AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Speculative Decoding by any other name would distil as sweet

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：NVIDIA's open 30B MoE targets the agent execution layer, with Switchyard routing each step to the cheapest capable model. The post NVIDIA AI Releases Nemotron 3.5 Lightning: A 30B Open MoE with 3B Active Parameters, and NeMo Switchyard Model Router 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：Threads

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Interaktiv Wo würden Sie sparen, wenn Sie SRG-Generaldirektorin Susanne Wille wären? Probieren Sie es aus Am 8. März stimmt die Schweiz über die SRG-Initiative ab, die die Gebühren massiv senken will. Die SRG müsste ung…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：The Looming Energy Wall AI is entering an era of seemingly smooth exponential acceleration. Models keep scaling and are emerging as multi-trillion-parameter behemoths with Fields Medal-level mathematical intelligence. D…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：OpenAI research reveals how enterprises are adopting agentic AI, using ChatGPT and Codex, and how frontier firms are pulling ahead in AI adoption.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：NVIDIA AI Factory Compute Is Becoming an Investable Asset Class Today, we announced partnerships with Apollo, BlackRock, Blackstone, Brookfield, Goldman Sachs and KKR to establish independent financing platforms designe…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：░░░█▀▀░█░█░▀█▀░█▀█░█░░░█▀█░█▀▀░░ ░░░▀▀█░█▀█░░█░░█▀▀░█░░░█░█░█░█░░ ░░░▀▀▀░▀░▀░▀▀▀░▀░░░▀▀▀░▀▀▀░▀▀▀░░Your buddy that tracks what you ship https://shiplog.life Log what you ship. A single-binary CLI that crawls your repos,…

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 agent observability enables effective evaluation of AI agents. Understand tracing, debugging reasoning, and performance insights to iterate and improve agent behavior.

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Notifications You must be signed in to change notification settings Fork 1 Star 59 BranchesTags Open more actions menu Folders and files NameName Last commit message Last commit date Latest commit History 622 Commits 62…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：Object removal models have improved faster than the metrics used to judge them. Diffusion erasers now reconstruct shadows, reflections and occluded structure convincingly, yet PSNR, SSIM, LPIPS, ReMOVE and CFD frequently rank their outputs the wrong way. The root cause is structural: erasure is an ill-posed, one-to-many task, so no single ground truth exists to […] The post Xiaomi’s MiLM Plus Releases PROVE: Perception-Aligned Object Removal Metrics RC-S and RC-T With a Real-World Video Benchmark appeared first on MarkTechPost.

