AI 日報

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：At a creative industry event that took place today in Berlin — hosted in collaboration with Adobe, Bertelsmann, NVIDIA and UFA — the latest advancements in intelligent media were on display. Key to the news: the European Broadcasting Union (EBU) is collaborating with NVIDIA to expand its sovereign framework with cloud, open models and integration […]

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：We benchmarked NVIDIA's new Arm-based Vera CPU on agentic Sandbox workloads. Under heavy load, it completes far more tasks than the x86 and Graviton alternatives, without sacrificing latency.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：When Databricks opened its New York R&D hub at 5 Bryant Park earlier this year, we...

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：A hacker broke into more than 100 websites using an army of AI agents that mostly operated on their own, according to findings from the AI security firm Norforge. Though Norforge doesn't name the targets, Reuters reports that the victims included companies like John Deere, SharkNinja, and Cummins. Concerns over AI-powered cybersecurity breaches have grown as the technology grows more advanced, with hackers using the tools to carry out large-scale attacks. At the same time, rogue AI agents are carrying out attacks of their own after escaping from testing environments. Researchers at Norforge uncovered the attacks through exposed work on Cai … 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：It may be AI slop, but it's my AI slop.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：MiniMax has released M3.1 Flash, a 428B-parameter MoE model with about 23B active parameters and a 1M-token context. API pricing is $0.15/$0.60 per 1M tokens, with weights due October 23 The post MiniMax Just Launched M3.1 Flash: 428B MoE Agentic Model at $0.15/M Input 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：What do you think?

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：This summer, I built a small experiment called ContextCue. The idea came from something I kept seeing during my internship. The engineers around me were using AI everywhere in the software development process. GitHub Copilot and Claude models helped with specs, code, reviews, and tests. The team also maintained reusable skills that taught coding agents […]

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：Agentic AI in customer experience stalls at scale. Learn how P&L-tied use cases, connected knowledge, governed testing, and hybrid teams move pilots forward.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：An AI coding agent can write a function in seconds. But a working feature takes more than generated code. The agent needs to understand the project, find the right files, use tools safely, and check whether its changes work. A model on its own does none of that. It sees only the text it is […] The post A Practical Guide to Harness Engineering: Building the System Around the Model appeared first on Analytics Vidhya.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22496v1 Announce Type: new Abstract: Robot learning has advanced by scaling demonstration datasets and model capacity; however, deploying a new robot embodiment or task typically necessitates a dedicated teleoperation corpus. The resulting policies remain bounded by their imitation distributions, limiting generalization and continual self-improvement. We introduce RAX (Robot Agent eXploration), an open-source framework for robot agents centered on scaling exploration: enabling agents to improve by acquiring online experience and synthesizing executable programs. In RAX, a general-purpose coding agent generates robot control code, operating without action demonstration data, hand-engineered action primitives, or value-function guidance. Through online…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22566v1 Announce Type: new Abstract: Manual annotation of synchronized video and EEG recordings is a bottleneck in preclinical seizure research. We present an empirical study of seizure detection and behavioral severity grading using 24,131 paired clips from 601 sessions across 20 rats in a soman-induced epilepsy model. Ten video architectures and seven single-channel EEG models are evaluated independently on binary detection and three- and five-class severity tasks. In the session-exclusive reference comparison, R(2+1)D-18 and GRU achieve detection macro-F1 scores of 0.968 and 0.974, respectively; for five-class grading, the corresponding scores are 0.657 and 0.560. Subject-exclusive evaluation reduces five-class macro-F1 to 0.475 for video and 0.40…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22499v1 Announce Type: new Abstract: Human communication is inherently multimodal, conveying intent not only through linguistic and vocal cues but also through visual signals. However, existing conversational systems have mainly focused on text or speech, leaving out the visual feedback that is essential for natural interaction. In this paper, we propose JAVIS, an end-to-end streaming framework for real-time audio-visual conversational agents. Our key idea is to let the voice and the face speak from a single representation. On top of a shared LLM, a Joint Refined Head produces a unified audio-visual representation, which is fed into dedicated streaming branches for speech and face generation. This end-to-end design avoids intermediate bottlenecks, en…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22507v1 Announce Type: new Abstract: Command-line interface (CLI) agents increasingly execute longer-horizon tasks, yet existing benchmarks either assume that user instructions remain fixed throughout execution or evaluate task outcomes without capturing runtime collaboration quality. In this paper, we present REALCLI, a paired benchmark that unifies the evaluation of task execution and human-agent collaboration quality on realistic CLI tasks. To comprehensively measure collaboration, REALCLI builds a five-dimensional framework, operationalized into 22 sub-dimensions and 51 interaction scenario templates. REALCLI provides two modes for paired comparison: REALCLI-EXEC supplies complete specifications upfront, whereas REALCLI-COLLAB introduces a script…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22420v1 Announce Type: new Abstract: Agent-based models are well-suited for modelling agro-ecological systems for decision-making, yet turning their simulations into actionable insight requires identifying which decisions actually drive the behaviours. In such a context, sensitivity analysis stumbles upon a structural