Decision models enable fast, confidence-aware decisions by scoring candidate answers in a single forward pass, without generating text or intermediate reasoning. Yet reasoning can substantially improve decision quality, raising the question of whether its benefits can be retained without the cost of generating it. We investigate this question with \textbf{GLiDE}, a family of decision models spanning 0.4B to 27B parameters. Building on Qwen hybrid language models, GLiDE enables bidirectional interactions between the context, question, and candidate answers by removing causal masking from full-attention layers. To transfer reasoning capabilities into single-pass inference, we combine soft-target distillation from multiple teachers, including a reasoning model, with progressive post-training on diverse decision tasks. We further explore parameter-free recurrent depth to increase inference-time computation without generating tokens. Across five model sizes, GLiDE lies on the performance--parameter Pareto frontier of the Hugging Face \DI{}, with each model outperforming evaluated alternatives of equal or smaller size. \dmtwo{} (27B) achieves a hidden-set score of 71.52, with an expected calibration error of 2.0\% and a median latency of 92.9\,ms on a single GPU. Further checkpoint averaging and parameter-free recurrent depth yield GLiDE~27B, which reaches 73.37 with an expected calibration error of 2.1\%.
Visual Attribution Limits and Graded Provenance Auditing in Commercial Video-Generation APIs
Haocheng Mei, Yuchuan Tian, Yingte Shu, Chao Xu, Kai Han, Hanting Chen, Yunhe Wang
AI 速读 基于摘要
结合被动归因测量与密码学来源验证,提出分级审计框架,以应对商业视频生成API中的模型替换风险。
cs.CR · cs.CV
查看原文摘要
Commercial video-generation APIs bill by model and tier, while intermediaries could substitute cheaper models, lower tiers, or cached clips. What can a delivered file establish about its origin? We combine measurements of passive attribution and cryptographic provenance into a graded audit. We test attribution probes and zero-shot detectors under re-encoding, downscaling, and frame-rate changes, and survey C2PA and GB 45438 metadata across 19 commercial endpoints. Only authenticated provenance supports accusations: tier contradictions or duplicate signed instances under fresh-generation contracts, excluding retries and idempotent returns. Unverifiable signed-endpoint deliveries trigger original-file demands under pass-through clauses; archive-reuse and delivery-parameter screens support review only. Six-model container and bitstream accuracy falls from 83.9% on raw files to 45.3% after uniform re-encoding, using different feature sets. Subsampling real references from 24 to 3 fps raises pooled D3 AUROC from 0.845 to 0.988. Only BytePlus authenticates tier claims under our pinned policy, including 187/187 audited deliveries across three Seedance tiers; tested remuxing and re-encoding leave processed Seedance files unverifiable. The audit identifies authenticated contradictions in 100/100 raw 720p signed tier-swap cases, with zero observed false flags on the tested honest pools.
It is a classical result that the definable isomorphisms of the simply typed lambda-calculus with function types are exactly the hereditary permutations, and that they are generated by $A \to B \to C \cong B \to A \to C$ and congruence. We give a new proof of this result that stays inside beta-normal eta-long typed terms and uses no completeness theorem: an induction that descends through both components of an isomorphism at once. We then go one level up and prove a coherence theorem: two derivations of an isomorphism denote the same isomorphism if and only if they are equal modulo an explicit list of equations (groupoid laws, functoriality, involution, naturality and the braid equation), so these equations present the groupoid of isomorphisms, a hereditary version of the Coxeter presentation of the symmetric groups. All results are formalised in Agda, on intrinsically typed syntax with hereditary substitution, without postulates. The work is a case study for the syntactic completeness conjecture of University Algebra, a proposed solution of Tarski's high school algebra problem using dependent types, whose semantic counterpart is open. We explain the motivation and which parts of the method we expect to carry over.
Autoregressive (AR) grounding models serialize spatial predictions, introducing sequential latency and imposing a causal order on output tokens. We view grounding as visual evidence extraction: objects, locations, and spatial relations are jointly constrained by the image and query, yet their dependencies do not imply an intrinsic left-to-right generation order. This distinction makes bidirectional diffusion a natural fit, allowing spatial hypotheses to emerge in parallel and be jointly refined through iterative denoising. We introduce GroundAnything, a 4B-parameter grounding foundation model that reconciles fast parallel decoding with precise localization through blockwise denoising. Training combines grounding pretraining from public datasets and dedicated data engines, direct AR-to-diffusion conversion with joint AR and diffusion objectives, supervised fine-tuning, and GRPO-based reinforcement post-training. Across 30 grounding benchmarks, our autoregressive variant, GroundAnything-VLM, establishes a new overall state of the art among similarly sized models at 72.42%, remaining competitive with GPT-6 Astra (71.35%). With entropy-guided decoding, GroundAnything also surpasses the prior state of the art at this scale, averaging 61.75% versus 53.32% for the fast MTP-based LocateAnything model. We further explore decoding strategies, showing that an optional self-speculative mode achieves a 4.51$\times$ speedup over the AR counterpart with a 0.74 percentage-point drop in COCO F1mIoU. Infrastructure experiments show that progressive inference optimizations translate parallel decoding into practical speedups. These gains support efficient visual grounding in latency-sensitive real-world systems.
