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：The zero-day exploit required local access to the user’s device, but gave potential attackers access to Muse accounts. | Image: The Verge Meta has issued a patch for its Muse macOS app following the discovery of a zero-day vulnerability that could allow someone to take control of the AI agent. The bug found by security researcher Patrick Wardle utilized an undocumented Muse setting that enabled potential attackers running local code to redirect transcription processing from Meta's servers to their own endpoint, Ars Technica reports, giving the attacker access to the Muse account. Several design decisions reportedly enabled this flaw, including having Muse dictation occur in the cloud instead of on-device, and allowing any app to control all of Muse's undocument…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Former chancellor, now senior figure at OpenAI, says UK needs datacentres to maintain ‘sovereignty’ over AI tech UK politics live – latest updates Datacentre nimbys are holding Britain back, George Osborne has said in reaction to nationwide protests about the giant water-and-energy guzzling structures. The Tory former chancellor is now the head of AI for countries at OpenAI, an artificial intelligence company and the developer of ChatGPT. His job is to represent the company to governments around the world, and he also has a role in enabling the building of datacentres and other infrastructure. 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：The early rapid expansion of AI capabilities that focused on frontier models was largely ushered into the world by a few powerful, US-based AI labs. Open-weight models released from labs in China, early on from DeepSeek, and later from Moonshot, Z.ai, and others, have in part disrupted that dominance. But growing concerns about the concentration […]

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Inside the RSI post-training pipeline

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Burnham is heading to New York for the United Nations general assembly Kanishka Narayan, the minister for AI, is on the trip to New York with the PM. In a video that he recorded on the plane, he says the fact that he is going shows that AI is now “top of the international agenda”. He says his message to the industry has been “take risks seriously”. According to the overnight briefing from No 10 ahead of his speech to the UN, Andy Burnham will make AI (artificial intelligence) one of the main themes of his visit to New York. Downing Street says: Major global challenges such as AI, the conflict in Ukraine and security in the Middle East are expected to dominate the agenda of the prime minister’s meetings in New York over the next 24 hours, as world leaders conver…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：It’s becoming obvious to many Americans that corporations have been raking it in while workers take it on the chin Last week, the unlikely duo of Bernie Sanders and Steve Bannon both spoke before a Washington group demanding a stop to AI and its datacenters. Notably, both lambasted the corporate oligarchs behind AI. 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：RBA governor says AI is ‘great white hope’ but its adoption is so far adding to inflation, rather than economic growth The Reserve Bank governor said AI could be a bubble and there was no evidence it is making the economy more efficient, as the Albanese government claims the technology will solve Australia’s economic malaise. Ahead of an expected interest rate rise next week, Michele Bullock also said the slump in house prices was deeper than others in Australia’s recent history. 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：crowning a new Chinese frontier lab

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：NVIDIA researchers have released SoL-Pi, 4 harness mechanisms for the open-source Pi coding agent, discovered by an AI running auto-research loops across 535 environments. On EdgeBench, SoL-Pi cuts token traffic by 44.7% to 49.0% and API cost by roughly 33%, while keeping about 94% of Pi's score on GPT-5.6 Sol and Opus 5. The post NVIDIA Introduces SoL-Pi: Auto-Research Loops That Cut Coding Agent Token Traffic by Up to 49% 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：Canadian province alleges deadly attack could have been prevented if company had warned police of shooter’s ChatGPT use British Columbia has sued OpenAI in California, saying a mass shooting at a school in the province could have been prevented if the company had warned local ⁠law enforcement that the shooter ⁠had used ChatGPT to ​plan the massacre. The lawsuit filed in San Francisco federal court on Monday names OpenAI and its CEO, Sam Altman, as defendants. It is seeking damages to fund recovery efforts in the province after the February attack, as well as an order directing changes to the way the company handles ChatGPT conversations that could lead to violence. 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：SpaceXAI has released Grok 4.7, its new flagship model for coding, agentic tasks, and knowledge work. Grok 4.7 is built on a larger base model and a longer reinforcement learning run. It still ships at the same price and speed as Grok 4.6. Is it deployable? Yes, as a hosted model. You can call grok-4.7 […] The post SpaceXAI Releases Grok 4.7: A Larger Base Model at the Same $2/$6 Price as Grok 4.6 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：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:2609.22332v1 Announce Type: new Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act. Action-labeled robot videos directly supervise control but are costly and limited in diversity, whereas egocentric human videos capture diverse interactions but lack robot actions and differ in embodiment and appearance. We introduce AffordanceWAM, an affordance-aware generative World Action Model that represents object-centric spatiotemporal affordance through Scalar Affordance and Affordance Heatmap, within the generated future World. This representation grounds visual prediction