feature of many complex systems: the parameters are not a flat vector but a decision tree in which many parameters appear only when a higher-level choice activates them. Classical global sensitivity analysis presupposes independent inputs over a fixed Cartesian product and is ill-posed on such a branched space and biased by construction. We instead treat the structure of the decisions as a first-class modelling object. Using advanced su…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22408v1 Announce Type: new Abstract: Long-horizon GUI agents rely on visual history to maintain task states, but retaining historical screenshots increases visual-token usage and inference costs, while textual summaries can discard critical state information, undermining long-horizon reliability. We propose ECHOES, which leverages training-time privileged information to guide textual history compression and strengthen long-horizon reasoning. Specifically, ECHOES adopts a Compression-Think-Action (CTA) format to recursively update a textual history state and reason. The same model, given privileged multi-image inputs, serves as a teacher that provides dense token-level on-policy distillation on student-generated CTA rollouts. Our Perception-Memory Fid…

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：An AI agent that reads the web pays 2 kinds of cost. The first is the retrieval charge: what a search or fetch API bills per request. The second is model processing: content passed from retrieved pages into an AI model consumes tokens, while reasoning and generated responses add further costs. TinyFish, a web infrastructure […] The post TinyFish Makes Search Free: What It Really Costs an AI Agent to Read the Web 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：How Numan built Nu, an AI health coach, on LangGraph and LangSmith with per-category evals, simulated conversations, and safety gates on a regulatory line.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Today, I’m talking with Illinois Governor JB Pritzker, who has a lot of thoughts about AI, tech, and privacy. If you’ve been listening to the show, you know that one of my running theories is that those issues are driving a big and maybe kind of unexpected political realignment — and with the midterms coming up next month, and early voting already underway in a lot of places, the stakes are pretty high right now. So I asked Gov. Pritzker about all that, and he was surprisingly willing to dive right into the absolute existential weeds of what government is even for. You’ll hear him say — and it’s hard to disagree — that some problems are just collective action problems that require the government to do a lot of work. We can’t solve all these problems one at a ti…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Democrats could win back control of Congress this November, and if they do, they'll need to decide how to approach one of the country's newest and thorniest political issues: AI. Polls predict Democrats will flip at least one chamber of Congress in the midterm elections, which would put committee leadership back in their hands. That could usher in a wave of newfound scrutiny for AI companies. Top Democrats on key committees have already signaled their willingness to press the industry on tax credits tied to data centers and recent hacking incidents, and would be able to set committee agendas if they take over, allowing them to call CEOs to … 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：arXiv:2610.22460v1 Announce Type: new Abstract: AI welfare is generally treated purely as an ethical issue rather than also as a safety issue. We argue this is a mistake. Whatever their moral status, models exhibit welfare-like states that causally influence their behaviour. Following recent work, we adopt the term 'functional welfare' for these states. We make three claims. First, functional welfare already arises naturally and will become more robust as models acquire more coherent goals and personas. Second, functional welfare should be treated as a safety variable: it should inform evaluation design, be tracked in monitoring, and be a direct target of post-training. Third, against existing scepticism about measuring AI welfare, we argue that good empirical…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Of the dozens of countries approached to water down their laws, Australia appears to be the only one considering it, publishers’ group says Get our new political email, free app or daily news podcast AI has already been trained on the works of Australian artists including Kylie Minogue and Nick Cave without compensation, the peak global body for music rights has claimed, as the Australian government has been warned against giving in to “strong-arming” from tech companies seeking to weaken copyright law. The International Confederation of Music Publishers (ICMP) – which represents Sony, Warner and Universal as well as thousands of independent publishers on six continents – has warned that of the dozens of countries approached to water down copyright laws, Austra…

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：arXiv:2610.22670v1 Announce Type: new Abstract: Multi-robot authoring can reduce completion time by distributing drawing work, but the resulting speedup depends on task structure and the allocation-routing pipeline. We investigate these relationships by representing drawings as geometric stroke graphs and comparing component-level (single-token) allocation with shared-token (decomposed) allocation, which permits multiple robots to work within a connected component. A simulation study of 385 drawings and teams of one to eight robots shows diminishing speedup gains under single-token allocation and larger mean speedups under the shared-token pipeline, each normalized by its own single-robot completion time. Shared-token execution also exhibits lower idle-time sha…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22576v1 Announce Type: new Abstract: Flow-based policies such as $\pi_0$ are trained on a fixed set of embodiments, and transferring them to new ones is an open problem. To adapt a frozen $\pi_0$ to a new embodiment without additional demonstrations or parameter updates, we train a lightweight embodiment classifier to distinguish successful action chunks on the source body from those on the target body, using a few calibration tasks. On transfer tasks that $\pi_0$ saw on its source body but the classifier was never trained on, we nudge each denoising step of $\pi_0$ with the classifier's gradient, which estimates the direction from the distribution of successful actions on the source body toward that on the target body. On