying relationships between concepts. This ability consists of multiple categories, such as analogical, structural, and cause-effect, each capturing a different aspect of higher-order understanding. To examine the performance of multimodal large language models (MLLM) on these relational inference tasks, we developed SciReC, a model-adaptive multimodal academic dialog benchmark. As the relational reasoning process involves multiple representations and various factors (visual understanding, exhibiting knowledge, and memory recall), we propose DMRA, a deficit-based diagnostic framework that quantifies the contr…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27460v1 Announce Type: new Abstract: Large output embedding matrices create a significant memory bandwidth bottleneck during autoregressive decoding, especially for compact LLMs with large multilingual vocabularies. We reformulate the output projection followed by top-k token selection as a maximum inner product search over token embeddings and replace the dense vocabulary projection with an HNSW-based vector index. The resulting output head retrieves only a small candidate set of high-scoring tokens and can be integrated into existing decoding pipelines by scattering retrieved logits into a sparse full-vocabulary tensor. On CPU inference with Gemma 3, Llama 3.2, and Qwen 3 models, our method substantially accelerates the output projection and improv…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27662v1 Announce Type: new Abstract: This work presents a generative continual learning framework based on growing self-organizing maps (GSOMs) that are augmented with learned distributional statistics as well as encoder-decoder models for class-incremental learning. The proposed approach enables exemplar-free replay using distributional statistical memory, which eliminates the need to store raw data. Each GSOM unit maintains its own mean, variance, and covariance estimates, which are subsequently used to generate synthetic samples for replay; in encoder-decoder configurations, these samples are then decoded back into the input space (via ancestral sampling) for subsequent training. Our method is fully unsupervised, as it does not rely on explicit ta…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27651v1 Announce Type: new Abstract: Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus geometry bounds what any such alignment can identify, before data exist. The obvious diagnostic for this degeneracy, the cheapest non-identity relabelling, ranks two published designs in the wrong order, because dense sampling creates near-duplicates whose transposition is nearly free. We turn this known invariance (Demetci et al., 2024) into a design-time diagnostic and intervention. In colour, where candidate geometries have closed form, we show that the failure is structural: sixty-four times the restart budget leaves a symmetric design unmoved while an asymmetri…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27634v1 Announce Type: new Abstract: Nearest neighbor classification relies fundamentally on how locality is defined, yet conventional $k$-NN imposes the same neighborhood cardinality throughout the feature space. This assumption can be inadequate for data whose local geometry varies substantially across the underlying manifold. We introduce Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification (CARSANN), a geometry-driven framework that adapts the spatial support of each neighborhood according to local geometric complexity. CARSANN first estimates intrinsic dimensionality using TwoNN and constructs an intrinsic representation through principal component analysis. Local mean curvature is then estimated using a shape-operator-b…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27574v1 Announce Type: new Abstract: Multi-label graph learning intends to capture the intrinsic complexity of real-world applications, where one sample is often related to multiple groups or consists of multiple objects. To date, a handful of multi-label graph learning methods exist, but none of them integrate training-time interpretation capability. While post-hoc graph explainers have been developed, they do not explicitly model label-dependent evidence sharing in multi-label graph learners, especially when label pairs are weakly or negatively associated. As a result, post-hoc approaches may miss how evidence should be shared or separated across different labels. This paper advances a new end-to-end self-explainable multi-label graph neural networ…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27521v1 Announce Type: new Abstract: Many dynamical processes unfold on the sphere but the default scientific machine learning architectures are Euclidean. Applying these architectures on a regular lat-lon grid causes problems: Cartesian convolutions become distorted at high latitude; 2D FFTs in Fourier neural operators incorrectly assume double periodicity; Cartesian positional encodings in ViTs distort spherical geodesic distances. Recent work moves towards natively spherical primitives, including spherical convolutions (e.g., DeepSphere or DISCO), Spherical Fourier Neural Operators (SFNOs), and geodesic attention. Here we propose Dandelion, a spherical version of Flower, a warp-based neural PDE solver. Layers of Dandelion predict a tangent-plane d…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27518v1 Announce Type: new Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by catastrophic forgetting and weight-disentanglement error. In the literature, these difficulties are merely treated separately and mitigated through a variety of solutions, while the geometry induced by the base optimizer is treated as an implementation detail. In this work, we show that the two difficulties are in fact two instances of the same phenomenon: a parameter update useful for one task shifts the model's outputs on another. We formalize this shared phenomenon as \textit{task interference} and reduce it to a common layer-wise Frobenius inner product $\langle…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27515v1 Announce Type: new Abstract: The recently introduced block-sparse featurizer (BSF; Fel et al., 2026) is similar to a sparse autoencoder (SAE), but its atomic unit is a small subspace (a block of directions) rather than a single direction. It is designed for features that live on low-dimensional manifolds, which are especially frequent in vision. This work studies the BSF's strengths and weaknesses, finding how it still somewhat suffers from classic SAE failure modes, like feature splitting and composition. We propose several architectural changes to the BSF, including a Tournament Top-K selection rule that significantly reduces feature splitting, and we also extend the block paradigm to the crosscoder.