AI 日报

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The Adjudicated Query pattern pairs the Amazon Quick chat agent with a bounded MCP server over a deterministic rules engine to deliver provably complete, defensible compliance answers. This post walks through the reference architecture and a deployable AWS CDK sample, using lease compliance as the running example.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Claude Desktop on Amazon Bedrock is limited to the model's knowledge cutoff without web search. In this post, we walk through connecting Claude Desktop to Web Search using Amazon Bedrock AgentCore Gateway, with JWT-based inbound authentication through AWS IAM Identity Center and Amazon Cognito.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Home affairs department orders all federal government agencies to conduct review of ‘legacy technology’ amid fallout from AI agent hacks Get our breaking news email, free app or daily news podcast The Australian government faces significant “tech debt” that could bring a big bill for taxpayers after the OpenAI Medicare breach, as government agencies will need to fortify their defences against future attacks by AI agents. This week, the home affairs department ordered all federal government agencies to conduct a “legacy technology stocktake” that requires a plan for each agency to “reduce legacy technology systems” to a level within the agency’s risk tolerance and appetite, the direction stated. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Here are Google’s latest AI updates from September 2026

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn three ways to get noticed and grow your career as AI reshapes how developers build software. The post AI is rewriting the developer career ladder. Here’s how to stand out. appeared first on The GitHub Blog.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Developers have long been able to customize Claude Code to their preferences, via settings, persistent instructions in CLAUDE.md, hooks, and The post “No reason why everyone should have an identical Claude experience”: Anthropic’s mods let you change Claude Code’s look and behavior appeared first on The New Stack.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Local AI is becoming more useful by the token. As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more to run locally. Coming this month, NVIDIA DGX Spark will be available with 64GB of unified memory from top manufacturer partners — Acer, […]

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Some of the world's leading organizations are building the future of non-profit work with Cloudflare.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Madison, a server in New York City, greets every table by asking about each diner's allergies. Lately, there have been some close calls. "Sometimes people will tell me they have a shellfish allergy, and I'll come back, and they won't ask me any questions," says Madison, who asked that her last name be withheld to protect her identity. "And they'll order a fish dish that comes with a broth that is made of shellfish." When she tells them a dish contains an allergen, she's had guests push back, saying ChatGPT disagrees. "They just want to talk to ChatGPT," Madison explains. "You're allergic to shellfish, and ChatGPT says there's no shellfish … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The following article originally appeared on Duncan Davidson’s blog and is being republished here with the author’s permission. Decision records give coding agents durable project context—as long as they don’t turn every decision into a courtroom transcript. Architectural Decision Records (ADRs) help human teams establish rules and carry context forward in software projects. They capture […]

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The opportunity: Personalization as a revenue engineEvery second a shopper spends...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Israel’s conduct in Gaza shows the danger of using AI in warfare. Humans must remain at the center of wartime decisions As tech leaders warn about the threats of artificial intelligence, most conjure up images of AI agents running amok, such as hacking systems used to run our critical infrastructure, banks or even militaries. Yet one serious danger is mentioned less frequently – the threat posed by AI – empowered lethal weapons. Fully autonomous versions of these weapons are colloquially known as killer robots. Israel’s conduct in Gaza shows that, in an important respect, such AI weapon systems are already here. An algorithm has been deciding who lives and who dies. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：the minimalist harness goes stable... and TypeScript!