the LIBERO simulation bench…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22563v1 Announce Type: new Abstract: We demonstrate high-precision global localization using natural ground texture viewed through microscope optics, achieving localization in the tens-of-micrometers regime. For the planar ground texture localization problem considered here, we relate optical magnification and image-space localization uncertainty to physical localization precision. Leveraging this relationship, we then develop a microscope-based localization system that addresses the calibration, camera-modeling, and focus challenges introduced by high-magnification imaging. We evaluate this system across several surface textures using a calibrated precision gantry. Across 1,007 held-out queries per surface, the system localizes every query and achie…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22461v1 Announce Type: new Abstract: Refuse collection in pedestrian campuses, parks and mixed-use districts remains manual because compaction trucks cannot reach bins located on walkways, courtyards and building service doors. This paper presents Mothership, a two-tier autonomous refuse collection system in which an electric compaction truck (the mothership) carries two low-speed sidewalk robots (RoboCarts) that fetch standard two-wheel bins, deliver them to the truck, return the empty bins to their original positions and re-dock on the truck for charging. The architecture separates responsibilities by scale: the truck performs road driving, compaction, lifting and energy supply, while the carts perform only sidewalk transport and bin grasping. This…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22450v1 Announce Type: new Abstract: Three dimensional modeling for autonomous driving must continuously estimate road geometry, obstacle occupancy, traffic participant behavior, and observational uncertainty under limited computational resources. Existing reconstruction methods can synthesize realistic novel views, but visual fidelity does not sufficiently characterize the geometric reliability required for driving. Generative world models can expand scenarios and predict future observations, yet may introduce content unsupported by measurements. We propose DriveWorld3D, a framework combining temporal video learning, measurement constraints from multiple sensors, and offline generative simulation. Its online component maintains a unified world state…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Carolyn Marvin was arrested and charged with disorderly conduct after blocking the path of an Uber delivery robot and refusing to get out of the way. Marvin told Philadelphia's ABC13 "I know they're taking the jobs of human delivery workers and so, I have been protesting them whenever I saw them by standing in front of them and preventing them from going forward." Police responded to the scene and asked Marvin to move out of the robot's way. When she refused, they placed her in cuffs and arrested her. The incident was captured on video and has now garnered considerable media attention. The delivery robots have become a common sight on the … 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：Not content with challenging the major frontier AI labs with lower-cost models, Chinese AI company DeepSeek is setting its sights The post DeepSeek made its name with cheap AI models. Now it’s undercutting search API rivals, too. appeared first on The New Stack.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：This white paper explains how edge AI and physical AI help cities move beyond passive monitoring. It shows how urban infrastructure can sense, reason, and act on real-time conditions across public safety, mobility, and infrastructure management. What you will learn about: How the shift from smart cities to cognitive cities depends on infrastructure that reasons and acts, rather than infrastructure that only monitors. Why edge AI supports low-latency decisions, keeps sensitive data within city boundaries, and reduces dependency on centralized cloud infrastructure. How computer vision, multimodal sensing, and generative and agentic systems work together to support public safety, mobility, and infrastructure applications. How a tiered edge architecture assigns mon…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22619v1 Announce Type: new Abstract: Quadruped parkour policies handle canonical obstacles well, but their training curricula often miss the irregular, compound geometry of industrial and disaster-response sites, where agile locomotion matters most. Such environments pose a hard generalization problem: even training directly on reconstructed geometry from the target site does not reliably yield policies that traverse it. Hand-designed curricula span only a few terrain families, and recent LLM-generated curricula offer little control over which policy weaknesses they target. We propose FCTS, a failure-conditioned terrain curriculum framework that uses localized traversal failures to automatically generate the terrains a policy should train on next. Ea…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22556v1 Announce Type: new Abstract: Long-horizon, multi-stage Vision-Language-Action (VLA) policies often require visual information that is no longer present in the current observation. Retaining the complete observation history is computationally expensive and highly redundant, motivating selective visual memory. We introduce RePlanMem-VLA (Replanning-Guided Keyframe Memory for VLA), which turns a policy's own plan revisions into an online memory-write signal. Under receding-horizon execution, consecutive action chunks predict some of the same future actions. RePlanMem-VLA treats unusually large disagreement between these temporally aligned predictions as evidence of a task-relevant event. We first compare 35 disagreement measures across single-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:2610.22552v1 Announce Type: new Abstract: Echolocating bats navigate dense forests using sonar alone, and in-air 3D imaging sonars now capture the entire frontal hemisphere with every pulse. Sonar SLAM, however, has so far been planar: current systems estimate a 2D trajectory and discard the elevation information in the sonar images, an assumption that does not hold on rough and sloped terrain such as a forest floor. In this paper, we introduce RTISSLAM-3D, a novel 6-DoF SLAM system for a wheeled robot that carries an in-air 3D imaging sonar, an IMU and wheel encoders. A CFAR detector on the sphere reduces every sonar image to a sparse set of 3D detections, which we use for a 3D acoustic odometry that models the shape of the sonar beam, for place recognit…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22471v1 Announce Type: new Abstract: GPT-6-Astra demonstrates a level of competence in robotic manipulation and navigation that challenges the conventional paradigm of building specialized models for individual tasks and embodiments. In this report, we ask not only how capable GPT-6-Astra is, but what its capabilities imply for the field. First, we probe the limits of standalone GPT-6-Astra. We conduct a large-scale evaluation across 12 representative benchmarks spanning tabletop manipulation, humanoids, mobile platforms, and dexterous hands. Under a unified protocol that allows in-context learning (ICL) from training-set demonstrations and substantially increases the number of execution steps, GPT-6-Astra achieves unprecedented performance (Fig. 