in task-relevant objects and interaction regions for action generation, and provides…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22325v1 Announce Type: new Abstract: Large language models have shown considerable potential for natural-language-driven parametric CAD modeling. However, a fundamental contradiction exists between their probabilistic generation and the deterministic requirements of CAD modeling, resulting in limitations in reliability, design-intent preservation, and geometric validity. Existing methods typically rely on large-scale annotated datasets, lack explicit modeling of design intent, and underutilize the deterministic capabilities of CAD kernels. To address these limitations, we propose ReliCAD, a unified framework that transforms uncertain LLM generation into reliable parametric CAD modeling. Through explicit design-intent modeling, ReliCAD converts user r…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22319v1 Announce Type: new Abstract: The rapid progress of artificial intelligence is reshaping robotics and accelerating the adoption of learning-based approaches. While purely data-driven methods have achieved remarkable success in computer vision and natural language processing, robotics remains constrained by limited data, complex real-world interactions, and the need for reliable operation. These challenges have motivated the exploration of physics-embedded robot learning, which embeds physics priors into learning algorithms. By encoding the underlying physical laws and constraints, physics priors can complement limited data with robotics-specific inductive biases, potentially improving generalization, interpretability, and sample efficiency. Ho…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22317v1 Announce Type: new Abstract: World models support autonomous driving by predicting the scene evolution associated with candidate trajectories. Driving dynamics differ in predictability, motivating a distinction between regular evolution and event-induced deviations that call for selective correction. We propose EditWM, a world model that decomposes future prediction into normal evolution and event-driven incremental correction in compact visual feature space. A trajectory-conditioned normal predictor provides the base forecast and is then frozen for correction learning. A correction decoder compares this forecast with observation history and planned actions, producing a bounded feature update whose contribution is regulated by a learned gate.…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22299v1 Announce Type: new Abstract: When a robot faces unfamiliar physical conditions, a common approach is to collect evidence about what changed and adapt. For such diagnosis to improve behavior, six ordered empirical conditions must hold: a meaningful reference, identifiability of the physical condition, use of the acquired evidence, decision value, selection value over a fixed alternative, and safe realization. We test this chain in controlled and public environments. It holds end to end in our controlled environments. After transfer to unseen mechanisms, however, it breaks at evidence use. On decisions requiring the full trace, the frozen decoder does not change its choice. A linear model using only trace increments recovers the correct choice…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22289v1 Announce Type: new Abstract: Large-scale egocentric and whole-body human demonstrations are becoming a primary source of data for embodied intelligence. They record what people perceive and do, but rarely the external specification that gave an action its purpose. In construction that omission is consequential: skilled work is directed at project-specific configurations defined in a design model - configurations not yet present in the environment being observed. A mason's transferable competence is not the geometry of one wall but the ability to realise a new geometry from a specification. We introduce the specification-conditioned demonstration: a synchronised record of the physical state a demonstrator perceives, the intended state supplied…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22285v1 Announce Type: new Abstract: Adapting language models to new domains via continual pre-training raises a basic evaluation problem: if the training corpus overlaps with what the model already knows, performance gains cannot be cleanly attributed to new learning rather than pre-existing knowledge. This matters most for knowledge-intensive, task-light (KHTL) robot deployments - pharmaceutical dispensing, hazardous-material handling, facility-specific protocols, where the physical task is simple but the governing rules are proprietary and safety-critical, and where extensive live testing is costly or unsafe. We introduce ORDER (Ontology-driven Decision-making for Embodied Reasoning), a benchmark built on a fictitious world: a 342,069-token synthe…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22278v1 Announce Type: new Abstract: Quadruped manipulators enable mobile grasping in complex environments, yet their whole-body control policies remain vulnerable to unreliable onboard visual perception. Existing methods are typically developed under relatively reliable observations and have not systematically examined how occlusion, segmentation-mask dropout, depth noise, and target-localization jitter affect grasp reasoning and target tracking. To address this gap, we introduce DeViGrasp-Bench, a benchmark for mobile grasping under degraded vision that incorporates controlled visual degradations, seen and unseen objects, multiple difficulty levels, and complex terrains, and evaluates task success, execution efficiency, and action smoothness. We fu…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22276v1 Announce Type: new Abstract: The Dynamic Window Approach (DWA) is widely used for local navigation, but its performance depends strongly on parameters that are typically fixed before navigation. In particular, the appropriate prediction horizon can vary with local free space: longer horizons support