Power electronics is central to the energy transition, but developing new hardware still relies on human-led design, fabrication, testing, and iteration. We present JARVIS, an embodied AI agent that autonomously closes this loop for circuit boards. JARVIS maintains machine-specific capabilities and constraints, scans its workspace using a robot-mounted 3D scanner, and constructs an executable digital twin in which it rehearses robot motions, fabrication steps, and circuit behavior before consuming materials. A single text instruction initiates the physical experiment. Using unmodified desktop equipment, the agent coordinates a robot arm, a PCB printer that deposits conductive silver ink and solder paste, and a pick-and-place machine. It verifies progress using cameras and sensors, then tests the fabricated circuit with an OPAL-RT real-time simulator and an oscilloscope. Based on the measurements, JARVIS diagnoses deviations from the design and generates a revised design in KiCad for subsequent rehearsal. In a demonstration involving a 60 Hz notch filter for grid-connected converter sensing, JARVIS completed a first-run experiment in 2 h 39 min without human intervention, achieving 50.6 dB attenuation at 60 Hz. Its digital-twin rehearsal identified five issues before fabrication, including a test criterion that would have incorrectly rejected a functioning board. During execution, the agent also resolved encountered faults autonomously. These results demonstrate an integrated agent-driven workflow for physical design, fabrication, measurement, and iterative improvement of power-electronic circuitry. To our knowledge, JARVIS is the first system in power electronics in which an agent closes the physical design-build-test-learn loop for circuit boards.
Towards end-to-end optimization in multimaterial 3D printing
Xue-Ling Luo, Steven Yang, Jingye Tan, Robert F. Shepherd, Noy Cohen, Nikolaos Bouklas
AI 速读 基于摘要
结合稀疏化物理增强神经网络与符号微分,实现从连续变化多材料系统到力学仿真与设计的端到端优化工作流。
physics.comp-ph · cs.CE · cs.RO
查看原文摘要
Multimaterial 3D printing enables the fabrication of functionally graded components, but optimizing their spatial material distribution alongside structural topology remains a formidable challenge due to high-dimensional design spaces and complex constitutive modeling. Using neural network constitutive laws in topology optimization requires their tangents and design sensitivities, which current approaches obtain by automatic differentiation through the network or derivation by hand. This paper combines sparsification, which reduces a trained physics-augmented neural network to a compact, interpretable closed-form law, with symbolic differentiation, enabling an end-to-end workflow from a new continuously varying multimaterial system to its mechanical simulation and design. By extracting closed-form, composition-aware hyperelastic constitutive laws from sparsified neural networks trained on experimental data, this approach facilitates exact symbolic differentiation of the terms required by the adjoint state method implemented with FEniCSx, circumventing the bottlenecks of applying neural network constitutive models in analysis and optimization. This pipeline is deployed on soft robotic gripper applications, demonstrating continuous composition optimization for highly anisotropic contact responses, and the concurrent optimization of macroscopic topology and material distribution under non-failure stretch constraints. This study is a step toward replacing conventional constitutive modeling and laborious empirical prototyping, establishing interpretable machine-learning models as practical, robust design primitives for advanced multimaterial additive manufacturing.
Tool-using LLM agents execute consequential operations on behalf of users. Because the LLM driving an agent processes trusted user instructions and untrusted content in the same context, agents are vulnerable to indirect prompt injection attacks that induce unintended actions by mixing malicious instructions into benign data. Defenses based on prompting or content detection are easily evaded by paraphrasing attacks, while system-level defenses that constrain tool calls using inferred user intent, or restrict which sources can supply values to sensitive tools, greatly compromise utility. We present ROPE (Routed Origin Policy Enforcement), a defense that greatly improves the utility-security tradeoff by leveraging system roots of trust to create and enforce per-task policies on sensitive tool parameters. Our key insight is that authentication and integrity protection provide a basis for identifying the source of content independently of instructions embedded in it. Before a task unfolds, an LLM router reads only trusted task input to set a provenance rule for each sensitive tool parameter, accounting for the nature of the task and the values and sources the user specified. As the agent works, an origin labeler records where each piece of content came from, using the user's request, platform metadata, and protected record fields as trust anchors. Before any sensitive tool executes, a deterministic verifier requires each of its origin-guarded values to match a value in a source its rule accepts. We show that ROPE provably guarantees parameter value provenance to sensitive tool calls and is immune to paraphrasing attacks. Against eleven defenses on AgentDojo and AgentDyn under static, adaptive, and long-horizon attacks, ROPE exhibits near-perfect security while compromising far less utility than the best baseline defenses. Code and data are available at https://github.com/xhOwenMa/ROPE.