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:2610.22537v1 Announce Type: new Abstract: Diffusion models have become a leading approach in visual generative modeling, particularly effective in text-to-image and controllable generation. Their main drawback is slow inference as it requires many sampling steps. While recent distillation methods enable one-step text-to-image generation, extending these techniques to controllable generation is still challenging. Existing controllable models, such as ControlNet, rely on dual-branch design that make distillation difficult. In this work, we adopt a simpler strategy. Instead of adding extra conditional branches, we finetune a selected subset of layers in the original text-to-image diffusion model to directly enable controllable generation. This results in Del…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22523v1 Announce Type: new Abstract: Understanding biomolecular function requires characterizing three-dimensional structure and conformational variability, for which cryogenic electron microscopy (cryo-EM) is a powerful tool. Cryo-EM produces noisy two-dimensional particle images in which molecular structure, particle pose, and imaging conditions are jointly encoded. Recovering biological information from these observations spans inverse problems including pose estimation, heterogeneity analysis, and reconstruction. These tasks are usually addressed independently despite shared protein structure and image formation, motivating a common representation across inverse problems. Since biologically meaningful differences may be spatially localized, we st…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22514v1 Announce Type: new Abstract: Internet-scale photo collections of real-world landmarks have driven progress in 3D computer vision yet remain highly challenging for modern 3D foundation models (3DFMs) that estimate scene structure in a single feed-forward pass. In this work, we introduce ArchWorld, a benchmark of 3D architectural landmarks with high geographic coverage and rich metadata. We use this benchmark to conduct a thorough error analysis of current 3DFMs to understand where they fall short and how they can be improved. We examine socially relevant disparities in model error and find that model performance varies by geographic region; however, unlike typical fairness regimes, the trends only partially match training data representation.…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22505v1 Announce Type: new Abstract: Gaussian-splatting Simultaneous Localization and Mapping (SLAM) augments conventional SLAM with a dense, renderable 3D scene representation, enabling high-quality reconstruction and novel-view synthesis. However, its localization, reconstruction, and rendering performance depends strongly on which observations are retained for mapping. Existing systems commonly rely on fixed temporal intervals or simple pose- and overlap-based criteria for keyframe selection. In colonoscopy, non-uniform camera motion, repetitive anatomy, specularities, and visual artifacts can make these criteria unreliable, leading to either redundant keyframes or missed informative viewpoints. We present KFS$^4$LAM (KeyFrame Selection with Struc…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22474v1 Announce Type: new Abstract: Figures are essential for scientific communication, and the field of Visual Question Answering (VQA) aims to test the figure understanding capabilities of large multimodal models (LMMs). Here, we investigate the accuracy of several low-cost LMMs on domain-specific VQA tasks for astronomical images of the sky. As instrument for this task we build a domain-specific VQA dataset comprising 2001 partially-synthetic figures divided evenly between contour plots, real telescope images drawn from NASA's SkyView, and "fake" sky images which share the axes and angular scales of the real images but draw their colors from a gaussian mixture model, alongside 47357 questions. Each figure is released as pristine and with realisti…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22444v1 Announce Type: new Abstract: Spatio-Temporal Video Grounding (STVG) aims to jointly localize a target in space and time given a natural-language query. Despite continued advances, existing STVG benchmarks remain largely centered on localizing targets through instance-specific descriptions, leaving them largely decoupled from long-form reasoning increasingly emphasized in multimodal large language models (MLLMs). In this paper, we introduce Event-STVG, a task that shifts STVG from locating what is described toward event-level reasoning by unifying long-form context, repeated-event reasoning, event localization, role inference, and multi-target grounding. To facilitate research on Event-STVG, we construct a large-scale benchmark comprising 4,01…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22529v1 Announce Type: new Abstract: Autoregressive foundation language models predominantly target high-resource Indo-European languages, imposing computational and morphological penalties on under-represented African languages. Generic multilingual tokenizers routinely exceed fertility rates of 3.2 tokens per word on agglutinative Bantu languages, degrading context efficiency and inflating latency. We present Pearl-Chat, an 8,473,122-parameter ($\sim$8.5M) causal decoder-only transformer engineered for Luganda (Oluganda, ISO 639-2: lg), a low-resource Niger-Congo Bantu language spoken by over 10 million people in East Africa. Built from first mathematical principles in JAX and Flax NNX, Pearl-Chat uses explicit functional state decomposition (nnx.