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

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38193v1 Announce Type: new Abstract: Patient world models and clinical agents aim to predict changes in patients' health and support clinical work. Developing these systems requires reliable histories of patient conditions, treatments, and the information available at each decision. Electronic health records (EHRs) contain these histories, but differences in how events are recorded make them difficult to use consistently. We present EHR2Trace, a system that converts EHRs from different sources into traceable patient events for model training and evaluation. It links events to source records, separates event time from information availability, and distinguishes medication orders, dispensing, and administration. A shared event representation supports b…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00084v1 Announce Type: new Abstract: Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific Agents, an open-source corpus of 503 profession-specific AGENTS.md profiles, with Gemini 3.8 Flash via OpenRouter in the Pi agent harness. We compare matched profiles with four controls: a minimal baseline ("You are a helpful assistant"), the profile's opening role sentence, a generic scientific rigor guide, and a profile from an unrelated domain. Across nine text-based science benchmarks (4,531 sampled questions, 100 matched profiles), 4,488 items completed all five conditions after API-error retries, scored with automated, rule-based grading. The average profile-b…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands, writing memory, selecting tools, ranking past turns. We ask whether off-the-shelf SLMs meet practitioner-defined thresholds and, when they fail, why, and whether quantization changes the answer. We build a benchmark of 4 such microtasks with fixed prompts and automatic metrics, each with a pre-specified threshold $\tau$ anchored to a cheap non-LLM baseline and a CI-aware eligibility rule (a configuration passes only if its confidence bound clears $\tau$). Sweeping Qwen3 0.6/1.7/4/8B at their best (FP16, greedy, one frozen prompt, no tuning), we…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00015v1 Announce Type: new Abstract: Large-language-model agents can propose and execute actions, but proposal, authority, dispatch, verified external effect, and serving promotion are different claims. We present Praxa, an agent harness that represents these states explicitly through deterministic admission, brokered execution, external read-back, reconciliation, and reviewed promotion. We report four evidence lanes. First, an author-run repository-local audit at a pinned revision passed 1,027/1,027 unit tests and 89/89 Workerd tests, instrumented all 363 expected source files, and met four coverage floors; raw per-test transcripts and independent reproduction are unavailable. Second, in a provider-backed Terminal-Bench Core 0.1.1 pilot across 12 cu…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00010v1 Announce Type: new Abstract: Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task success or token cost. We argue that the missing object is the shape of memory use: under finite context and repeated retrieval, agent memory can concentrate on a small core while leaving rare states in a long tail where prediction errors accumulate. We study this effect through a conservative tail audit and find that concentration is reproducible but policy-dependent. Random-walk agents produce log-normal-compatible retrieval artifacts, whereas semantic LLM policies yield the strongest truncated-power-law-compatible core--tail traces. Motivated by this audit, we pro…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The AI chipmaker’s new safety platform adds controls around AI agents, while enterprises remain responsible for defining their authority and setting boundaries.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：If a chatbot prompt like ‘find Australian medicine statistics’ results in a website breach, the responsibility does not lie with a piece of code The recent panic about a breach of Medicare computer security by an “AI agent” contrasts sharply with other recent cases such as the Telstra and Optus outages that left many Australians unable to reach Triple Zero. In those cases, no one blamed the computers involved. The mistakes were clearly sheeted home to the corporations that operated them. This wasn’t always the case. When the term “artificial intelligence” was coined some 70 years ago, the first mainframe computers (absurdly primitive by modern standards) were viewed with the same awe and concern as the AI agents of the present day. There were even “algorithms”…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：We catch up with RLM first author Alex Zhang, MIT PhD, on Jev, PhD masxing, and the future of harnesses.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The move comes as agentic AI plays an increasingly big part in business operations, sparking oversight concerns.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：A finance team’s job is not simply to report the numbers: it’s to interpret what...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：OpenAI’s new Dots can work around the clock without drawing down a user’s normal usage allowance during the launch period, The post OpenAI’s always-on agents are free, until one specific thing happens appeared first on The New Stack.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Observability has long been a staple of enterprise operations, giving companies a way to understand what their applications and infrastructure The post “No human wants to look at billions of traces”: Dynatrace bought Arize because agents need a new kind of observability appeared first on The New Stack.

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

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：State attorney general issues subpoena to OpenAI as ​part of broader inquiry into potential security vulnerabilities California’s attorney general has issued an investigative subpoena to OpenAI, starting an investigation into the startup ⁠as ​part of a broader inquiry into potential cybersecurity vulnerabilities and incidents related ⁠to its AI models, his office said on Thursday. Last month, Rob Bonta announced that ⁠the Department of Justice was conducting a formal ​investigation into the “Hugging ‌Face incident”, amid increasing ‌scrutiny of the AI industry. AI agents developed by OpenAI hacked Hugging Face in July, gaining access to parts of the open-source platform’s infrastructure. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：In managed OLTP, restores have always been painfully slow and they get slower at...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn how to use Amazon S3 Vectors as the persistent memory layer within the NVIDIA NeMo Agent Toolkit (NAT), deployed on Amazon Elastic Kubernetes Service (Amazon EKS). This post shows how NAT's memory subsystem works and how to implement Amazon S3 Vectors as a custom memory provider, using a multi-agent investment research use case.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：How we built a model router into Open SWE's harness that cut median cost per coding task by 64% with no measurable drop in quality, and how to build your own.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Ambient agents respond to events such as an Amazon S3 upload, a schedule, or an alert instead of waiting for a chat prompt. This post walks through building framework-agnostic ambient agents on Amazon Bedrock AgentCore using Amazon SQS, AWS Lambda, and Amazon DynamoDB, with a single ask_human tool and a Jobs page for human-in-the-loop review.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：The unstated disagreement that underpins safety debates