We introduce a predictive world model for electronic health records (EHR) that represents patient histories as action conditioned latent trajectories. Rather than modeling clinical events solely through autoregressive token prediction, our framework explicitly separates patient states from observed clinical actions and learns their evolution through a state and action conditioned transition operator. At its core is a state dependent linearization predictor that propagates local changes in latent patient state, enabling time resolved prediction, multi step rollout, and action conditioned simulation. Empirically, we show that generated latent trajectories preserve downstream predictive signal, temporal structure, and subgroup level statistical relationships present in encoder derived representations. We further decode free running rollouts into the original clinical feature space and evaluate future clinical measurements against observed values using task matched forecasting baselines, demonstrating that the learned dynamics retain predictive information beyond latent space agreement. Across binary classification and time to event tasks, EHR WM achieves competitive, though task dependent, performance relative to substantially larger EHR foundation models while using a 30x smaller parameter footprint. Finally, perturbing observed action sequences produces corresponding changes in generated trajectories, demonstrating the action sensitivity of the learned dynamics. Together, these results support world modeling as a complementary framework for learning explicit, time indexed representations of patient evolution from longitudinal EHR.
Recent work on robot manipulation has focused on specialist policies trained on demonstrations. We show that generalist AI models can control manipulators more reliably than specialist policies such as vision-language-action models (VLAs) and world-action models (WAMs). We systematically analyze agentic manipulation policies (AMPs), in which a generalist AI model commands the manipulator directly, adapting its actions as the task unfolds. We present AMP1, a reference harness that runs unchanged across single-arm, bimanual, and mobile manipulation. AMP1 achieves state-of-the-art results on the RoboLab-120 and CaP-Gym benchmarks, with no demonstrations or task-specific training. On RoboLab-120, AMP1 reaches an 85.6% success rate zero-shot, compared to 49.2% and 42.9% for leading VLA and WAM policies. The agent succeeds zero-shot in 104 of 108 real-world trials spanning twelve tasks and three robot instances, reducing failure rates by 20x and 15x relative to strong VLA and WAM baselines. The basic harness supplies no grasping, pushing, or placing skills; the agent develops its own strategies, such as searching for hidden objects, using objects as tools, and calibrating its cameras. With the addition of a persistent memory store, the agent can also learn from experience: an augmented harness with a memory representation that is carried across episodes lowers the failure rate on RoboDojo bimanual manipulation tasks by 4.6x relative to zero-shot deployment. Our analysis suggests that AMPs are substantially more general and robust than specialist manipulation policies, providing a promising foundation for robot manipulation. See https://apple-aiml-research.github.io/ml-amp/ for code and videos.
Feed-forward models have been very successful in 3D reconstruction with ad hoc attention designs that relate all view patches densely. However, the cost of this dense global attention grows quadratically with the number of views, preventing the model from applying to larger-scale reconstruction settings. In this paper, we argue that most dense attention computations are unnecessary from a classical structure-from-motion perspective: 3D structures stem from geometrically matching regions in 2D. We bring this principle to learning-based feed-forward reconstruction with our Sparse Geometric Attention Reconstruction (SGAR) method. In SGAR, each patch token attends to only a small set of patch tokens from other views, chosen by a lightweight learned key selection module trained to predict cross-view 3D proximity of tokens. Thus, dense global attention is replaced by much more efficient geometric-similarity-guided sparse attention. SGAR is a general method that can be applied to different feed-forward models by fine-tuning. In our experiments, we show that SGAR is the fastest among both state-of-the-art dense and sparse methods and the most accurate sparse one. It runs up to 12-times faster than dense attention at 1,000 views with stable pose accuracy where existing sparse methods fail, and shows the best performance in reconstructing more complete geometries on the same time budget.