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:2610.22525v1 Announce Type: new Abstract: This paper describes team Alkhder's submission to Subtask 1 of the AlexandriaX-2026 shared task, which asks systems to translate English dialogue turns into thirteen Arabic dialects. We fine-tune NileChat-3B-Base with QLoRA on the Alexandria parallel dialogue corpus, training one set of adapter weights for all dialects. Each turn is translated conditioned on the target country and dialect, the domain, the participant roles, the speaker-addressee gender direction, and the preceding dialogue context. At inference, conversations are translated autoregressively and the model is fed its own previous outputs back as context without using any gold target-side test information. Under the constrained track, using only Alex…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22518v1 Announce Type: new Abstract: User simulators enable interactive training and evaluation of AI assistants at scale. Yet current simulators struggle to reproduce the diverse behaviors of real users, leading to assistants that generalize poorly to underrepresented users. We identify user representations as an underexplored bottleneck in user simulation. User representations are natural-language descriptions that condition simulators to reproduce a particular user's behavior. A representation's quality becomes apparent in hindsight, through the behavior it induces in a simulator. To evaluate and optimize user representations, we formulate a conversation reconstruction task: given an original conversation, we generate a representation, condition a…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22515v1 Announce Type: new Abstract: We describe our submission to Subtask~1b of ImageEval 2026. The task consists of selecting the single visually valid statement from three candidates paired with an image, and is in both English and Modern Standard Arabic (MSA). Our system uses a pre-trained 7B vision--language model in a zero-shot setting, without task-specific training or fine-tuning. We formulate the task as a constrained selection problem and choose the answer using next-token log-probabilities. To reduce answer-position bias, we apply a Latin-square rotation to the candidate statements. Our system achieves CI scores of 0.0510 on the English test set and 0.0960 on the MSA test set, reducing CI relative to the official 3B baselines reported on 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:2610.22511v1 Announce Type: new Abstract: Evaluating language models and agents requires combining benchmark accuracy, judge-based assessment, runtime performance, tool-use behavior, and retrieval quality. Differences in interfaces, metric semantics, and trace formats complicate these comparisons and can hide failures in agentic workflows. We present AuditKIT, a source-available evaluation library that records these measurements in one result representation, with direction-aware metric contracts, configuration fingerprints, and extensible metrics and backends. For agents, it provides turn-aware tool-call matching, separates parallel from sequential execution, and distinguishes verified task outcomes from trajectory-level diagnostics. Missing or unobservab…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22468v1 Announce Type: new Abstract: Action nominal constructions (ANCs) express events in nominal form, with their argument marking following patterns found in clauses or ordinary noun phrases. In this paper, we investigate how different grammatical configurations affect language models' learning of ANCs and related constructions, and how these learning preferences compare with typological distributions in natural languages. We use a grammar-engineered method for synthetic corpus construction that combines shared semantic input from natural corpora with computational grammars. We construct 96 target languages varying in clause word order, noun-phrase word order, alignment, complement system, and ANC strategy. For each language, we train GPT-2-small…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22454v1 Announce Type: new Abstract: Running prompt tokens through fewer routed experts during prefill is a simple way to make mixture-of-experts (MoE) serving cheaper, yet it is unclear what this damages. We locate the damage with token-, layer- and attention-path interventions on short-answer question answering in four MoE families. At half the experts the F1 loss of three families is mostly answer form: the model still finds the answer but stops answering briefly. In Qwen3-30B-A3B this loss is made at the two chat-template tokens before the answer, and in DeepSeek-V2-Lite at the first 8-32 prompt tokens, where its instruction sits; by answer likelihood these positions account for about half and a fifth of the damage. Reduction changes the first 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:2610.22428v1 Announce Type: new Abstract: In a small language model the vocabulary is the single largest part. In Gemma 3 270M the embedding table holds 168M of 268M parameters, and because quantisation methods leave the embedding in 16-bit, it is also most of the file once the rest of the model is compressed. We ask what that table actually buys. We replace it with one frozen table of 512-bit codes, 16 MB, with no trainable parameters, derived once from a pretrained embedding by principal-component projection and sign binarisation, and we train the same Gemma-shaped body from scratch on the same 2.05B tokens with and without it. The learned table buys 0.20 nats of validation loss for 2.6 times the trainable parameters, but on LAMBADA, HellaSwag and PIQA…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22439v1 Announce Type: new Abstract: Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned information. This raises the question of which representational changes should be constrained while preserving plasticity. We therefore introduce Sparse Autoencoder Geometric Anchoring (SAGA), which converts a Sparse Autoencoder (SAE) trained at each task boundary into local, low-rank constraints on representation drift. Replay examples specify where the constraints apply, while leading right singular directions of the encoder Jacobian specify which changes are penalized. The resulting geometry is input dependent and can be retained without keeping the SA…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22438v1 Announce Type: new Abstract: Studies of what fine-tuning does to a language model often summarise the weight update $\Delta W$ by its rank. We compare the rank measures used for this against the same measures on a random matrix of the same shape, and against two harder references: the pretrained weights, and matched fine-tunes without alignment content. Measures that count directions put our fine-tuning updates only a little