Treg 是一個工具聚合平臺，類似於 OpenRouter，提供 2,600 多個 API，且不加價（0% 加成）。本文還包含討論和連結。

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：sophntic fig. i — the other sophont, observed soph·ont · n. one capable of reason Releasing soon We reject the paradigm of scale. 1× Sophontic 60× Competitors, on reasoning evaluations Sophontic cultivates geometric den…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10484v1 Announce Type: new Abstract: Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in vision-language-action models (VLAs) are typically optimized for reconstruction under L1/L2 losses in raw action space, where numerical proximity need not reflect linguistically meaningful distinctions. On BridgeV2, we show that action trajectories contain verb-grounding information beyond visual state changes, and that reconstruction-only discrete tokenization systematically erodes this information. To address this problem, we introduce SALT, a Semantically ALigned action Tokenizer that augments a VQ-VAE-style tokenizer with an auxiliary objective requiring a frozen vision-langu…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10449v1 Announce Type: new Abstract: Long-horizon service robots require persistent world models that can be built autonomously in unseen environments and revised as task-relevant objects change. Existing methods rely on online mapping, which accumulates localization and observation errors, static scene representations that cannot capture persistent object changes, or holistic vision-language predictions that lack verifiable 3D geometric evidence. We present PBD-AG, a persistent baseline-delta active graph framework that decouples robot-verified stable fixtures from revisable dynamic object events. Under our framework, the robot autonomously bootstraps the structural baseline from onboard exploration and inspects discovered fixtures to ground hierarc…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10387v1 Announce Type: new Abstract: We present a novel stepping strategy for pitch unlocked planar monopeds where the reaction torques from stabilizing pitch with a conventional PD + feedfoward controller are recruited to counteract energetic losses from damping. By moving the location of the mass center, our controller increases the pitch stabilization torque, thereby adding energy to the gait. A new stepping policy adjusts the distribution of energy between the radial and angular degrees of freedom to counteract dissipative losses and achieve a user specified balance between steady state fore-aft speed and apex height. Hybrid averaging analysis yields closed form expressions for the fixed points and eigenvalues of the resulting gait, lending insig…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10383v1 Announce Type: new Abstract: Bimanual dexterous grasping of large objects is a critical challenge in robotic manipulation. However, most existing studies focus on sequential manipulation rather than cooperative grasping, and methods addressing such bimanual tasks have largely been limited to simulation. These limitations stem from the difficulty of acquiring full 3D object models and generating physically plausible grasping actions. To fill this gap, we propose a real-world bimanual grasping framework that includes: a multimodal dataset capturing joint angles, visual observations and force signals; a Denoising Diffusion Probabilistic Model (DDPM)-based module that generates joint-level grasp configurations from segmented point clouds; and an…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10367v1 Announce Type: new Abstract: Direct teleoperation of vehicles faces critical technical bottlenecks: communication latency and the operator's inability to physically perceive unmodeled environmental disturbances (e.g., aerodynamic drag, bank angles) coupled with highly nonlinear tire-road dynamics. To address these challenges, we propose a tailored unilateral teleoperation framework. The system integrates the Wave Variable (WV) approach to passively guarantee stability under stochastic delays, and an adaptive Radial Basis Function Network (RBFN) to actively compensate for vehicle-specific uncertainties. Unlike existing WV-neural network architectures designed for bilateral robotic arms, our framework features decoupled adaptive laws specifical…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10232v1 Announce Type: new Abstract: Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation. Building on the future-prediction ability of video models, many WAMs generate future videos and recover actions with inverse-dynamics models, or use these predicted videos as goal conditions for action generation. In both cases, the world model is trained mostly on successful demonstrations and has little reason to predict the consequences of bad actions. We introduce FACT, a causal World-Action Model that predicts future video and task progress conditioned on the executed action. This action-conditioned interface allows failure rollouts to supervise action consequences, turnin…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10220v1 Announce Type: new Abstract: Humanoid locomotion in highly confined environments requires navigating dense environmental obstacles and complex self-collision bounds while maintaining multi-contact dynamic feasibility. Traditional trajectory optimizers frequently struggle in these restricted spaces, as navigating the large collision space with splines on particle abstractions is insufficient and leads to poor local minima. To address this, we propose a three-stage whole-body planning framework that formulates kinematic path planning directly over kinematically reachable rigid-body volumes. By integrating differentiable collision avoidance into a reachability-constrained formulation, our framework synthesizes volume-informed guides that reliabl…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10056v1 Announce Type: new Abstract: Following a target human in crowded environments involves an inherent conflict between staying close to the target and navigating safely among surrounding pedestrians and obstacles. This conflict becomes more severe in dense scenarios, where aggressive following risks collisions and conservative margins lead to target loss, especially when pedestrian behaviors are unfamiliar or unpredictable. Existing reinforcement learning (RL) methods typically encode these competing objectives into a single dense reward, but the resulting proximity-safety balance is implicit and difficult to adjust across conditions. To address this, we decompose the human-following task into a sparse task reward and independent cost constraint…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10025v1 Announce Type: new Abstract: For safety-critical software, data from the software's operational past (e.g. a sequence of success and failure events