Manish Jha, Jialin Qian, Michael Weber, Baozhong Yang
原文摘要
Using generative AI, we extract managers' economic expectations from over 120,000 corporate conference call transcripts. The resulting AI Economy Score predicts GDP growth, production, employment, and wages five or more quarters ahead, beyond survey forecasts and other existing measures. Industry- and firm-level scores capture sector- and firm-specific activity, and a composite of firm, industry, and macroeconomic expectations further improves forecasting power and horizon. Predictability concentrates among historically more accurate, less biased managers, consistent with an information rather than a noise channel. Managerial expectations thus offer incremental insights into economic activity, with implications for macro- and microeconomic decision-making.
Johan Mathe, Adele Myers, Simon Mataigne, Nina Miolane
原文摘要
Many machine learning tasks are invariant under transformations such as translations and rotations. The $G$-bispectrum is a complete invariant that determines a signal up to a group action, but its computation is costly and existing implementations each cover a single group. We present bispectrum, an open-source, fully unit-tested PyTorch library providing efficient, differentiable selective $G$-bispectra for seven group actions. Selectivity reduces the number of coefficients from $O(|G|^2)$ to $O(|G|)$ for finite groups, from $O(m^{5/2})$ to $O(m)$ for planar rotations on the disk with $m$ harmonics, and from $Θ(L^3)$ to $Θ(L^2)$ for spherical 3D rotations using our augmented selective spherical bispectrum at band limit $L$. The library is invariant up to floating-point error and computes selective $G$-bispectra in sub-millisecond time on GPU. We evaluate them as pooling layers on PatchCamelyon and OrganMNIST3D against five baselines. Across 46 comparisons, bispectral pooling remains competitive, matching all baselines on PCam and improving on max pooling by 5.0 percentage points on OrganMNIST3D. On Spherical MNIST, our method with an MLP head reaches 95.8% on rotated test digits, matching a spherical CNN at $4\times$ lower latency and coming within 0.3 percentage points of a tensor-product network at $364\times$ lower latency. Selective $G$-bispectra provide fast, competitive invariant layers for finite and continuous groups.
Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typically restricted to pure spatial localization, lacking the high-level capacity to reason about semantic targets or complex social contexts. Furthermore, these models often process individuals sequentially, requiring redundant computations over the same scene image for multi-person inference. While recent Vision-Language Models (VLMs) offer the exceptional semantic reasoning needed to address gaze-related semantic tasks, their reliance on discrete text generation inherently limits precision in continuous spatial tasks like gaze localization. To bridge this gap, we propose OmniGF, a unified vision-language framework that adapts foundational VLMs for highly scalable multi-person gaze reasoning. The model adopts a dual-branch decoding strategy: a structured language branch generates discrete reasoning states, while a continuous spatial branch directly taps into the VLM's dense hidden states. Supervising these extracted representations with high-resolution gaze target heatmaps effectively overcomes the spatial bottleneck of text-only coordinate generation. Furthermore, to explicitly ground the model in multi-person scenes, we augment the input with head embeddings encoded from cropped head images, providing fine-grained appearance and orientation cues for all individuals simultaneously. By modeling all individuals and leveraging the strong semantic capability of VLMs, OmniGF seamlessly integrates precise spatial gaze target estimation, semantic gaze prediction, and complex social gaze reasoning. Extensive experiments demonstrate that our framework establishes new state-of-the-art performance across multiple standard benchmarks. Code is available at https://github.com/cvlab-stonybrook/omnigf.