efficient motion in open areas, whereas shorter horizons help preserve feasible motions in narrow or cluttered regions. This paper proposes D3DWA, an adaptive DWA framework based on a Dueling Double Deep Q-Network (D3QN), which jointly selects the DWA evaluation weights and prediction horizon from a continuous navigation state at every control step while retaining DWA's trajectory generation and collision checking. In eight simulated environments,…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22274v1 Announce Type: new Abstract: Recent advances in humanoid robotics have produced diverse skills through reinforcement learning, motion imitation, and generative modeling. Yet these capabilities remain siloed because they are built around incompatible representations, interfaces, and controllers. We present CHOREO, a framework for training-free composition of heterogeneous humanoid skills. Our key observation is that, regardless of how a skill is learned, it can ultimately be expressed as an executable motion trajectory. Based on this observation, CHOREO converts each capability into SkillMotion, a unified representation that combines motion states, contacts, semantics, and boundary conditions. Skills are composed through direct continuation, c…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22295v1 Announce Type: new Abstract: Event pipelines often discretize asynchronous timestamps before learning. This step looks harmless, but its stability depends directly on temporal resolution. We study this dependence at the representation level. We first show that hard temporal binning is discontinuous: an arbitrarily small timestamp shift near a boundary can move unit event mass between bins. We then define a class of nonnegative, mass-preserving, resolution-faithful continuous encoders and prove that every encoder in this class has global L1 sensitivity at least 2/Delta, where Delta denotes bin width. Linear two-bin interpolation attains this limit. Local support and first-moment preservation also make it unique. Experiments on SHD, N-MNIST, an…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22293v1 Announce Type: new Abstract: Vision-language models (VLMs) and vision-language-action models (VLAs) are increasingly deployed in real-world applications. There, a small perturbation to the recorded camera image may change a decision significantly. However, existing benchmarks for these models only sample perturbations, which does not guarantee the absence of a failure in the untested region. We present the first robustness validation of six VLMs (drawn from the Gemma, InternVL, LLaVA, and Qwen families) and five VLAs (drawn from the GR00T, OpenVLA, and $\pi$ families) over entire continuous regions of photometric and geometric image perturbation: brightness shifts, camera rotations, and their composition. To this end, we build on the validati…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22291v1 Announce Type: new Abstract: This paper presents a comprehensive experimental evaluation and detailed analysis of state-of-the-art multi-object tracking algorithms, with an emphasis on quantifying the individual contributions of detection and association components to overall tracking performance. Unlike existing surveys that primarily offer theoretical categorizations or taxonomies of tracking methods, our work adopts a rigorous experimental perspective grounded in publicly available implementations, providing practical guidance for researchers and practitioners in method selection and system design. We introduce a unified pipeline diagram that consolidates the core components across the two main branches of visual multi-object tracking: tra…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22284v1 Announce Type: new Abstract: Talking-face (TF) deepfakes are detected unevenly by rPPG-based methods across generators. We study two lightweight visual-only cues, rPPG-derived waveforms extracted by RhythmFormer and lip-region discrete cosine transform (DCT) coefficients, on the seven TF methods of Celeb-DF++ under a subject-independent protocol. In-domain, lip-region DCT matches or exceeds the rPPG-derived 1D ResNet on every method except SadTalker, and Concat fusion reaches AUC 0.891 against 0.824 and 0.827 for the unimodal baselines. Under leave-one-generator-out evaluation the cues split: each transfers clearly better to three held-out methods, and IP-LAP is near chance for both. Concat averages 0.798 but falls below rPPG alone where DCT…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22283v1 Announce Type: new Abstract: Understanding the design space of streaming video diffusion is essential to exploring its potential for generation quality and computational efficiency. We develop a unified analytical framework that relates model and sampler choices, historical conditioning, execution scheduling, and training strategies. The framework accommodates a broad family of causal context-selection policies and makes their computational dependencies and training-inference alignment explicit. Within this design space, we study three representative policies: clean, same-level, and progressive history. On the full VBench prompt set, same-level and progressive history achieve aggregate scores of 85.24 and 85.60, respectively, compared with 84…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2609.22282v1 Announce Type: new Abstract: Reconstructing visual stimuli from electroencephalography (EEG) is difficult because scalp measurements have high temporal but limited spatial resolution, and paired EEG-image datasets remain small relative to modern generative-model training corpora. We present a reproducible single-subject baseline on THINGS-EEG2 that first tests the more defensible question of whether EEG can retrieve the viewed stimulus in a visual embedding space. A compact temporal-spatial convolutional encoder maps repetition-averaged EEG (63 by 250) to provided 512-dimensional ViT-B/32 image features. Model selection uses a concept-disjoint validation split, and final evaluation uses the official 200-image, 200-concept test gallery. Across…