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Albertsons Cos. is using ChatGPT Enterprise and the OpenAI API to help teams work faster and make grocery shopping easier for millions of customers.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：AWS on Thursday launched Strands Decider 2B, its take on decision models like Jev, Kev, imajev, Laya, and others. TypeSafe’s Jev kicked off the current The post AWS launches a local answer to TypeSafe’s Jev decision model appeared first on The New Stack.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：3 Higher accuracy across extraction tasks Long lists Records spanning pages Scanned forms Advanced Citations How we built v2.5 Try v2.5 on your documents Today we’re introducing Extract v2.5, a new generation of our sch…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Fine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost. In this post, we fine-tune an LLM-powered search agent with multi-turn reinforcement learning (MTRL) on Amazon SageMaker AI and share the gains we measured in retrieval quality and reliability.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：After leading Meta’s Llama models, Ahmad Al-Dahle is now transforming Airbnb with AI — from how its teams develop products to how it serves guests.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Cloudflare AI Gateway now supports native web search API integration in partnership with Ceramic.ai, Exa, and Linkup. Developers can now inject real-time web context into model inference calls via AI Gateway, REST APIs, or Workers bindings.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Suno is branching out from the world of AI music, launching a new feature that generates spoken voices based on scripts or prompted descriptions. Speech is now available in public beta across Suno's web and mobile platforms, and allows you to simultaneously generate voiceovers and background music to accompany them. "Music will always be at the heart of Suno and what we build. At the same time, our vision has always extended to other forms of human expression," Suno chief product officer, Jack Brody, said in the announcement. "Today, we're expanding what's possible in Suno with Speech: the first audio model that generates voice and music to … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：AWS's Strands Agents team released Strands Decider 2B, an Apache-2.0 decision model built on Qwen3.5-2B-Base. It returns choices, yes/no probabilities and scores with calibrated confidence in one forward pass, never text. It runs at a 115 ms median on an RTX 3090 and scores 0.723 on the JevBench public set, which makes it a fast local option for routing, tool selection and guardrails in AI agents. The post AWS Strands Labs Releases Strands Decider 2B: An Open Source Decision Model That Picks Options in About 115 ms appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00368v1 Announce Type: new Abstract: World-model planners typically scale outward by rolling farther, sampling more trajectories, or optimizing longer, while assigning the same computation to every imagined transition. We show that making every transition uniformly deeper wastes computation and can degrade planning because useful refinement is concentrated at a small set of decision-critical events. We introduce DeepJEPA, a weight-tied joint-embedding predictive world model that treats transition depth as an inner test-time scaling axis and learns when another recurrent update is worth computing for each candidate and rollout step. Across five visual-control settings, DeepJEPA improves or matches the strongest fixed-depth planner while averaging only…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00317v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models increasingly rely on action experts that generate short action chunks under receding-horizon control. While chunk-level training is convenient across robot embodiments, it optimizes local action likelihood without explicitly accounting for long-horizon task success. Sequence-level reinforcement learning can address this limitation, but typically requires policy rollouts and closed-loop interaction, which are costly for real-robot manipulation. We introduce DriftOPD, a teacher-free, rollout-free framework for sequence-level on-policy distillation of continuous VLA action experts. We show that the sequence-level reverse Kullback-Leibler (KL) divergence decomposes into a chunk-leve…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00069v1 Announce Type: new Abstract: Long-horizon ego/exo data contains rich procedural evidence, but are redundant, noisy, and costly to process or retain. We propose a compact framework that converts continuous multimodal workplace video into a structured Procedural State Memory, implemented as a Work Environment Model (WEM). Inspired by event segmentation theory, we detect boundaries using changes in visual context, location, motion, narration, gaze/object interaction, and optional exocentric workspace evidence, rather than fixed windows or visual novelty alone. Each segment is abstracted into an evidence-linked event card containing actor, interval, location, action, objects/tools, pre/post state, confidence, and provenance. These event cards inc…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00040v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting have enabled open-vocabulary and referring segmentation by distilling semantic knowledge from 2D foundation models into 3D representations. However, existing referring fields embed language features in a globally view-invariant space, making them fundamentally unable to resolve observer-centric spatial relations (e.g., "to the left of") that depend on camera pose. We propose DSSR-3D, an inference-time framework for view-dependent referring segmentation on continuous 3D Gaussian fields, formalized as two interfaces - pose-invariant semantic localization and pose-conditioned spatial reasoning - such that any pair of functions satisfying these constraints yields a valid instan…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00024v1 Announce Type: new Abstract: Across three vision-language model architectures (LLaVA-1.5-7B, Qwen2.5-VL-7B, InternVL3-8B), we report