AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20825v1 Announce Type: new Abstract: Clinical predictive models often rely on structured Electronic Health Record data, such as time-series and procedure codes. While recent approaches have begun leveraging unstructured clinical notes, they typically encode them as flat sequences, which may lose explicit relational and temporal structure present in clinical narratives. In response, we propose HERMES, a graph-based framework that operates exclusively on clinical text while preserving clinical relationships. This approach builds on two key ideas. First, personalized Knowledge Graphs (KGs) are constructed through Large-Language-Model-guided extraction from clinical notes with Contrastive Logic Modeling that explicitly captures temporal dynamics and trea…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20824v1 Announce Type: new Abstract: We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small Language Models (SLMs) with fewer than 3 billion parameters, running entirely on consumer hardware. We evaluate seven distinct approaches, including token-level entropy early stopping, semantic entropy estimation, and uncertainty-aware routing to larger expert models, across 7 model pairs and 5 standard NLU benchmarks. Our key finding is that token-level entropy is effectively blind in SLMs: in 91% of dataset-model combinations, mean token entropy is near zero regardless of answer correctness, rendering token-based confidence signals unusable at this scale. We demonstrate that semantic entropy, computed by generat…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20978v1 Announce Type: new Abstract: High-consequence subsurface decisions are often made under severe data scarcity. Experts may arrive at competing interpretations of the same subsurface system, yet early in a project there is rarely a practical way to determine which one is most realistic. This uncertainty can persist until several wells are drilled, often costing millions of dollars. Existing approaches for evaluating geologic interpretations rely either on subjective judgment or on dense data that are rarely available in early-stage investigations. We present a workflow that addresses this challenge by translating competing geologic interpretations into alternative spatial priors and ranking them according to their consistency with hydraulic-hea…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20968v1 Announce Type: new Abstract: In non-stationary online learning, dynamic regret has attracted increasing attention as a measure of how well an online learner performs against a time-varying comparator sequence. Despite considerable advances, attaining optimal bounds for strongly convex and exp-concave losses often involves intricate analysis. In this paper, we present a \textit{simple} framework that reduces dynamic regret minimization to switching regret minimization. As a result, we can derive dynamic regret bounds by using off-the-shelf algorithms with switching regret guarantees. The key idea of our reduction is to construct, for \textit{any} comparator sequence, an auxiliary random sequence that is unbiased at each round, with the control…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20954v1 Announce Type: new Abstract: We present a novel end-to-end model-based Reinforcement Learning (RL) algorithm for efficient policy synthesis under given Linear Temporal Logic (LTL) specifications (e.g., safety or reachability) in unknown environments. To do so, a Limit-Deterministic B{\"u}chi Automaton (LDBA) representation of the LTL task is synchronised with a Bayes-Adaptive Markov Decision Process (BAMDP) representation of the environment, which allows us to leverage an enhanced exploration-exploitation trade-off that is achieved via Bayesian RL, as opposed to traditional non-Bayesian approaches. We further propose a novel Bayes-Adaptive Monte-Carlo Planning (BAMCP) algorithm to allow for approximate Bayes-optimal strategy synthesis in 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:2609.20942v1 Announce Type: new Abstract: Large language models (LLMs) increasingly participate in scientific evaluation, both as automated reviewers and as assistants to human reviewers. As model-generated reviews enter public data and future training corpora, AI peer review can become recursive: later reviewers learn from judgments produced by earlier models. We study one step of this feedback loop in a controlled setting. Starting from Llama 3.1 8B, we first fine-tune a reviewer on official ICLR reviews from 2018--2023 and then train four successor models on ICLR 2024 data with systematically varied mixtures of official and model-generated reviews. Our study shows that introducing synthetic reviews compresses rating distributions and reduces both same-…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20912v1 Announce Type: new Abstract: In this work, we study the neural scaling laws of RydbergGPT, an autoregressive transformer model trained on qubit projective measurement data gathered from interacting Rydberg atom arrays. The quantum system is known to exhibit a finite-size remnant of a critical point as the laser detuning parameter is varied. We find that near the critical point the transformer loss as a function of training dataset size is well described