Ajay Manicka, Karim Kadry, Sebastian Ruiz-Lopera, Maryam Alsharqi, Sanjana Arji, Samuel Ruiperez-Campillo, Nestor Uribe-Patarroyo, Brett E. Bouma 等 10 位作者
原文摘要
Medical images encode intrinsic tissue properties that indicate disease progression, yet these properties remain entangled with the system-dependent physics of image formation. Differentiable inverse rendering asks whether they are recoverable by inverting the imaging system's forward physics rather than through post-hoc correction. We address this in optical coherence tomography (OCT), focusing on the optical attenuation coefficient, a per-pixel marker of pathology and cellular composition. Conventional recovery relies on closed-form inversions limited to simplified light-tissue models, or learned methods coupled to specific imaging configurations. We instead recover per-pixel attenuation from a single OCT image by gradient descent through a differentiable physics-based forward model. We verified the method against analytical solutions, validated it on five in vitro phantoms, and applied it without modification to 29{,}269 clinical intravascular OCT images from 128 patients. The inversion needs no training data or segmentations and is portable across platforms and retrospective archives. Replacing the forward model or recovering another optical parameter leaves the optimization procedure unchanged. We demonstrate per-pixel recovery is tractable because gradient information scales to this high-dimensional problem, where gradient-free methods become intractable. Our work supports quantitative tissue characterization from OCT images and provides a framework for extension across imaging modalities and organ systems.
Mariela Talavera-Muñoz, Cecilia Diana-Albelda, Miguel Antonio Sampedro-Nuñez, Victor Rodriguez-Laval, Jesus Bescos, Álvaro García-Martín
原文摘要
Gastroenteropancreatic neuroendocrine tumors (GEP-NET) lack prognostic biomarkers, and computed tomography (CT)-based body composition radiomics at the third lumbar vertebra (L3) is a promising candidate. Small cohorts make high-dimensional radiomic models prone to overfitting and single-split evaluations variable and optimistic. This methodological study proposes a four-step validation protocol for radiomic survival analysis in small cohorts: (1) false discovery rate (FDR)-corrected feature selection, (2) a dual-path comparison of prior feature selection versus embedded regularization, (3) repeated nested cross-validation (CV) and (4) a negative control with Gaussian noise features. In 78 GEP-NET patients, 535 radiomic features from five L3 compartments were used to evaluate five survival models with Harrell's concordance index (C-index), time-dependent area under the curve (AUC) and integrated Brier score (IBS). Step 1 selected at least one feature in 18% of outer folds under noise (nominal level 20%) versus 84% with radiomic features. The dual-path comparison showed no consistent difference between strategies. Repeated nested CV reduced variability across seeds (41% median reduction in C-index standard deviation), but not enough to distinguish models. The nested CV C-index exceeded chance by 0.07-0.15 with radiomic features but not clearly under noise (0.40-0.42 with prior feature selection, 0.47-0.55 with embedded regularization). Frequently selected features tentatively linked greater subcutaneous fat, skeletal muscle compactness and texture to better prognosis. These findings suggest a modest prognostic signal in L3 radiomics, with considerable uncertainty that the protocol quantifies. The protocol may transfer to other small-cohort radiomic survival studies. Code: https://github.com/marielatalaveram/radiomics-survival-validation-protocol.
Walid Elbarz, Mohamed Bourriz, Vincent Simonneaux, Hamd Ait Abdelali, François Bourzeix
原文摘要
Recent geospatial foundation models have introduced a new paradigm for large-scale Earth observation by providing pretrained embedding representations that can be directly exploited for downstream tasks. In this work, we investigate the use of Google AlphaEarth Foundations embeddings for national-scale crop type mapping in Morocco. The proposed workflow operates directly on publicly available 64-dimensional pretrained embeddings using lightweight downstream classifiers, eliminating the need to process raw satellite imagery during model training and inference. The approach targets three crop categories, namely winter cereals, tree crops, and other crops. For nationwide inference, the Fields of the World global field boundary map is used to constrain predictions to agricultural parcels, enabling efficient large-scale mapping. Experimental evaluation on an independent test set over ten repeated runs achieved an average classification accuracy of (87.17 +/- 0.42%). Nationwide inference over Morocco was completed in approximately five hours, with the dominant computational cost arising from cloud-based retrieval of the embeddings rather than model execution. These results demonstrate the potential of pretrained embedding representations for computationally efficient national-scale crop type mapping.