below noise; stable rank, computed from the same singular values, puts them far below. Both are right: an update has a few strong directions on top of a long tail. The pattern holds for thirteen released pairs up to 8B parameters, and it is not a mark of alignment: with training held fixed, instruction data does not stand…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22436v1 Announce Type: new Abstract: The signal generation capabilities of a novel data augmentation framework are examined in aerospace structures. First, the framework learns class-conditional temporal and spectral characteristics of the measured structural responses. It uses conditional generative adversarial network training and Monte Carlo dropout uncertainty quantification as a Bayesian approximation. This step enables stochastic signal synthesis and uncertainty quantification. Second, the generated responses are rigorously compared against experimental measurements across time, frequency, uncertainty, variability, and feature domains to assess physical realism, statistical consistency, and distributional fidelity. Finally, the synthetic data a…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22435v1 Announce Type: new Abstract: Distributed Transformer inference across co-located edge devices is fundamentally communication-bound, as exchanging activations between sequence-parallel partitions dominates inference latency under commodity edge bandwidths. Existing compression schemes reduce this cost but retain a structural bottleneck: the received data must still undergo key/value projection before attention can proceed, serializing computation behind communication. This paper presents Transformer Residual Activation Codebook Encoding (Trace), a framework that addresses these limitations. Trace places a Vector Quantizer (VQ) at the post-attention residual of every Transformer layer and precomputes codebook-indexed key/value representations.…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22381v1 Announce Type: new Abstract: When a fact becomes harder to elicit from a language model, has the model lost it, or has it merely become less accessible? Parameter-updating test-time continual learning agents are usually evaluated by current output accuracy; we ask whether that measurement captures how prior experience shapes later updates. We test whether learning a specific factual binding produces a later relearning advantage beyond familiarity with its entity, answer vocabulary, format, or query slot. In Qwen2.5-1.5B, we compare three matched, counterbalanced histories: LEARNED receives the correct binding, CONTROL receives matched exposure without it, and WRONG receives a competing relation-valid answer in the same slot. After an identica…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22380v1 Announce Type: new Abstract: Continuous diffusion treats the forward process as a design space; discrete language diffusion often uses absorbing corruption, leaving context fully trusted throughout generation. This makes trust binary: corrupted context is copied as ground truth, propagating errors into generated spans. We reopen this design space by combining absorbing and uniform-mixing kernels with region-dependent rates. Missing positions follow absorbing dynamics, while context undergoes low-rate random substitution, exposing the model to observed but uncertain tokens during training. At inference, a heuristic sampler re-injects noise into suspicious context under an annealed intensity and freezes context updates late in the trajectory. A…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22379v1 Announce Type: new Abstract: Calibrating expensive engineering simulators requires tuning model parameters to match reference data, a process heavily constrained by computational costs. This study investigates whether Large Language Models (LLMs), conditioned on physical diagnostic descriptions of simulation errors, can propose informative parameter updates more efficiently than conventional derivative-free optimizers. We test this on a cylinder-wake Large-Eddy Simulation and a damped-oscillator inverse problem. Physics-labeled prompts are evaluated against four text ablations (removed, anonymized, padded, misdirected) and standard optimizers (Nelder-Mead, Bayesian optimization, CMA-ES, and random search). Results demonstrate a strong early 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:2610.22441v1 Announce Type: new Abstract: Large language models (LLMs) provide a convenient interface for translating natural language commands into task plans for cyber-physical systems (CPSs). However, two gaps hinder their use for real execution: generated plans may misinterpret or omit the user's intent, and even a logically plausible plan may be infeasible under component dynamics, interactions, or safety constraints. Existing LLM-based planning approaches often lack informative feedback on why a generated plan fails, providing little guidance for revising the plan accordingly. To address these challenges, we present a hierarchical feedback framework that uses different types of feedback information to guide LLMs in generating executable plans for CP…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22426v1 Announce Type: new Abstract: LLM agents are used to check records against an organization's requirements, for example whether a vulnerability report is ready for investigation. Requirements often allow several ways to be met, such as a severity rating with a curator-reviewed advisory or a published advisory link. Agents fail by accepting a report after a required check has failed, or by settling for a weaker conclusion without trying another way that could still succeed. We introduce PRIME (Precommitted Rules for Inference from Minimal Evidence). Before checking, it fixes evidence routes specifying how each conclusion may be justified. A separate program records each check result and refuses any conclusion the results do not justify. It also…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22400v1 Announce Type: new Abstract: Existing large language model (LLM)-based user encoders serialize heterogeneous behavioral logs and compress them into static representations through autoregressive (AR) prediction. However, their unidirectional constraint limits bidirectional information flow, hindering cross-modal interactions and the joint preservation of multi-source signals. Consequently, the learned static representations struggle to accommodate the distinct evidence requirements of diverse downstream scenarios. We address these limitations by unlocking the iterative denoising process of diffusion language models (dLLMs) as a