Surgical teleoperation deprives surgeons of touch, forcing visual inference of tissue forces; the commercial platforms now restoring force feedback remain closed, preventing open research on haptic shared control. This paper provides a system contribution: it presents an open-source, ROS 2-native framework that integrates the compact, three-degree-of-freedom (3-DOF) Haply Inverse3 haptic device with the da~Vinci Research Kit (dVRK). The framework includes a novel mapping strategy that combines 3-DOF translational device input with separately tracked VerseGrip orientation into 6-DOF patient-side manipulator commands. Two virtual-fixture-inspired guidance modes serve as reference implementations to evaluate the framework in a within-subjects user study on a teleoperated hot-wire benchmark task in simulation, and the architecture is further demonstrated on physical dVRK hardware. Relative to unassisted manual control, linear guidance significantly reduced both the number of wire contacts and the task completion time, whereas the progressive-stiffness guidance produced consistent but statistically non-significant trends in the same direction. Subjective ratings of workload, agency, and satisfaction showed favorable descriptive trends for the guidance modes. The results demonstrate the feasibility of haptic shared control with a compact device coupled to the dVRK and provide an openly available, reproducible platform for future research. They further suggest that simpler linear feedback may be more robust for inexperienced operators than more complex profiles.
We investigate the reconstruction of holographic duals for strongly coupled quantum field theories in regimes characterized by large hierarchies and the presence of false vacua. Within the gauge/gravity duality, these features translate into non-trivial thermodynamic behaviour and exotic renormalization group flows, including skipping flows between non-adjacent fixed points. Building on previous work based on Physics-Informed Neural Networks (PINNs), we extend the holographic inverse problem of reconstructing the bulk scalar potential from boundary thermodynamic data into this new regime. This setting presents a variety of conceptual and numerical challenges, such as near-degenerate states, large hierarchies of energy scales, and regions of the potential that are not directly probed by the input data. We develop a set of methodological advances that overcome these obstacles, thereby improving the established PINNs-based methodology and extending it to new physical regimes of interest that were previously out of reach. Applying the developed framework, we demonstrate accurate reconstruction of scalar potentials deep into the false vacuum regime, achieving robust agreement with the physical features of the underlying thermodynamics despite significant numerical stiffness. Our results extend the bridge between holography and machine learning, and suggest that data-driven approaches can provide new insights into the structure of strongly coupled systems.
LLM agents spend nearly all their time waiting for the model. On Amazon Bedrock AgentCore, our agents waited a median of 2.7 seconds for each model reply, then computed for an estimated 5 to 40 milliseconds. AgentCore does not charge for CPU during the wait. But it reserves a separate environment, a virtual machine with its own memory, for every conversation, and keeps it reserved until the conversation is closed. So 1,000 conversations reserve 1,000 environments to do the work of 2 to 15 processor cores. A service runs out of environments long before it runs out of processing power. The shortage has two causes, and each has a fix. An environment stays reserved after its conversation ends: in the customer-service benchmark we ran, a conversation lasts 33 seconds on average, but its environment is held for 15 minutes more unless the client closes it. And an environment serves only one conversation, which is mostly waiting: in our simulation, 64 conversations sharing one environment need 59 times fewer environments, and 99 of every 100 replies are delayed by at most 40 milliseconds. The milliseconds are an estimate because they are hard to measure: a stubbed model, a timer around the model call, and steps run back to back each gave a plausible number that was too low. We show how to avoid all three. Of the two fixes, closing needs only the client. Sharing needs the platform, and of the agent runtimes we surveyed only one allows it, in part. They keep conversations apart because an agent runs tools, and sometimes code, chosen by a model. The open problem is to keep them apart without reserving an environment for each while it waits.
Proactive video assistants must decide not only what to say, but also when to speak. Existing reinforcement-learning objectives can reward timely, correct responses without accounting for response volume, thereby encouraging unnecessary or repeated emissions. We identify this failure mode in MMDuet2, whose proactive area-under-the-curve (PAUC) reward promotes timely responses but does not price the number of emissions. We show analytically that this makes additional responses weakly penalized or effectively free, systematically encouraging over-emission. We then propose an emission-aware F1 reward for interval-valued annotations, using exclusive span--emission matching to price false emissions and missed spans. Under MMDuet2's training recipe, our policy on the visual subset of OmniPro replies 2.5x less often than MMDuet2 while raising timing F1 from 0.259 to 0.396 and content-aware F1 from 0.103 to 0.154; a more conservative variant cuts replies by 82.5% and raises precision from 0.161 to 0.418. On ProactiveVideoQA, the same reward adds replies where the baseline is nearly silent, and PAUC ranks a heavily over-emitting policy second despite near-last F1, because it is insensitive to response count. Our results indicate that proactive assistants should be trained and evaluated with objectives that price emissions.