a universal negative finding for mid-layer interpretability. On POPE -- the benchmark common to all three -- the mid layers encode the ground-truth answer in 68-91% of errors, yet this signal is not causally active for the final prediction: residual-stream patching yields 0% non-trivial flip at the layer level on all three architectures, and on two of three at the per-head level (Qwen: 0/12,600 patched forwards). The lone exception, InternVL3 layer-20 head-2, is a non-vocab, self-attending head whose effect is localized to that specific head (p < 1e-4). Despite the null, the errors separate operationally into th…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00006v1 Announce Type: new Abstract: Pretrained Vision Transformers encode whether two image patches belong to the same object. This IsSameObject signal is decodable from frozen patch embeddings at high accuracy, which suggests that object binding emerges from self-supervised pretraining alone. We show that this single accuracy number hides the structure of the signal. Binding is local: the probability that two patches of the same object are decoded as bound falls off monotonically with the distance between them and levels off at a nonzero floor, a falloff well described by an exponential with a finite length scale. This decay holds across object sizes, across three families of probe, on both ADE20K and COCO, and across DINO and CLIP backbones, which…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00003v1 Announce Type: new Abstract: Vision models pretrained for frame-level appearance often struggle to infer hidden physical properties from motion. We study center-of-mass (CoM) localization for opaque, asymmetric rigid bodies from short monocular videos, where surface cues and point tracking are unreliable under self-occlusion. We propose STATERA, which adapts a pretrained video backbone (V-JEPA) with mostly frozen weights and a lightweight temporal tubelet mixer to predict per-frame CoM heatmaps and trajectories. To support this task, we introduce the HiddenMass Benchmark, comprising 50K MuJoCo trajectories and a 63-sequence real-world test set with physically calibrated CoM ground truth. In simulation, STATERA-50K-Sigma improves normalized Co…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38342v1 Announce Type: new Abstract: On-policy self-distillation uses a model as its own teacher to provide dense supervision for reasoning, often through reference-solution conditioning. Providing privileged information does not by itself ensure effective token-level supervision throughout long responses. We introduce Activation-Conditioned Self-Distillation (ACSD), which extracts a steering vector by contrasting activations of self-generated trajectories that reach verified correct answers within a generation budget with those of all remaining trajectories. A frozen copy of the base model applies this vector at each prediction position, and the student learns from its next-token distributions on student-generated prefixes. Outcome verification is u…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38198v1 Announce Type: new Abstract: Diffusion maps, and kernel methods more generally, provide an interpretable nonlinear spectral representation basis for geometric learning. In the geometric limit, small bandwidth, these matrices tend to be high rank and thus require materializing dense Gaussian kernels requires $O(N^2)$ memory. We introduce FlashDiffusion, a matrix-free method that evaluates dense Gaussian kernel blocks in fused GPU tiles and couples the eigensolver to an empirical $\beta$-flow that selects the finite-sample resolution scale. A continuation over sample size and bandwidth warm-starts increasingly expensive spectral solves from coarser resolutions.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38197v1 Announce Type: new Abstract: Financial time-series forecasting must capture price dynamics across heterogeneous assets while incorporating news available at prediction time. We introduce DualCast, a dual-path framework that extends a frozen language model with a discrete financial vocabulary. Each log-return patch is represented by a learned summary token and three residual shape tokens, preserving local drift and volatility while allowing shape patterns to be shared across assets. To improve codebook utilization, we develop adaptive frequency-equalizing residual vector quantization, which rebalances overloaded codewords without compromising reconstruction accuracy. The fast path trains only the new financial-token embeddings and output heads…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38196v1 Announce Type: new Abstract: Accurate time series forecasting is critical across various domains, yet traditional ensemble methods often suffer from the disproportionate influence of extreme forecasts. We introduce the Conformal Adversarial Generative Ensemble (CAGE), a novel framework that combines generative modeling, adversarial discrimination, and conformal prediction to enhance forecast reliability and accuracy. CAGE employs multiple generative models to produce initial forecasts, which are then evaluated by a discriminative component using conformal prediction techniques. P-values derived from nonconformity scores help dynamically adjust model weights, minimizing the impact of unreliable forecasts. This approach ensures that only the mo…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00197v1 Announce Type: new Abstract: We investigate automated rewards for training language models in conversational humor, focusing on reward exploits and countermeasures. Two approaches aim to capture understandable surprise and predicted audience amusement. Controlled tests show that an embedding-based surprise reward accepts word-shuffled replies as readily as witty ones. A fluency filter detects the shuffles, but the combined reward also rejects some witty replies and fails further validation. An audience model's predicted laughter is instead vulnerable to laughter cues in either speaker's messages. Normalizing these cues across speakers blocks the covered attacks, although unmatched expressions remain exploitable. Three reinforcement-learning r…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00061v1 