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27513v1 Announce Type: new Abstract: Softmax attention stores key and value vectors for every preceding token, causing inference memory to grow with sequence length. Recent language models incorporating Gated DeltaNet (GDN) or Kimi Delta Attention (KDA) reduce this cost by replacing the KV cache in most layers with fixed-size recurrent states. However, these recurrent states are commonly stored in FP32 and consume substantial GPU memory; their updates are memory-bandwidth bound and contribute significantly to decoding latency. To our knowledge, we are the first to study post-training quantization of recurrent states in GDN and KDA based language models. We find that uniform quantization provides a poor accuracy--storage trade-off: INT8 and FP8 alread…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27512v1 Announce Type: new Abstract: Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models. When a full-precision source checkpoint is evaluated and quantization is applied downstream without equivalent re-evaluation, this workflow creates a structural validation--deployment gap: because quantization is a many-to-one mapping over parameter space, source-precision certification does not guarantee behavioral equivalence in the deployed configuration. We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence, providing a theoretical basis for quantization-triggered backdoor attacks. Buildi…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.27507v1 Announce Type: new Abstract: Policy Gradient for Parallel State Entropy maximization (PGPSE) expands state-space coverage by training independently parameterized policies in replicated copies of the same environment. However, its pooled team-entropy score measures only collective exploration and cannot identify policies that contribute non-redundant coverage. We introduce Marginal Coverage Credit for PGPSE (MCC-PGPSE), which combines leave-one-policy-out coverage with state-owner specialization to estimate policy-specific credit. MCC-PGPSE preserves PGPSE's pooled objective and redistributes non-negative auxiliary intrinsic rewards according to these credits without changing their total mass. This redistribution is designed to discourage redu…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.

Hyperprobe 可讓 AI 代理在不重新部署的情況下直接除錯生產環境，幫助開發團隊更快定位和解決問題。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Today we released by far the largest update in the history of OpenClaw. It was built by 933 contributors, including 569 first-time contributors, and is composed of over 16,000 pull requests. You can read the full releas…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Most popularPro Plan $9/ month For builders ready to scale across sites. 15-day money back guarantee Up to 10k monthly events 30 websites & team members 5 years data retention Grow Action Agent & 24/7 Monitoring AI SEO…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The Cutting Room Floor (TCRF) is a much-beloved wiki dedicated to archiving and protecting unused content and unreleased builds from video games, and it’s been supported by hundreds of volunteers since its inception in…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Notifications You must be signed in to change notification settings Fork 0 Star 1 BranchesTags Open more actions menu Latest commit History 7 Commits 7 Commits Folders and files NameName Last commit message Last commit…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Notifications You must be signed in to change notification settings Fork 0 Star 0 BranchesTags Open more actions menu Latest commit History 5 Commits 5 Commits Folders and files NameName Last commit message Last commit…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Revisited: Guardian journalist Michael Safi looks into the world of artificial intelligence, exploring the dangers and promises it holds for society Today in Focus is on a summer break and will be back with new episodes from 1 September. In the meantime, we are bringing you season one of Black Box, before the launch of season two in early September. This episode was first broadcast on 21 March 2024. For decades, Eliezer Yudkowsky has been trying to warn the world about the dangers of AI. Now people are finally listening to him, but is it too late? 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：Notifications You must be signed in to change notification settings Fork 4 Star 30 BranchesTags Open more actions menu Latest commit History 438 Commits 438 Commits Folders and files NameName Last commit message Last co…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Cursor began rolling out Origin, its own code hosting platform, to paid users on Monday morning. Roughly three and a half hours later, GitHub's status page lit up with what became a six-hour-and-forty-two-minute global…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：--> [Submitted on 26 Aug 2026] Title:Redwood: A Frontier AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AI View a PDF of the paper titled Redwood: A Frontier AI Accelerator Designed, Verified…