Continuous Integration (CI) is a popular programming practice for the seamless integration of code changes into the code base. Using CI, developers benefit from automated assembling and testing of the code after each commit. However, while the frequent integration and building supports developers, it also comes at the high costs of wasting time and resources for minimal changes. In this work, we investigate the potential of reducing the drawbacks by anticipating the build outcome using machine learning techniques. In particular, we propose a random forest model with various features such as changes to the source and build code, and changes to the complexity of the code. We observe that our model shows a good performance in an intra-project and holistic setting yielding a median MCC of 0.82 and 0.86, respectively. We also found that the most important features of our model concern the historical build result information. Additionally, we investigated the development of the performance of our model over time and found that our model can quickly arrive at its peak performance. In an additional experiment, we removed the hard-to-interpret historical build information features and found that our model still yields decent performance while improving the interpretability of it. Summarizing, our model can help to avoid unnecessary build runs by anticipating the build result and thus, save resources.
We present a new adaptive stepsize rule that biases gradient descent toward flatter minima in both theory and practice, and establish the first uniform-in-time guarantees for both sharpness and loss reduction for a broad class of locally quadratic objectives. Our critically damped Polyak (CDP) stepsizes multiply the classical Polyak rule by $4$ and a mild damping factor. The factor $4$ is critical in that it produces equioscillations around the manifold of minimizers $\mathcal{M}$ to leading order. Damping provably drives convergence to $\mathcal{M}$. CDP thus operates at the edge of stability by adapting its stepsizes to local curvature. Once the loss is small, its projected iterates follow gradient descent on $\log{λ_1(\nabla^2 \mathcal{L})}$ along $\mathcal{M}$ to leading order, paralleling the flatness bias of normalized gradient descent (Arora et al., 2022). Unlike normalized gradient descent, CDP step lengths shrink with the distance to $\mathcal{M}$, enabling convergence to an interpolating solution that locally minimizes sharpness at finite learning rate. We establish our theory for a broad class of non-negative losses with locally quadratic Morse-Bott structure near $\mathcal{M}$, capturing regular interpolation regimes in smooth overparameterized neural networks. Empirically, CDP stepsizes produce a flattening effect similar to that of Sharpness-Aware Minimization (SAM, Foret et al., 2021), reducing sharpness even in settings beyond our theory, including nonlinear teacher-student networks and fine-tuning of pre-trained LLMs.
RTL simulation is essential for hardware design and verification, yet its execution time grows rapidly with design scale and complexity. CPU- and GPU-based simulators exploit parallelism to accelerate RTL evaluation, but achieving high simulation throughput for large designs remains challenging. FPGA-based simulators offer higher throughput by mapping RTL computations directly onto hardware, but their scalability is constrained by FPGA resource capacity. We present FoldSim, an automated framework that enables cycle-exact simulation of large RTL designs on a single FPGA through hierarchical folding. FoldSim maps instances across the design hierarchy onto shared logic while maintaining their independent state. Given foldable module classes, its compiler constructs a static schedule that coordinates their execution, reducing dynamic synchronization overhead and making state accesses predictable. FoldSim backs state that exceeds on-chip capacity with external memory and brings it to the shared circuits as needed. A configurable DRAM model separates target-memory timing from host delays. The compiler explores replica allocations and state placement to balance resource savings against simulation time. On one AMD Alveo V80, FoldSim runs an 8-SM GPU and a 1,024-node Rocket datacenter with 4,096 processor cores. The unfolded implementations require approximately 16x and 200x as many LUTs as FoldSim's, respectively. The datacenter keeps about 1.9 GB of state in HBM, while a 4-SM GPU completes a 1024x1024 GEMM in 4.24 seconds, versus 26 hours in software RTL simulation.
Generative artificial intelligence (AI) is currently revolutionizing content creation across various media. Between those who fear it will replace human creativity and those who regard it solely as a tool, many in the creative industries are beginning to view generative AI as a collaborator. Yet interaction with these systems often relies on discrete, turn-based prompting that can interrupt flow and constrain expression to symbolic text. We explore physiological signals as a source of continuous adaptation without explicit commands, as a path toward embodied co-creation. This paper presents ReTiNA-Cinema, a methodological proof-of-concept that integrates electroencephalography (EEG) with generative AI to enable physiologically guided visual modulation of cinematic material. By linking physiological activity to the evolving appearance of a film, the system provides a basis for exploring embodied sense-making, in which viewers' bodily responses contribute to shaping the sensory experience through which they interpret the unfolding scenes. The system combines real-time EEG signal processing with a generative AI pipeline based on Stable Diffusion Turbo for frame-level image transformation. Single-user and two-user configurations map EEG-derived features to prompt selection and transformation strength. ReTiNA-Cinema offers a framework for exploring how the physiology of viewers might influence a film's visual presentation, extending the possibilities for participation in cinematic experiences and storytelling. This system raises questions about the effects on engagement, perceived agency, and emotional response, which remain open to future empirical study. Video illustrations: https://www.youtube.com/playlist?list=PLMu36WzSQKiVeBnrUdwUAoUhqLqGX3_bw and implementation: https://github.com/KairosHive/retina-cinema.
Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving. Directly quantizing recurrent states to low precision often leads to severe accuracy degradation, as quantization errors propagate through successive state updates. We discover that the impact of these errors depends on two complementary dimensions: temporally, errors in long-lived memory can persist across many decoding steps; spatially, errors in different key rows affect model outputs differently, while state magnitudes vary substantially along both rows and columns. Motivated by these observations, we propose STEPQuant, a spatial-temporal post-training quantization framework for Delta-rule recurrent states. STEPQuant allocates precision according to error magnitude and memory lifetime, and jointly fits key-row and value-column scales based on state distributions and key-row impact on output error. Experiments on Qwen3.8-27B and Kimi-Linear-48B-A3B-Instruct across both long- and short-generation benchmarks show that STEPQuant closely matches FP32-state accuracy under a nominal 6-bit budget and outperforms uniform INT8 in its 4-bit configuration. Integrated into SGLang with optimized GPU kernels, 6-bit STEPQuant achieves over 5x recurrent-state compression and reduces total serving memory by up to 68.7%. Our code is available at https://github.com/Dreamer-Toby/STEPQuant.
Data assimilation (DA) in partially observed nonlinear systems requires repeated estimation of both hidden states and their uncertainty. Conventional nonlinear filtering can be computationally expensive and often relies on an explicit dynamical model. In this paper, we develop the Neural Conditional Gaussian Model (Neural CGM), a data-driven dynamical model that maps unobserved physical states into a learned latent space, where the dynamics of the latent states follow a conditional Gaussian structure. This structure allows closed-form DA updates in the latent space, while nonlinear encoder-decoder mappings retain the flexibility needed to represent complex dynamics in physical space. A key feature of Neural CGM is its treatment of uncertainty in DA. The latent posterior mean and covariance are mapped to the physical variables through a Gaussian decoder that combines local moment propagation with learned nonlinear corrections. The resulting physical-space posterior statistics depend on the sequentially updated latent distribution rather than on a separate post-processing estimate. The same statistics enter a Gaussian negative log-likelihood during training, so both the posterior mean and uncertainty affect the learned model. Because Neural CGM learns the dynamical model itself, it can also be used for state forecasting and simulation without explicit knowledge of the governing equations. Numerical experiments on benchmark nonlinear dynamical systems show accurate state estimation and forecasting while substantially reducing online assimilation cost relative to conventional nonlinear DA methods. Neural CGM is therefore suited to repeated state estimation, uncertainty quantification, and prediction from partial observations.
Segmentation foundation models offer reusable tools for universal medical-image segmentation, but their development and evaluation have largely centered on structural CT and MRI imaging. Functional imaging such as PET provides complementary metabolic information yet remains less studied and validated. Moreover, existing evaluations often involve different datasets and tasks, making modality-associated variation difficult to distinguish from differences in segmentation targets and data distributions. To enable a more direct comparison, we introduce UMD, a whole-body multi-organ dataset comprising 490 PET/CT and 464 PET/MRI examinations with 13 annotated organs (approximately 675,000 2D slices and 12,000 3D organ annotations). UMD evaluates structural and functional images separately on corresponding organs within the same examination, reducing variation in patient anatomy and target selection. We benchmark the out-of-the-box segmentation capabilities of five representative 3D foundation models on UMD. Overall, most evaluated models show limited PET segmentation performance, and some configurations also yield near-zero overlap on CT or MRI under the evaluated workflows. These findings highlight the need to assess tool applicability across different imaging conditions and identify opportunities for cross-modality generalization. UMD provides a paired data resource and evaluation setting for this investigation.
In real-world black-box optimization problems, a mechanistic simulator is often available that approximately predicts the behavior of the system as a function of the parameters being optimized. Here, we show how an amortized inverse map of such a simulator can be used in Bayesian optimization to restrict the search space while using a Gaussian process kernel that is aware of the original problem geometry. This allows for efficiently leveraging the low intrinsic dimensionality of the optimization problem. We characterize its approximation bias and information gain, and derive an intrinsic-dimension-dependent regret rate under additional geometric and Gaussian Process assumptions. We illustrate the method with an application to drug dosing personalization in Parkinson's disease. We use, as a simulator, a pharmacokinetic/pharmacodynamic (PK/PD) model of a drug, a mechanistic model calibrated on population data with quantified parameter uncertainty. A dosing neural network is trained offline against the model, amortizing the map from patient PK/PD parameters to the regimen predicted to be optimal, and online Bayesian optimization then searches over this learned, low-dimensional representation rather than over raw dosages. Numerical simulations demonstrate the improved performance of our method in this application, as well as under simulator misspecification.