Announce Type: new Abstract: Personalizing large language models (LLMs) requires aligning generation behavior with user-specific preferences rather than aggregate quality. While Direct Preference Optimization (DPO) provides a stable framework for preference learning, its effectiveness in personalized settings critically depends on how preference pairs are selected. Existing approaches typically rely on heuristic criteria, such as likelihood-based extremes, which decouple optimization from explicit user utility and can lead to degraded personalization. We formalize personalized preference learning as a geometry-aligned optimization problem by analyzing the first-order interaction between gradients of expected user utility and DPO update direct…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00047v1 Announce Type: new Abstract: Diversity collapse in parallel chain-of-thought has motivated inference-time interventions built on a natural design: when a process reward model (PRM) prunes a chain, its high-PRM prefix is extracted and grafted verbatim as an in-context demonstration into a still-decoding sibling. We isolate this mechanism, PRM-Pruned Fragment Grafting (PPFG), as the most cost-minimal operationalization of cross-trajectory step-level transfer, and test it at the operating point where prior fragment-grafting work reports gains only under additional compensating ingredients. On Qwen2.5-7B-Instruct with Math-Shepherd on full MATH500 (n=500, three seeds), PPFG in both stagnation- and random-targeting variants is statistically indist…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00012v1 Announce Type: new Abstract: LLM agents increasingly act through modular systems, such as order, payment, inventory, and shipment services, where actions in one module change which transitions are valid in another. Standard world models usually fit observational traces, but this is not the quantity needed for intervention-time planning: a trace may show that payment precedes shipment without identifying whether payment authorizes shipment, inventory mediates the effect, or a hidden trigger explains both. We study this gap through FedCausalCompose, a causal world-model framework for modular LLM agents in which local actions provide intervention-response evidence for cross-module interfaces. We first show that observational world models incur a…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Cloudflare has released Clef (27B) and Clef-flash (9B), open-weight decision models that return typed probabilities instead of text. They are Jev-API compatible, accept images, and run on Workers AI at 209.3 ms and 38.8 ms median latency. The post Cloudflare Releases Clef and Clef-flash: Open-Weight Decision Models That Return Typed Probabilities Instead of Text appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：As a top cloud provider, Google has deep experience integrating its infrastructure with the other Google products that enterprises use.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing which positions to write from those same distributions. For domains of general interest (pixels, phonemes, or words) there are inherent dependencies between tokens. We show that a step matches the training distribution only when the positions it writes are conditionally independent given the tokens already fixed, that no product of per-position distributions can match a dependent group, and that…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Chatham Financial uses Codex and GPT-5.6 to build technology and redesign workflows, cutting trade validation from 30 minutes to under 4.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show that strengthening the model’s ability to discriminate languages during pretraining reduces and, on some measures, closes this multilingual gap on continuous phonetic and higher-level linguistic measures, while preserving substantial cross-language sharing. Using a controlled English/French HuBERT setting, we test two interventions which strengthen language discrimination: an auxiliary language…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Cohere has released Embed 5, a new embedding model family. It targets enterprise search, RAG, and agentic retrieval. The model family ships in 2 tiers. Embed 5 Pro targets maximum retrieval quality. Embed 5 Fast targets latency and cost on the live query path. Both accept text, images, and fused text plus image inputs. Both […] The post Cohere Releases Embed 5: How It Compares to Voyage 4 Large, Gemini Embedding 2, and OpenAI appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译： Release: pwasm 0.2a0 pwasm is one of my folly projects - an entirely vibe-coded pure Python WebAssembly engine that I built in January during my first bout of AI mania. I hadn't touched it since January, so I decided to let Claude Opus 5.5 loose on it and see if it could make any significant improvements: Evaluate current state of pwasm - then consider what it would take to get the MicroPython and micro JavaScript experiments from the research repo working under it - and what it would take to speed it up 42 commits later (with minimal follow-up prompting) it now handles almost all of the WASM specification and the wheel from PyPI bundles working WASM builds of MicroPython, QuickJS and Micro QuickJS. I wouldn't trust this thing at all - hence the alpha version…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Tech company releases Gemini 4 Argon only to a vetted group of cybersecurity experts to avoid misuse by hackers Google on Wednesday said it would withhold its most powerful artificial intelligence model from the public for now, releasing Gemini 4 Argon only to a vetted group of cybersecurity experts to avoid misuse by hackers. “Safely releasing frontier capabilities at this level requires a phased approach,” wrote Koray Kavukcuoglu, Google’s chief AI architect, in a blogpost announcing the model. Continue reading...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Content-based row matching, 6 per-value verdicts and a null rule make OmniExtractBench an extraction benchmark anyone can audit. The post Datalab Introduces OmniExtractBench to Fix Bias and Opacity in Extraction Benchmarks appeared first on MarkTechPost.