Hasaan Ahmad, Qizhen Ying, Yuxuan Sun, Tianjin Huang, Guangming Wang
原文摘要
A world model predicts how a scene changes after an action, and a planner uses it to search for actions that reach a goal. If the camera moves or the controller changes, the same command moves the robot differently: when its commands are turned by 90 degrees, a frozen planner with the LeWM world model that succeeds in 77.5% of episodes succeeds in only 7.8%. Current fixes retrain the model, need training data, or forget a set-up when it returns. We propose Library of Hands (LoH), a training-free method that keeps the world model frozen and corrects only the map from commands to applied actions, which we call the hand. LoH reads the hand through the frozen model, with no extra sensor: it finds the action that best explains the change between two camera images (a reading). It stores every hand it identifies, so a returning set-up is recognised rather than re-learnt. In closed-loop tests, LoH more than doubles success on three simulated tasks, from 28.6% to 62.3%, and loses only 0.6 percentage points when nothing changes. It also works, unchanged, with two other world models and on two of three models pretrained on real robot data, and its gain grows with the quality of its readings.
Vision-language-action (VLA) models are trained as general-purpose foundation models for robot learning, and require fine-tuning for each downstream task and robot. This raises practical questions such as how much data and training updates are needed, how checkpoints should be selected, and whether simulation can be leveraged to alleviate the cost of real data collection. We study these questions on a task that requires both precise manipulation and spatial understanding of the scene. In this task, an SO-101 arm moves a chess king between two squares that are given only by their names, such as e4 and a5. We fine-tune $π_{0.5}$ with various dataset sizes and update budgets, using teleoperated demonstrations as well as simulated demonstrations from a randomized scripted expert that imitates the variability of human demonstrations. In simulation, the success rate scales with both data and updates. Importantly, we find that a short learning-rate cool-down adds up to 31 points and is necessary for comparing checkpoints, and that validation loss and action error are unreliable for model selection. On the real arm, we fine-tune on up to 256 teleoperated demonstrations and evaluate ten policies in 25 trials each. Partial results indicate that pretraining on the simulated demonstrations helps substantially, most clearly when real data is scarce. We also present a negative result, in which training on the policy's own rollouts with filtered behavior cloning, RECAP-style advantage conditioning, corrections from an automatic coach, or residual reinforcement learning did not yield a measurable improvement over plain behavior cloning in our setting. We release the simulator, the expert and the real demonstrations.
Marcus Armstrong, Navid Ayoobi, Pradham Mummaleti, Alexander Chulzhanov, Arjun Mukherjee
原文摘要
Interpretability tools are usually built for one model at a time: a refusal direction, a truthfulness probe, or a steering vector is found with labeled data inside the model it explains. We ask whether such tools can be carried to other models through a map between residual streams fit only on unlabeled prompts. We transfer a refusal direction, tested causally by addition and ablation, and two read-out tools, a correctness direction and a sentiment probe, across 110 pairs of models from five families and 1B to 72B parameters and between base and instruction-tuned models, with controls for specificity and five seeds. How much transfers depends on what the map was fit on. A map fit on ordinary questions recovers 54\% of the target's own refusal steering and 16\% to 77\% of its correctness gain; adding unlabeled prompts from the region where the tool operates raises these to 102\% and 88\% to 98\%, while control directions recover at most 1\%. We prove that a linear map behaves this way whenever two models correspond linearly on the data it covers, and a label-free coverage score derived from this result tracks recovery across more than 16,000 runs and explains earlier reports that maps between models fail across domains. Carried read-out tools outperform anything the target's unlabeled representations yield. Interpretability results, once found, can be reused across models at the cost of a few unlabeled prompts.
Scribble-supervised segmentation is typically evaluated with a fixed annotation set, leaving robustness to distinct semantic and geometric imperfections poorly understood. Motivated by an audit of 12,031 manual PASCAL Visual Object Classes (VOC) 2012 scribbles and prior work, we introduce six controlled perturbation operators. Class corruption, spatial offset, and directional perturbation directly operationalize audit signals. Stroke-length reduction is motivated by prior scribble studies, while random dropout and fragmentation serve as diagnostic controls. Each operator reports requested and achieved changes. We evaluate manual and automatic scribbles across two image domains, two principal backbone settings, and multiple training pipelines, with an additional MiT-B1 PFA anchor evaluation. In the five-seed Tree Energy Loss (TEL)-ResNet101 VOC study, mean intersection over union (mIoU) drops from 70.08 to 1.46 under class corruption, compared with 35.57 for spatial offset, 52.20 for directional perturbation, and 63.24 for stroke-length reduction at their strongest settings. At the evaluated endpoints, semantic-anchor corruption produces the largest degradation, while geometric and support responses depend on the pipeline and dataset. Our benchmark provides a reproducible protocol for diagnosing annotation robustness beyond clean-set accuracy. The operator code is available at https://github.com/Wmhiram99/scribble-operator-benchmark.