Biomedical entity linking maps textual mentions to concepts in structured knowledge bases such as UMLS or SNOMED CT. Most existing systems link each mention independently, using only the mention or its surrounding sentence. This ignores dependencies between mentions in the same document and can lead to inconsistent predictions, especially when the same concept appears under different surface forms. We introduce LongBEL, a document-level generative framework that combines full-document context with a memory of previous predictions. To make this memory robust, LongBEL is trained with cross-validated predictions rather than gold labels, reducing the mismatch between training and inference and limiting cascading errors. Experiments on five biomedical benchmarks across English, French, and Spanish show that LongBEL improves over sentence-level generative baselines, with the largest gains on datasets where concepts frequently recur within documents. An ensemble of local, global, and memory-based variants achieves the best results across all benchmarks. Further analysis shows that the largest gains occur on recurring concepts, suggesting that LongBEL mainly improves document-level consistency rather than isolated mention disambiguation.
Recent advances in image restoration have greatly improved global image fidelity, producing visually plausible results across most regions of an image. Nevertheless, even high-quality restorations often exhibit localized failures, including artifacts in semantically important regions such as faces and text, structural inconsistencies, and texture mismatches. Although these errors typically affect only a small portion of the image, they often dominate the overall perceptual quality of the result. In this work, we propose Failure-Aware Image Restoration (FAIR) to address the "last-mile" problem in image restoration. Rather than applying one uniform generative prior over the whole image, we condition a single-pass restoration model on both where local failures are likely to occur and what corrective guidance each region requires. This region-bound conditioning enables fine-grained and controllable restoration that improves semantic accuracy and stylistic consistency in critical regions while maintaining faithful, high-quality restoration elsewhere. Our method complements existing restoration pipelines by shifting the emphasis from global fidelity to local perceptual acceptability. Extensive experiments show that the proposed approach resolves common failure cases and improves perceptual quality, bridging the gap between technical accuracy and practical usability.
Post-training quantization (PTQ) is the standard way to run modern diffusion models on memory-constrained accelerators, yet every existing diffusion PTQ scheme fixes the $\mathit{number\ format}$ in advance and only tunes the scale, zero point, or per-layer bit-width. At a fixed bit-width the best format depends on the distribution being encoded, and that distribution differs across weight channels, across layers, and along the diffusion timestep, where activation distributions slide from heavy-tailed and noise-dominated to tightly clustered and structured. We propose Chameleon, a PTQ framework that holds the bit-width fixed and treats the format itself as a discrete variable, chosen per weight channel and per activation layer, optionally refined per timestep bucket. Activation formats come from {INT8, FP8 E4M3, FP8 E5M2, MXFP8, MXINT8}, selected ahead of time from two cheap statistics (empirical kurtosis and the closed-form diffusion SNR) and stored in a lookup table; weight formats come from {INT8, MXINT8} at 8 bits or {INT4, NF4, FP4 E2M1, MXINT4, MXFP4} at 4 bits, selected offline by reconstruction error. An architectural fork adapts the same selection layer to multi-step UNets, single-step distilled models, and Diffusion Transformers. Most of the gain comes from the per-layer choice; the timestep refinement helps mainly at 6-bit activations. Across SDXL, SDXL-Turbo, and PixArt-$α$ on COCO-2014, Chameleon achieves the best FID in all six backbone $\times$ bit-width settings, with CLIP within 0.24 of the FP16 reference and the best of all quantized methods at $W_{4}A_{8}$. On PixArt-$α$, a real mixed-format kernel runs 1.09$\times$ faster than FP16 end-to-end with 3$\times$ smaller weights.
作者提出 t-SVDM-I 与 t-SVDM-II 的首个分布式内存实现,面向 N 维张量,并用异步非阻塞通信优化数据重分布与关键计算内核。
cs.DC
查看原文摘要
The star-M tensor algebra generalizes the optimal compression guarantees of the matrix singular value decomposition (SVD) to higher-order tensors. The t-SVDM-I decomposition is computed using a set of invertible transformations and slice-wise truncated SVDs with a prescribed rank, and its adaptive, multirank variant t-SVDM-II can determine slice-wise ranks to satisfy a prescribed error tolerance. Existing implementations of these algorithms are limited to shared-memory environments, restricting their applicability to modern large-scale datasets. In this work, we present the first distributed-memory implementations of t-SVDM-I and t-SVDM-II, which are generalized to N-way tensors. To address computational and communication bottlenecks, we design asynchronous, non-blocking communication strategies for efficient data redistribution to obtain highly efficient key computational kernels. Strong-scaling experiments demonstrate the efficiency and scalability of our approach (at least 70% parallel efficiency on up to 128 nodes, or 6144 cores), and we apply the star-M compression techniques to a set of application datasets of size up to 768 GB.