experienced by the software) can provide strong statistical support for reliability claims about the software. However, such data might not describe past software failure events in sufficient detail, and this might leave a reliability assessment (based on this data) unable to account for important features of past software failures. In this paper, by extending conservative Bayesian inference (CBI) techniques used in reliability assessment, we illustrate a principled statistical approach for checking the robustness of reliability claims derived from insufficiently detailed operational data. We demo…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10023v1 Announce Type: new Abstract: Vision-based navigation complements Global Navigation Satellite Systems, but certification demands integrity guarantees that account for faulty measurements. Previous work presented a probabilistic computer vision pipeline for runway-based pose estimation with fault detection inspired by Receiver Autonomous Integrity Monitoring. This work extends that framework by deriving protection levels, which provide probabilistic bounds on pose error that remain valid under undetected faults. We present an algorithm for computing protection levels for the nonlinear Perspective-$n$-Point problem applied to an aviation setting. The algorithm covers all six degrees of freedom of the aircraft pose (position and orientation) dire…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10203v1 Announce Type: new Abstract: Despite the success of convolutional neural networks in image classification tasks and their general application in multi-modal models, their susceptibility to out-of-distribution and adversarial attack samples raises concerns regarding trustworthiness and safety. Among the approaches to tackle such issues, detection methods that analyze the model's intermediate activations to estimate a confidence score are a promising family that evaluates the decision process, relying on a dimensionality reduction step to enable efficient downstream processing of the high-dimensional activations. However, when considering convolutional layers, the dimensionality reduction methods in the literature either lack a mechanism to 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:2608.10195v1 Announce Type: new Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects. These are the Gestalt operations that visualization design builds on. Whether vision models organize visual content this way has not been systematically tested. We introduce a behavioral battery that scores models against human data from prior perception studies on four grouping tasks: mark-color odd-one-out, color-series counting, silhouette recognition, and object odd-one-out. We apply it to 45 models across five training families: supervised, self-supervised, and contrastive vision-language encoders, open-weight VLMs, and closed foundation m…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10181v1 Announce Type: new Abstract: Computer vision saliency models predict where people will look, one map per image, and a billion-dollar predicted-attention industry sells those maps in place of measuring real viewers. I test the leading models from the audience side, against 11.4 million webcam gaze points from 3,023 US adults recruited to national quotas, viewing circulating news photographs. I show that an untrained central marker outperforms every trained network, because the content the networks add on top of the center falls where these audiences never look. What accuracy remains is systematically biased, favoring younger, White, and moderate viewers over older, Black, and ideologically extreme ones. I propose a way forward and build on wha…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10173v1 Announce Type: new Abstract: Most radiotherapy dose-prediction models use only CT images and anatomical structures, although intensity-modulated proton therapy (IMPT) dose also depends strongly on beam geometry and available clinical datasets are often small. We present DoseBridge, a denoising diffusion bridge model that uses the patient CT as a structured bridge endpoint and encodes plan-specific beam geometry in a spatially aligned beam mask. Multiscale fusion combines CT, target, organ-at-risk, and beam-mask representations with 1.95% additional parameters. DoseBridge was retrospectively evaluated on single-institution CT images and treatment plans from 52 patients with advanced-stage lung cancer treated with 60 Gy in 30 fractions; 42 case…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10170v1 Announce Type: new Abstract: Patient motion remains a source of image degradation in brain MRI, leading to signal loss, blurring, and geometric distortion that compromise quantitative analysis. Existing deep learning methods for motion correction typically rely on paired clean-corrupted data or k-space acquisitions, which are rarely available in clinical settings. We propose SSRL-MAR, a motion artifact-aware unpaired representation learning framework for motion artifact reduction that requires neither paired training data nor explicit motion labels. SSRL-MAR employed a three-stage training strategy: (1) contrastive learning on 3D patches to extract motion representations by contrasting clean and synthetically corrupted images, (2) a motion ar…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10162v1 Announce Type: new Abstract: Methods for text-based generation of hand-object interaction (HOI) sequences primarily focus on producing smooth, physically plausible trajectories. A truly utilitarian method should additionally support variable-length generation, composite motion sequences, motion completion and infilling, and reliable termination without compromising physical plausibility. Standard diffusion models for HOI generation are typically trained only for text-to-motion generation on atomic motions and require the motion length to be specified a-priori. Autoregressive (AR) methods provide greater sequence-level flexibility, but commonly depend on discrete motion codes, which can lose contact-sensitive motion detail. To address these ke…

AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.10131v1 Announce Type: new Abstract: Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are difficult to inspect beyond downstream task performance or global dimensionality reduction. We propose position-prompted PCA (P3CA), an encoder-agnostic method for local probing of channel-rich spatial tensors. Given a user-selected spatial prompt, P3CA estimates the feature normalization and dominant covariance directions within that region, then applies the resulting projection to the full tensor to visualize where locally informative directions are expressed. This produces a region-conditioned representation lens without modifying the encoder, retraining, or requiring…