Large Reasoning Models (LRMs) have shown excellent performance in reasoning tasks using long Chains of Thought (CoTs). However, this has also led to a significant increase of computational costs and the generation of verbose output, a phenomenon known as overthinking. The tendency to overthink is often exacerbated by Reinforcement Learning (RL) algorithms such as GRPO/DAPO. In this paper, we propose BFS-PO, an RL algorithm which alleviates this problem using a Best-First Search exploration strategy. Specifically, the reasoning chains generated at training time by BFS-PO are organized into a search tree, within which the shortest correct sequence is selected as the best and expanded using a backtracking mechanism based on maximum entropy nodes. In this way, we bias the exploration of the solution space towards the search for increasingly shorter solutions, training the LRM to generate progressively more concise answers. Using different benchmarks and base LRMs, we show that BFS-PO can simultaneously increase the LRM accuracy and shorten its reasoning chains.
Muhammad Moazam Azeem, Abdul Rehman Khan Tareen, Muhammad Obaid Ullah
原文摘要
This paper presents a GPS-triggered geofencing and enforcement scheme that integrates real-time satellite positioning with Software-Defined Radio (SDR) based RF jamming to detect and neutralize unauthorized unmanned aerial vehicle (UAV) boundary violations. Conventional geofencing depends on onboard GPS and cooperative flight firmware. The proposed approach instead moves enforcement to a ground base station, so the response does not depend on the UAV. An ESP32- WROOM-32 microcontroller paired with a u-blox NEO-6M GPS receiver streams telemetry over Wi-Fi to a Python/GNU Radio base station. There, a lightweight Haversine boundary-violation algorithm computes the great-circle distance between the UAV and the geofence. This distance drives a piecewise-linear adaptive speed and altitude control law. The law progressively decelerates and descends the UAV inside a 1 km warning zone and brings it to a complete halt at the boundary. If the boundary is breached, a HackRF One SDR escalates to band-limited noise jamming of the 2.4 GHz control link. The hardware stack was integrated on a GoolRC S116 quadrotor with an end-to-end enforcement latency of about 1 s. Field trials achieved 95% disconnection accuracy within a 50 m radius, and u-center NMEA analysis confirmed sub-2-meter GPS positioning precision. Simulation over an 8-sector, 50 km geofence model confirms speed and altitude-invariant boundary enforcement for cruising speeds of 5 to 50 m/s and cruising altitudes up to 100 ft. A comparison against a PID baseline shows that the proposed law guarantees overshoot-free shutdown at the boundary without gain tuning. It also runs in constant time, which makes it well suited to low-cost, resource-constrained embedded platforms.