by a power-law with a loss floor correction. However, away from criticality the quality of the power-law description is substantially reduced. We then compare the statistical structure of both Rydberg measurements and natural-language corpora using an entropy-normalised, finite sample correcte…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20906v1 Announce Type: new Abstract: Quasars are luminous objects in the universe that exhibit stochastic brightness variations encoding information about the supermassive black holes powering them, and modeling these variations from ground-based survey data time series, known as light curves, is a statistical challenge. This paper reviews how stochastic differential equations (SDEs) have been adapted with neural network parameterizations to overcome this challenge in history. We create the Continuous-Delayed-Memory Stochastic Gradient Descent which depend on the past state of the discrete iteration process. We performed the simulation on some 2-dimensional landscape and observed some wider-exploration and more precise convergent behavior compared to…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20904v1 Announce Type: new Abstract: Hybrid motor-imagery brain-computer interfaces (MI-BCIs) combining EEG and fNIRS can outperform EEG-only systems by exploiting complementary electrophysiological and hemodynamic information. To obtain such hybrid information when paired EEG-fNIRS acquisition is unavailable or inconvenient, recent studies have focused on EEG-to-fNIRS cross-modal generation. However, existing methods still suffer from slow generation and often require pretraining, limiting their use in real-time MI-BCI scenarios. Although one-step generative models offer an attractive route to low-latency synthesis, removing the iterative refinement process can reduce generation fidelity and introduce non-physiological artifacts. To address these pr…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20888v1 Announce Type: new Abstract: Massive KV caches can cause severe memory-bandwidth bottlenecks during long-context decoding. Sparse attention methods mitigate this via selective loading, but that comes at a cost: rigid heuristics drop necessary context, leading to quality degradation. We introduce \textbf{Elastic Threshold Attention (ETA)}, an end-to-end trainable architecture that achieves hardware-accelerated decoding speed without sacrificing dense model quality. ETA predicts dynamic, contextual thresholds directly from query representations, allowing the model to allocate dense-like context to difficult retrieval or reasoning steps while pruning routine tokens. To learn this policy from scratch without representation collapse, ETA \emph{mul…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20886v1 Announce Type: new Abstract: Business intelligence (BI) is a cornerstone of enterprise decision-making and is widely used by enterprise users in software such as Power BI and Tableau. In traditional BI workflows, users need to prepare data by (1) identifying relevant tables, (2) performing data transformations, and (3) building join relationships, before they can (4) answer their business questions. These steps can be complex and time-consuming, making BI challenging. Given the strong capabilities of large language models (LLMs) in working with data, we study their ability to answer BI questions end-to-end, without requiring users to manually perform the tedious preparation steps. To do this, we harvest a large collection of real-world BI pro…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20883v1 Announce Type: new Abstract: Despite the widespread use and success of generative AI techniques today, theoretical guarantees on learning a distribution supported in $d$ dimensions from $n$ samples degrade as $O(n^{-1/\Theta(d)})$, though shown to be minimax optimal. We hypothesize that present bounds are too pessimistic because smoothness assumptions are not enough to capture the structure of distributions that often appear in real applications. Consequently, we introduce the class of sparse priors and define the "Sparse Dimension" as a measure of sparsity of a prior over the space of all distributions. We show that distribution learning under a $k$-sparse prior achieves a Bayesian risk lower bound of $\Omega(\sqrt{k/n})$ under common distan…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.21165v1 Announce Type: new Abstract: Off-target protein binding is a major source of adverse effects for small-molecule drugs, yet most structure-based molecular design methods focus on generating selective compounds de novo rather than improving the selectivity of existing, well- characterized drugs. We introduce specificity optimization (SpecOpt), a molecular design task that seeks constrained structural modifications to an existing compound that increase its binding preference for an intended target over known off-targets while preserving its structural identity and drug-like properties. To enable systematic evaluation, we construct a ChEMBL-derived benchmark from compound-target interaction data, identifying intended targets through curated drug-…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.21157v1 Announce Type: new Abstract: Large Language Model (LLM) agents are increasingly being explored for chip design, but