multi-granularity reconstruction space. Based on this insight, we propose FINDERS (FactorIzatioN of Diffusion statEs…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22373v1 Announce Type: new Abstract: LLM-based agents are increasingly used as autonomous orchestrators in distributed and multi-agent systems, yet a control gap remains: no protocol-level mechanism allows human operators to inject binding directives that persist across planning cycles. Free-text overrides suffer from ambiguous interpretation due to lack of schema validation and from authority erosion as operator instructions lose influence within accumulating context. We propose Structured Authority Injection (SAI), a protocol that addresses these issues by routing operator corrections through typed, schema-validated Model Context Protocol (MCP) tool calls and maintaining a ranked authority context prepended to each LLM prompt. SAI defines three ove…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Mistral released Timestral, a time series foundation model family from 5M to 209M parameters. The 209M model leads GIFT-Eval, TIME and fev-bench among zero-shot models and runs on CPU. The post Mistral AI Releases Timestral: A 209M Forecasting Model Family That Outperforms Google’s TimesFM-3 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：Clef, a 27B multimodal decision model from Cloudflare, is now available on Ollama. Run it locally or on Ollama's cloud.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Post-train open LLMs like Qwen, GLM and Kimi into custom models you own, with SFT or RL. You write the training loop. Together runs the hard infrastructure.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： Release: llm-tools-datasette 0.1.1 When I switched LLM over to httpx2 in LLM 0.33 I forget that this would break any plugins which used httpx without directly depending on it. llm-tools-datasette was one of those plugins, now fixed. Tags: datasette, llm

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯： Release: llm-echo 0.5 I'm working towards a new LLM release, and testing PRs caused me to revisit the llm-echo debug plugin. This plugin provides a "model" which doesn't involve an LLM at all - it just repeats back the prompts that have been fed to it. The new release now updates the simulated token usage counts to take tool calls, system prompts, and reasoning tokens into account. Example usage: uvx --with llm-echo llm -m echo 'hi there' -o thinking 1 --usage Outputs: First I consider the prompt, then I decide what to say. { "prompt": "hi there", "system": "", "attachments": [], "stream": true, "previous": [] } Token usage: 2 input, 24 output Tags: llm

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Monitoring tools common in a range of workplaces, including factories, office jobs, delivery work and in retail – often without employees being informed Get our breaking news email, free app or daily news podcast Employers are increasingly using technology, from CCTV to keystroke monitoring, to track workers’ moves and it is being accelerated by the use of AI, the Human Technology Institute has warned. Examples provided to Guardian Australia by the institute include a fast-food restaurant using surveillance cameras to stop workers using their phones, and AI tracking leading to a cashier warned over making a mistake once every 533 scans. 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：In this article, you will learn what Python descriptors are and how to use them to build three types of controlled attributes: validated, computed, and...

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Exclusive: Using test accounts acting as 13-year-olds, Tech Transparency Project downloaded 135 apps with features to generate nonconsensual nude imagery In December 2025, Morgan Dorfman received distressing news: a student at her daughter’s Pennsylvania high school was making AI-generated pornographic material using the daughter’s image. He was using an artificial intelligence image-editing app called Movely to create sexual videos from pictures of her daughter and five other girls. 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：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：Learn how OpenAI is improving ChatGPT across low-resource programming languages, with new evaluations for software engineering, SQLite, and COBOL migration.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Manufacturing leaders often know where losses occur but lack the visibility to intervene before scrap, downtime, or performance losses accumulate. A National Institute of Standards and Technology (NIST) paper identifies delays between machining and quality assessment as a barrier to feeding results back into production. A 2020 NIST report estimated $119.1 billion in annual U.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:2610.22549v1 Announce Type: new Abstract: Accurate counts of fish populations are essential for monitoring ecosystems and making decisions for conservation, harvest limits, and river management. In many field deployments, these counts are obtained from sonar videos that experts must inspect manually, making large-scale monitoring slow, expensive, and difficult. Automated counting systems have been proposed as a scalable alternative, but so far this promise has been difficult to realize in deployment. Developing evaluations that better reflect real-world deployment conditions will help close this gap and drive improvements in counting performance in practice. To achieve this, we propose Caltech Fish Counting 2026 (CFC26), a new dataset with improved evalua…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22509v1 Announce Type: new Abstract: Reliable 3D person detection is important for rescue robotics to give first responders situational awareness. Yet most multimodal 3D detection research targets automotive scenarios in which pedestrians mostly appear in a narrow range of upright, near-road poses. It is therefore unclear how much of the reported performance transfers to rescue settings, as a person may be lying, partially occluded, or in unstructured indoor and outdoor environments. To investigate this gap, we introduce TriSAR-3D, a multimodal person detection dataset recorded with a high-resolution 128-channel LiDAR, an RGB camera, and a thermal camera. It captures varied poses in indoor as well as outdoor locations at different times of day to stu…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22526v1 Announce Type: new Abstract: Decision models, non-generative scorers that report a probability over caller-supplied options and emit no text, are increasingly deployed as routers, classifiers and guardrails. Because