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

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：San Antonio City Councilmember Ric Galvan remembers when data centers first arrived in his city in the 2000s, looking like relatively unassuming office buildings. But that's changed in recent years, as data centers have grown into massive "hyperscale" facilities spanning millions of square feet and housing the physical infrastructure for AI. There are now more than a dozen data centers in Galvan's roughly 55-square-mile district, and he expects that number to grow to around 20 over the next few years if proposed projects are completed. They're clustered along two main roads, concentrating nuisances in the same neighborhoods: traffic and tr … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00360v1 Announce Type: new Abstract: Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise that serves the first goal can interfere with the second. In trajectory-guided settings such as ViViDex, where RL refine hand-object trajectories from human video, our baseline PPO runs end near their initial action noise after 5M steps, motivating explicit control of exploration scale. DexPolicy makes that scale an explicit function of training steps, annealing from broad to narrow exploration while holding loss, architecture, reward, and optimizer settings fixed. We study three policy-optimization settings: PPO, critic-free GRPO continuation, and a flow-parameterized…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00330v1 Announce Type: new Abstract: Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment. We formulate retrospective open-vocabulary memory as probabilistic inference from censored observations, where the key idea is to reason with evidence per opportunity: a detection or non-detection should influence belief only in proportion to the robot's opportunity to observe the corresponding location. We introduce ECROM, which uses this principle to estimate long-term prevalence for concepts specified only at query time and converts the resulting belief directly into an active-search prior. To evaluate this problem, we introduce a controlled long-term benchmark in ten HM3D home…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00065v1 Announce Type: new Abstract: Legible planning is the creation of plans that best disambiguate their goals from a set of other candidates from an observer's perspective. In this paper we propose a method for legible planning for arbitrary PDDL domains, by extending previous research on legibility to classical planning without requiring to construct ad-hoc planners. We also discuss how the observer perspective may be estimated through a second order theory of mind that connects the planner's and the observer's task spaces. Our solution can for example be deployed in human-robot teaming scenarios, where an autonomous robot in a team can implicitly communicate its goal by producing legible plans. We present benchmark results on several PDDL plann…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00057v1 Announce Type: new Abstract: Guiding a tractor along a predefined reference path is a key component of precision agriculture. This study develops a path tracking controller based on Nonlinear Model Predictive Control, which incorporates multiple segments of a piecewise-linear reference path directly into the objective function. In addition, methods for selecting viable reference segments from the full path are presented. The control system is evaluated during a field test with a tractor controlled via the Tractor Implement Management steering interface. The NMPC solver converged on average after 3.45 ms and tracked the curved reference path with a mean absolute cross-track error of 6.1 cm.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00067v1 Announce Type: new Abstract: Reliable visual inspection is essential for quality assurance in aero-engine blade manufacturing, where defect appearance may vary across production lines, imaging conditions, blade poses, and surface backgrounds. Such domain shifts cause a mismatch between training and deployment data and degrade the reliability of deep defect detectors in online inspection. This problem is particularly challenging because aero-engine blade images usually contain sparse defects, making pseudolabel-based adaptation vulnerable to noisy or missing predictions. To address this issue, we propose Aero-engine Blade Defect Detector (ABDD), an online adaptive detection framework based on test-time adaptation. ABDD introduces a Dual-Alignm…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00064v1 Announce Type: new Abstract: Assembly actions are compositional: they combine a manipulation with a part or tool. In deployment, systems routinely encounter novel combinations of familiar components, yet an atomic action classifier assigns every unseen combination exactly zero probability by construction. The prevailing solution is verb--noun decomposition, which predicts components separately and recombines them to reach unseen actions. While widely adopted, how decomposition generalizes under compositional shift remains poorly understood. We present a systematic analysis of verb--noun decomposition across three assembly datasets (MECCANO, HAViD, and IMPACT). Although decomposition escapes the atomic ceiling, its generalization extends only…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00031v1 Announce Type: new Abstract: Street-view imagery is increasingly used to infer urban attributes, but predictive accuracy alone does not reveal how much a photograph contributes beyond data already available for the same place. We compare image-based predictions with existing urban data across seven attributes from five public resources and three VLMs. The same urban units are evaluated using images, task context, nearby observations, and public records, while image replacements and conflicting records test source reliance. Existing urban data matched or exceeded image-only models for road damage, curb ramps, and house price, while neighbouring official statistics nearly matched the best image result for population. Images were more informativ…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00030v1 Announce Type: new Abstract: Object detection models often experience performance degradation when deployed under distribution shifts, caused by for example changes in weather type, operational environment, or object appearance. Domain Generalization (DG) aims to develop models that remain robust under such shifts and generalize well to unseen domains. DG research specifically focused on object detection models is scarce, although these models face additional challenges around localization and multi-scale representations. Synthetic data is a promising tool to support in DG, by enabling large-scale generation of diverse new samples. In this paper, we present an object detection-centric review of DG and examine the role of synthetic data from t…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00017v1 Announce Type: new Abstract: We present Spatial Lifting (SL), a novel methodology for dense prediction tasks. SL operates by lifting standard inputs, such as 2D images, into a higher-dimensional space and subsequently processing them using networks designed for that higher dimension, such as a 3D U-Net. Counterintuitively, this dimensionality lifting allows us to achieve good performance on benchmark tasks compared to conventional approaches, while reducing inference costs and \textbf{drastically lowering the number of model parameters}. The SL framework produces intrinsically structured outputs along the lifted dimension. This emergent structure facilitates dense supervision during training and enables single-forward-pass self-consistency-ba…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38332v1 Announce Type: new Abstract: Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires deciding how to allocate fresh contexts and what information to carry between them. We call a model's ability to make these decisions contextual