Fault-tolerant quantum computation requires a classical decoder fast enough to process syndrome measurements at the rate at which they are generated, and to return its decisions with low latency. This is most demanding for superconducting processors, whose fast syndrome cycles force a trade-off between decoding speed and accuracy. Decoders fast enough to keep up sacrifice accuracy, which must be compensated for with larger codes and thus additional physical qubits. Here we introduce Rapids, a streaming neural decoder that is both fast and accurate. We achieve this by co-designing the decoder with a field-programmable gate array (FPGA): the network is built from operations that map cheaply onto the device and trained in its integer arithmetic. For the distance-19 surface code, Rapids decodes each round of syndromes in under a microsecond on a single FPGA, fast enough for superconducting processors, and returns its decisions with the low latency that fault-tolerant algorithms require. Its logical error rate is 240 times lower than that of existing real-time hardware decoders. The same design extends to the color code and the [[144,12,12]] bivariate-bicycle code, on which our decoder is 16 times more accurate than the real-time Relay decoder. We further show that the decoder scales: spread over several FPGAs or hardened into custom silicon, it becomes faster, more accurate, or able to decode larger codes. Classical hardware thus becomes a further resource, alongside qubits, that can be scaled to improve fault-tolerant quantum computers.
Embodied intelligence aims to let robots perform complex physical tasks with human-like adaptability and reliability, which requires three complementary capabilities: history-based cognitive reasoning, precise and timely physical execution, and the composition of reasoning and execution through environmental feedback. Yet existing benchmarks either evaluate reasoning and execution within the same tasks or assess them separately without their composition, so they reveal little about whether a failure comes from reasoning, execution, or their composition. We introduce Mind2Act World, a diagnostic benchmark of 30 simulated manipulation tasks from five real-world application domains. Each task has three difficulty levels and two scene settings (Clean and Random), yielding 180 configurations. The tasks form three views: Mind tests decisions based on past observations, Act tests precise and timely execution, and Mind2Act combines both in closed-loop tasks where action outcomes guide later decisions. Comparing the three views shows whether a system lacks a capability or fails to compose capabilities it already has. A diagnosis harness further attributes the failed episodes of three representative systems to Mind, Act, or their composition and summarizes each system in a profile card. Our evaluation of multimodal agents, vision-language-action models (VLAs), and world-action models (WAMs) shows that competence in a single view does not carry over to Mind2Act tasks. Even the strongest agent succeeds in 52.7% of Mind and 39.0% of Act episodes but in only 12.0% of Mind2Act episodes. The strongest agent retains task state but struggles with sustained contact, whereas end-to-end policies execute practiced motions but retain little task state. These findings point to composing reasoning and execution through environmental feedback as the main open problem.
Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines -- TF-IDF features and linear classifiers -- because the textual feature is often the object of study rather than a means to prediction. Yet these pipelines inherit preprocessing defaults from mid-century information retrieval that were never validated against classification accuracy. The most entrenched of these is stopword removal. This study introduces an exhaustive single word ablation that measures the effect of a preprocessing step directly against the downstream objective, and applies it to stopword removal as the hardest case to dislodge. Matching Supreme Court Database labels to Caselaw Access Project opinion texts, the study examines two binary tasks that bracket F1 headroom, ideological direction (no-removal baseline F1 ~0.68) and constitutional versus non-constitutional law type (~0.92), across 7,668 and 7,001 opinions. For each task, the ablation removes each of about 18,500 candidate words in turn, and a task-specific stoplist is built from the measurements. Common generic stoplists fall below the no-removal baseline in all twelve held-out tests. The task-specific stoplists move held-out F1 by +0.0023 (95% CI [-0.0124, +0.0170]) on ideology and by +0.0001 ([-0.0082, +0.0085]) on law type. Neither task shows a detectable benefit from removal, and supplemental analysis finds that word-level statistics predict removal effects poorly, because true removal effects differ by less than the measurement can register, leaving little to predict. The method generalizes to any inherited preprocessing default; the result is a caution specific to interpretable legal text-as-data, where a step that reshapes which features a model sees can distort the doctrinal and ideological signal the research is meant to recover. The burden of proof sits with removal.