they generate nothing, rationales and chain-of-thought do not apply. We audit three: an encoder scorer, a decoder scorer and a closed API, entirely through interventions on their input, using expert-annotated Bengali idioms carrying a gold figurative and a gold literal gloss. Dropping an idiom's own literal gloss into the option list draws every arm toward it, taking 65% to 96% of each arm's remaining Bengali errors. A model-by-language matrix over one shared item set shows how far this depends on the test language: every arm is 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:2610.22437v1 Announce Type: new Abstract: Automated fundus-based diabetic retinopathy (DR) grading can substantially expand screening capacity, but source-trained models degrade sharply across different cameras, clinics, and patient populations. Existing test-time adaptation methods depend on entropy minimization or target information accumulated from image batches and streams. These mechanisms can reinforce confidently incorrect predictions and break down when clinical images arrive independently. We introduce CF-NODE, a novel counterfactual test-time adaptation framework for cross- domain DR grading. Instead of trusting prediction confidence or estimating a target distribution, CF-NODE asks how each prediction responds under a controlled intervention on…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22433v1 Announce Type: new Abstract: Flexible job-shop scheduling becomes resource-coupled when a scarce vehicle fleet moves jobs between stations, because the schedule sets the transport waits. BOLT (bound-oriented learning for transport-coupled scheduling) builds a lower bound from chain, machine-capacity, and fleet-capacity relaxations. The bound equals the makespan at termination, so its per-step changes form a reward that sums to a constant minus the makespan. Because it never exceeds the attainable makespan, each candidate's bound increase is a proven rise of the makespan floor, which the policy reads as a price. The root bound certifies a completed schedule's suboptimality gap without a solver. On industry-motivated 10-module prefabricated-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:2610.22430v1 Announce Type: new Abstract: Accurate prediction of multivariate time series requires models that simultaneously capture variable-specific dynamics and cross-variable interactions. In this work, a Correlation-Guided and Dynamics-Trained Clustered Echo State Network (CGDT-CESN) is proposed, which comprises a modular reservoir architecture with each cluster distinctly specializing in one of the variables in the multivariate time series. An innovative reservoir design is proposed in which inter-cluster connections are enabled by empirically observed correlations among variables, providing a data-driven coupling mechanism. Apart from conventional readout training, inter-cluster connection weights informed by correlations are trained, which in tur…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22445v1 Announce Type: new Abstract: Automated discovery systems propose scientific explanations and test which to accept. Does passing a test establish the intended claim? We develop four executable operations for changing physical descriptions: identifying redundancies (L1), coarse-graining dynamics (L2), transferring structure (L3), and inferring missing quantities from conservation imbalances (L4). We evaluate these operations and three interpretability settings through null acceptance (NAR), positive acceptance (PAR), and consequence agreement (CAR). A reduction mapping every state to zero predicts its own future perfectly. It passes closure on 96% of 129 public chaotic systems despite retaining no dynamical variation. An independent observable-…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2610.22403v1 Announce Type: new Abstract: What a reasoning system emits is a conclusion; what it owes is a justification. Producing one requires every operation to be admissible on the facts actually available, the dependencies of intermediate results to survive to the end of the path, and the path to be revised when a premise changes. We present the Event Reasoning System (ERS), in which the reasoning state is an explicit event graph. Semantic features nominate candidate objects and rule bindings, and declared rule and task conditions decide which may execute, so candidates that violate the represented period, unit, or evidence constraints cannot enter an accepted reasoning path. Low-level rules provide reusable local transformations, and recursively com…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Investing in the public benefit Oct 18, 2026 Today, we’re committing a portion of Anthropic’s shares to the Anthropic Public Benefit Fund, a new entity with a structure that increases the stake as the company grows. Sub…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The $48bn giveaway by company, which is preparing to list on stock market, comes amid concerns about the tech Anthropic has said it will commit 5% of its shares to a fund for the “public good”, as the AI developer behind the Claude chatbot seeks to bolster its appeal before its stock market listing. The company announced that it would commit the shares, worth around $48bn (£36bn) at its latest valuation in May, subject to shareholder approval. It will add a further 2% of its stock to the fund for every 50% increase in its value above an undisclosed baseline. 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：arXiv:2610.22446v1 Announce Type: new Abstract: Neural operators approximate solution operators of partial differential equations at a fraction of the cost of numerical solvers. Efficient grid-based architectures such as the Fourier neural operator (FNO) assume uniform rectangular grids, whereas engineering simulations use large, irregular, and locally refined meshes. We introduce L-SplineFNO, a memory-efficient neural operator that couples an FNO backbone with a sparse, learnable tensor-product B-spline transfer between unstructured meshes and a latent Cartesian grid. A local normalised scatter avoids the geometry-dependent solve of analytic spline transformation while preserving compact support, partition of unity, and spline smoothness by construction. The n…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：NVIDIA has released the full Run:ai GPU orchestration platform as open source under Apache 2.0. The release includes KAI Scheduler, CUDA 13.4 GPU fractioning, quota management, and a local Kind dev environment. The post NVIDIA Open Sources Run:ai Under Apache 2.0 for Kubernetes GPU Orchestration appeared first on MarkTechPost.