most existing approaches operate directly at RTL. We ask whether agents can design better chips by leveraging higher-level abstractions. We compare Direct RTL Design, Agent-based HLS Design, Post-Compiler HLS Refinement, and Post-HLS RTL Refinement, and combine Agent-based HLS Design with Post-HLS RTL Refinement as Agent-based HLS with RTL Refinement (AHRR). We use FPGAs as a practical, easy-to-deploy platform for end-to-end evaluation, but note that the design-flow tradeoffs we study are largely independent of the target technology. Across a diverse 11-tasks benchmark suite, AHRR achieves a 2.6$\times$ geometric-mean speedup ov…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.21149v1 Announce Type: new Abstract: Before patients can use AI-assisted psychiatric intake systems, health systems need practical ways to routinely evaluate these tools against their clinical standards for quality assurance. Because clinicians may use different intake styles, evaluation for this task must (1) support comparison across interviewing approaches, (2) minimize clinician burden, and (3) measure clinically relevant performance for health systems deploying these technologies. We present a clinician-grounded evaluation platform built around a memory-augmented patient simulator for open-ended AI interviewing, InterviewPlayground. We created interactive patients using InterviewPlayground with our expert-authored vignettes, constructed a simula…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.21139v1 Announce Type: new Abstract: Replacing attention in a pretrained language model is a compatibility problem: a plausible substitute may alter representations expected by later layers. TinyCeNN-LM introduces a \emph{quality-gated post-training conversion} framework using CeNN-inspired cellular-recurrent layers with bounded local processing, compact recurrent memory, routing, fusion, and accept-or-rollback validation. Three implementations are studied: Integrated Memory, MemoryFusion, and PDelta3-GDN2-CLVR+Local32. Strict PDelta3 conversion accepts a layer only when representation and NLL criteria pass fixed thresholds. On SmolLM2-135M, layers 0-2 are accepted with cumulative $\Delta\mathrm{NLL}=+0.01209$, while layer 3 is rejected despite accep…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.21113v1 Announce Type: new Abstract: Fine-tuning has emerged as a widely adopted approach for adapting LLMs to a variety of downstream tasks. However, how it reshapes their internal mechanisms remains poorly understood. To address this, we investigate how fine-tuning alters internal representations in LLMs, including attention patterns and layer-wise activations, and examine whether these changes are linked to task-relevant components identified by EAP (e.g., attention heads and logit-level activations) that drive task performance. We find that EAP-identified components are concentrated within specific layers, indicating a degree of functional localisation in how models internalise task-specific behavior. Notably, the distribution of these components…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.21096v1 Announce Type: new Abstract: In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated responses. We analyze the Forman-Ricci curvature to identify structural patterns indicating information bottlenecks in attention graphs. We then introduce a method that captures both semi-local and global information-flow characteristics of attention heads associated with hallucinated responses. We evaluate our approach extensively across several LLMs and established benchmarks. Empirical results demonstrate that our proposed single-pass approach provides consistent improvements over existing attention-based and multi-response baselines across two hallucination-de…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.21061v1 Announce Type: new Abstract: Automatic target recognition (ATR) with synthetic aperture sonar (SAS) supports advanced naval capabilities, but deep learning is constrained by scarce target imagery, background clutter, and human-in-the-loop assessment. We adapt DINOv3 Vision Transformer (ViT) models to underwater SAS ATR using a three-stage parameter-efficient framework. Stage 1 uses Low-Rank Adaptation (LoRA) while freezing the ViT backbone, bridging the gap between natural-image pretraining and underwater acoustic propagation. Stage 2 uses hard-negative mining to strengthen the decision boundary against acoustic mimics, including rocks and sediment formations resembling man-made targets. Stage 3 uses Supervised Contrastive Learning (SupCon) 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:2609.20981v1 Announce Type: new Abstract: Autoregressive (AR) models suffer from local greediness, while diffusion language models (DLMs) often lack the strict causal structure required for reasoning. To combine the advantages and overcome the drawbacks of the dual, we propose Causal Latent Revision (CaLR), a framework that reformulates reasoning as constrained latent optimization. By adopting a causal topology matrix (CTM) from an expert model and implicit differentiation, CaLR performs gradient-guided ``thought revision" to enforce logical consistency, enabling dynamic self-correction of intermediate steps during parallel generation. Empirically, CaLR achieves SOTA DLM performance