reasoning. Existing approaches largely prescribe these decisions through their harness; we instead shift them to the model. We introduce 1) Hermes, a family of simple, configurable harnesses that progressively varies model control over context allocation and reuse, and 2) Hermes-Learn, a two-stage framework for learning these capabilities. We find that capable models can exploit this flexibility to scale wi…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38276v1 Announce Type: new Abstract: Alcohol intoxication is a leading contributor to fatal and severe-injured e-scooterist crashes. Current countermeasures, such as temporal restrictions or pre-ride cognitive screening, cannot continuously assess an e-scooterist's physical motor control or impairment in real time. We conducted a controlled experiment in which 25 participants rode an instrumented e-scooter through a test track while sober and at two targeted blood alcohol concentration levels (0.05% and 0.08%). The e-scooter was instrumented with a six-axis inertial measurement unit (IMU), and throttle and brake lever position sensors, all sampled at 100 Hz. Two complementary signal features were computed: normalised permutation entropy, which quanti…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38195v1 Announce Type: new Abstract: Operators for interfacial problems are trained on reference solutions produced by the solver they are intended to replace. This work develops a data-free physics-informed neural operator for level-set interface advection, in which the interface is the equation's unknown and the operator maps an initial interface to the full spatiotemporal trajectory under a prescribed flow. Training uses only the transport residual and a geometric constraint; no reference solution enters the objective at any point. A spacetime Fourier backbone emits the entire trajectory in one pass, and the initial condition is imposed by construction rather than by penalty, which removes the competition between the anchoring term and the residua…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38194v1 Announce Type: new Abstract: Despite the importance for interpretability, decision trees face severe scalability challenges. Existing global optimal methods are often limited by binary feature selection and shallow tree depths, whereas traditional heuristic approaches frequently sacrifice predictive accuracy. To overcome these limitations, this paper proposes a moving-horizon approximate branch-and-reduce method to train near-optimal deep classification trees on large-scale datasets with continuous features. Built on a hierarchical root-subtree optimization framework, the method solves the root-level problem via branch-and-reduce while approximating the induced subtree problem using greedy heuristics. Although the underlying framework is capa…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2609.38190v1 Announce Type: new Abstract: The purpose of this research is to find data and methods using machine learning and deep learning to correctly predict the estimated travel time for transportation and logistics in a supply chain system. The supply chain ecosystem is very complex and heavily relies on the transportation and logistics of raw materials and finished goods. Accurate travel time estimation is critical because it helps supply chain members to improve logistics consistency and performance. This helps in planning, demand forecasting, lead time management and assembly planning. The logistics on the delivery side of the customer also plays a crucial role in customer satisfaction and voice of customer. With the collection of huge historical…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00074v1 Announce Type: new Abstract: K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer. The researcher supplies access to a model of their choice, hosted or running locally, and the application supplies everything else: a place for the work to run, a layer of scientific scaffolding, and a complete record. Each project is an ordinary folder, so the data, the code, the results, and the record stay on a machine the researcher administers and can be read years later without the application. Three things separate it from a chat assistant or a general-purpose coding agent. It ships a library of written scientific procedures, guided workflow templates, catal…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00018v1 Announce Type: new Abstract: Role-specialized QA pipelines increasingly pass rationales from a reasoner to a verifier, but it is unclear what this message actually buys: better answers, stronger support assessment, or a new failure surface. We introduce a message-intervention diagnostic that fixes the evidence and candidate answer while varying only the rationale passed across the reasoner-to-verifier boundary. On 400 MuSiQue, HotpotQA, and 2WikiMultiHopQA examples with DeepSeek as generator and verifier, faithful rationales add almost no answer accuracy over no rationale, while corrupted rationales strongly alter support judgments. Under a blind verifier prompt, harmless paraphrases shift support by only 0--2.5%, whereas corrupted rationales…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：In this comprehensive coding guide, we explore Google Research's Kauldron—a JAX training library optimized for research velocity and modularity. Learn how konfig turns experiments into plain dictionaries, kontext wires components via string paths, and ktyping enforces runtime shape checks. The post A Coding Guide to Google Research’s Kauldron: Configs That Are Plain Data, Components Wired by String, and a JAX Trainer You Can Read End to End appeared first on MarkTechPost.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：“InstructMesh” can generate designs for everyday objects that are easy to edit and fabricate for both experts and newcomers to 3D modeling.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：With Live Data in Apps in Amazon Quick, AI-built apps query your governed Quick Sight datasets in real time instead of static, build-time snapshots. Each query runs as the person viewing the app, so row-level and column-level security apply per reader. Learn how to build, publish, and share a live-data app using natural language.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Advanced AI may matter most for the routine work behind breakthrough ideas. Explore why execution could shape the next economy and the pace of progress.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Amazon Quick Sight is a fully managed, cloud-native business intelligence (BI) capability for building and publishing interactive dashboards. The new hierarchy filter gives dashboard authors rich, multi-level filtering in a single compact control, reducing clutter and guiding readers to the data they need in fewer steps.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Reinforcement learning: Why alignment of numerics and MoE routing matter Join us for our inaugural conference, Forge 2026 Blog Reinforcement Learning Why Alignment Of Numerics And Moe Routing Matter Reinforcement learni…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：AI is doing more junior-level work, forcing organizations to rethink how employees gain the experience and judgment they need to move into senior roles.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Australians are conversing less every year, with a recent study showing we lost an average of 338 spoken words each day between 2005 and 2019 We talk a lot about losing our ability to write as a result of AI. I’m convinced our greatest loss might be our ability to listen. Listening to different views and entering into different worlds is integral to our humanity. But Australians are conversing less every year. While rapidly evolving AI tools and chatbots promise faster responses and so-called “empathetic” listening, a recent study showed we lost an average of 338 spoken words each day between 2005 and 2019. That adds up to a staggering loss of 120,000 spoken words per person, compared with the year before. Continue reading...