on complex benchmarks, surpassing strong AR baselines and demonstrating s…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20974v1 Announce Type: new Abstract: In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual information. We propose Attention-Aware Routing (AAR), which augments the router with temporal and spectral features extracted from a sliding window of attention weights that represent a summary of the model's contextual state, disentangled from the hidden state. Keeping the base transformer entirely frozen, we train only the routing parameters, isolating routing as the sole variable. AAR improves GSM8K by +3.37 pp over a routing-only SFT baseline on OLMoE. Beyond performance, we show that routing and attention form a coupled circuit: routing changes at layer l pro…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.20971v1 Announce Type: new Abstract: Long-context large language model inference is increasingly limited by prefill, where dense self-attention processes the entire prompt before generation begins. Sparse block selection can reduce this cost, but a block centroid may hide a highly relevant token among many irrelevant ones. We call this failure mode mean dilution and propose RBS-Attention, a training-free sparse-prefill method with two complementary selection branches. A centroid base branch captures average relevance, while a rescue branch uses the maximum key-block radius and its prompt-, layer-, and head-dependent distribution to identify blocks at risk of underestimation. Independently thresholding the two branches and combining their masks contro…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Seventh intergenerational report also outlines how Australia is at cusp of an uncertain age of artificial intelligence Follow our Australia news live blog for latest updates Get our new political email, free app or daily news podcast There will be more Australians dying than being born in 40 years’ time, according to the government’s latest intergenerational report, which lays bare the fundamental challenges of managing an ageing population at a time of rapid change and lower economic growth. The country’s seventh IGR also outlines how Australia is at the cusp of a new and uncertain age of artificial intelligence that will shape the economy and society over the coming four decades. 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：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Using GPT-5.6, V7 turns scattered company files into context agents can use to complete complex, source-linked work.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The CEOs of tech firms issue stark warnings over the rate of change, with AI capability doubling every four months Recently, Jacob Coxon, a researcher at Anthropic, quit his job over concerns that AI was on a collision course with humanity. A flurry of headlines put the spotlight on the current crisis: unregulated competition between technology companies and between the US and China is putting our global infrastructure at risk at the very least, and threatening human existence at worst. One’s mind fills with pictures of robot armies or systematic blackmail. 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：Discussion | Link

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： It has been half a month since I started a new role at a big company. Nobody knows anything here. The specs, code, tests, PRDs, tickets, resolution of those tickets, reports, etc., everything is made by Claude Code. Nobody on my team likes this. They are being forced to ship as much as they can. I have heard multiple times from higher management that pushing code is not a bottleneck, so why are we slow? People are working 12 to 13 hours a day just to press enter. Nobody is reading anything. Everyone, literally everyone, from an L1 to an L7 engineer here is doing the same thing. Talk to Claude. — voxium Tags: ai-misuse, llms, ai, generative-ai

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Flet 1.0 shipped on September 15, 2026, and the team now calls the framework ready for production apps. We look at what changed: a layered CI suite that drives packaged apps on real devices, bundled Python 3.12, 3.13 and 3.14, more than 100 mobile ready packages, faster control diffing, and dart-bridge in process communication. We also cover the one migration trap that will bite 0.28 users. The post Flet 1.0 Released: Build Production Web, Desktop and Mobile Apps in Python Only appeared first on MarkTechPost.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： My comment on MCP was always a bad idea? — Hacker News. This article entirely misses the value that MCP brings today. Sure, there's almost no reason to use MCPs if you are running a full-blown terminal agent (Claude Code, Codex, Meta Muse, OpenClaw etc) with unfettered internet access - just let it call APIs directly. If you want to operate something that's less YOLO than that, you'll find yourself wanting: Control over exactly which external services it can access A way to handle authentication that doesn't allow the agent to directly access API keys A sensible UI to allow users to connect and authenticate further services Strong audit logging for what's going on MCP makes all of that so much easier to provide. Thinking MCP is obsolete because full codi…