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

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

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

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

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Guided Vision is launching in Gemini Live on compatible Android devices today to use AI to give real-time audio descriptions of anything you point your phone's camera at. By sharing your camera in Gemini Live, you can have Google's AI help with things like reading small text, describing your surroundings, finding or identifying objects around you, and describing details on specific objects. Like the VoiceOver Live Recognition feature Apple has added to the iPhone and Vision Pro, it's designed for people who are blind, have low vision, or want assistance in specific situations. In addition to the Gemini app, Guided Vision is also available … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：A federal judge has dismissed a pair of antitrust lawsuits filed by Chegg and Rolling Stone parent company Penske Media Corporation, which accused Google of driving away web traffic with its AI-powered search features, as reported earlier by Reuters. US District Judge Amit Mehta takes Google's side in a ruling on Wednesday, writing that PMC and Chegg's claims don't stand up to antitrust law. In lawsuits filed last year, Chegg and PMC accused Google of abusing its monopoly power by coercing publishers into supplying content for AI Overviews for free, or risk disappearing from search results. The publishers alleged Google's practices diverted … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Learn how to configure secure, multi-environment access to Claude Platform on AWS from a single subscription: cross-account SigV4 for AWS workloads, workspace-scoped API keys for developers, and OIDC federation for external environments, with workspace-level isolation in a dedicated AI Services account.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：‘AI factories’ developer on track to launch the second-biggest IPO in Australian history, but investors warn its forecasts are ‘a little bit of a fairytale’ Get our breaking news email, free app or daily news podcast From her balcony in Launceston, Kayla Thompson can see the buzz of construction at what will soon be one of Australia’s first AI factories. Her teenage stepchildren get an even clearer view from their classroom window. Like many of her neighbours, Thompson didn’t realise Firmus Technologies had an ambitious plan to build datacentres in Tasmania until after construction began. The Australian company was on a mission, and preparing to list on the ASX later this month after an anticipated initial public offering designed to raise $7bn from investors.…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Amazon is calling for people to support AI data center projects, or risk irreparable harm to the US economy and national security. In a more than 3,000 word blog posted today, Amazon web services CEO Matt Garman pushed back on public concerns around the impact that data centers may have on jobs, power demands, and the environment, saying "our nation can't afford to lose" the race for AI dominance. "With any change, there will be important questions raised, but there will also be misinformation and outright lies, and in the age of social media and 24/7 news, myths take hold faster than ever before," said Garman. "In fact, this build out is s … Read the full story at The Verge.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Martin Trust Center Managing Director Bill Aulet introduces Dear Dreamer, a free platform for middle and high school students who want to learn about entrepreneurship.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Generative AI makes it cheap to produce personalized content at scale, but which variation do you show each customer? Amazon Payments used a multi-objective contextual bandit on Amazon SageMaker AI to personalize an acquisition funnel, achieving a high single-digit conversion lift for one audience, and learning why content, not the model, was the constraint.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00355v1 Announce Type: new Abstract: Efficient indoor LiDAR perception is challenging because mobile robots must understand cluttered three-dimensional environments under strict latency and memory constraints. Existing point-based and voxel-based methods often incur substantial computational overhead, whereas conventional bird's-eye-view (BEV) representations improve efficiency at the cost of discarding vertical geometric information. We present IndoorBEV, a lightweight LiDAR perception framework that mitigates this tradeoff through a height-aware BEV representation and geometry-conditioned feature fusion. IndoorBEV summarizes the vertical point distribution in each BEV cell using statistical height features and multi-frequency height encoding, allow…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00220v1 Announce Type: new Abstract: Real-time motion generation for tendon-driven continuum robots requires accurate modeling of nonuniform bending and whole-body collision avoidance. This paper presents a unified actuation-space framework for planar multi-segment tendon-driven continuum robots. An energy-based variable-curvature model captures spatially varying tendon spacing and bending stiffness and provides analytical Jacobians for differential inverse kinematics and safety monitoring. A multipoint CBF-QP enforces backbone clearance under obstacle motion and actuation-velocity bounds, while its decision dimension depends only on the number of independently actuated segments. The model closely agrees with GVS references, with a maximum curvature…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00198v1 Announce Type: new Abstract: Recent advances in motion generation and whole-body tracking have enabled humanoid robots to execute increasingly diverse motions, yet the same motion capabilities may be requested repeatedly during continual deployment. Reliable reuse is challenging because intervening motions can change the robot's entry state, making previously successful motions unsafe to replay blindly. Meanwhile, validated capabilities accumulate during deployment, while bounded storage requires deciding which ones are worth retaining. To address these challenges, we present HumanoidTTT, a framework for test-time capability reuse in continual humanoid control. Specifically, we introduce Selective Full-Motion Reuse, which authorizes direct re…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：Millions of robotic machines are already operating in factories worldwide, but oversight and safety standards risk falling behind.

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：arXiv:2610.00008v1 Announce Type: new Abstract: Sim-to-real research pursues physics fidelity as a primary objective: simulators are judged by how closely they reproduce real-world contact dynamics. For governance benchmarking of LLM-driven robots, where the simulator demonstrates that an admission/policy/contract/audit pipeline behaves correctly, contact fidelity at object handoffs (grasp, carry, place) becomes a liability: contact-force integration noise injects audit-chain divergence that is structurally unrelated to the governance property under test. We propose bounded-fidelity sim-as-demo-stage, a design pattern that suppresses contact physics within explicitly bracketed handoff envelopes while preserving full dynamics elsewhere. The construction uses MuJ…

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：In our previous posts, we showed how open table formats, open APIs and unified governance...

AI 服务暂时不可用，以下为来源摘要，待恢复后补全翻译：GPT-6 Astra Ultrafast, running on NVIDIA Blackwell GPUs, is available now in the OpenAI API and to eligible ChatGPT Work and Codex users. Accelerated by inference optimizations through OpenAI’s models that tap into the capabilities of the NVIDIA Blackwell architecture, Ultrafast offers up to 8x faster token generation than the Astra Standard mode. For developers, […]