Direct communication between AI systems relies on natural language as an intermediate layer, incurring encoding/decoding overhead, token cost, and latency. We ask whether internal activation states can instead be transferred causally between different large language model (LLM) architectures via a learned projection, evaluated at three levels: representational similarity, cross-model retrieval from projected states, and end-to-end causal transfer via activation injection during generation. Using four architecturally diverse open-weight models (Qwen2-0.5B, Phi-3-mini, Mistral-7B, FLAN-T5-base), we find that representational alignment in trained models exceeds a random-initialization null baseline and is best captured by a rank-based metric (mutual k-nearest-neighbour alignment), more robust to activation-magnitude outliers than centered kernel alignment (CKA) or Procrustes analysis. A learned projection network retrieves the correct target-model representation from a held-out set well above chance for the three causal decoder-only model pairs (45-50% top-1 accuracy vs. 5% chance) but at chance level for the encoder-based FLAN-T5. Injecting projected activations into a target model during generation produces a statistically significant, pre-registered causal effect on retrieval-based output similarity for only one of the three decoder-only pairs (Qwen2-0.5B to Phi-3-mini: 23.3% vs. 0.0% under negative control, p=0.047, FDR-corrected); the two pairs targeting Mistral-7B show no such effect despite comparable representational alignment at the hidden-state level. We interpret these results as evidence for causal transfer of the representational vehicle, not of meaning, and conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
This paper introduces a geometric approach to the representation and learning of time-variant parametrizations of deep assignment flows, for binary data labelings on graphs. Each edge carries an optimally controlled parameter flow in a 2-dimensional totally geodesic submanifold, based on objectives derived from a non-local linear scale space representation of the input data. The aggregation of triplets of such flows in 5-dimensional totally geodesic submanifolds is learned from data. The fusion of these flows determines the trajectory in the high-dimensional symmetric parameter space and by geometric integration the layers of binary deep assignment flows. Numerical results demonstrate the expressivity and the limitation of our highly parallel geometric local synthesis approach to high-dimensional deep assignment flow parametrizations.
Yingjie Wang, Yi Dong, Edmund Lau, Jie Meng, Taylor T Johnson, Xiaowei Huang
原文摘要
Rare events govern the safety profile of modern AI systems, yet their probabilities are extremely difficult to estimate: direct Monte Carlo requires prohibitive sample budgets. Subset Simulation (SS) addresses this by decomposing a rare-event probability into moderate conditional probabilities over nested intermediate events. However, classical SS requires a handcrafted scalar performance function whose sublevel sets define those events, demanding detailed knowledge of the failure geometry and limiting transfer to new domains. We propose SCARCE (Scalable Cascade Analysis for Rare-event Characterisation via Embeddings), which replaces the performance function with learned latent representations and geometric rulers that score proximity to failure regions. Adaptive thresholding constructs nested intermediate events directly from data. We formalise SCARCE through a non-negative supermartingale, yielding a high-probability upper envelope that remains valid under early stopping. On MNIST misclassification, where dense Monte Carlo provides ground truth, SCARCE achieves approximately 400--500 times lower mean absolute error than grid-searched traditional SS while eliminating systematic over-counting. We then study PAIR-style LLM jailbreaks under a fleet-level threat model with adversarial fraction $η$. On Llama-Guard-3-8B hidden states, a PCA-based ruler attains 2.6% mean relative error for $η\geq 10^{-3}$ against finite-sample references whose average bootstrap relative half-width is 27.9%, and transfers to a GCG-style corpus with 2.93% relative error after recalibration. A directional criterion $\mathrm{KL}(p_{\mathrm{good}}\,\|\,p_{\mathrm{bad}})$ ranks rulers consistently with estimation error (Spearman $ρ=0.83$).
Predicting the runtime of noisy quantum circuit simulations is important for scheduling, resource allocation, and performance optimization. However, accurate prediction is challenging because backend-aware transpilation can substantially alter the original circuit structure, while the backend-derived noise model and simulator execution behavior can introduce additional runtime variation. We study the effectiveness of graph neural networks (GNNs) and conventional regression methods in predicting Qiskit Aer simulation runtime measured after transpilation. We construct a dataset from a benchmark pool of 1,402 unique circuits spanning 22 circuit families, two Qiskit fake-backend configurations, and four transpiler optimization levels. Specifically, we compare a source GNN using original circuit information, hybrid GNN combining source-level graph with post-transpilation features, and transpiled GNN using only transpiled circuit information, along with five regression models. In the overall-model setting, the transpiled GNN achieves the strongest performance among the graph-based representations at all four optimization levels, obtaining $R^2$ values of 0.974, 0.713, 0.745, and 0.605 for optimization levels 0 through 3, respectively. However, under backend-specific evaluation, the advantage of GNN decreases, with conventional regression models matching or outperforming the GNNs in several settings. These results indicate that post-transpilation information is useful, while the value of explicit graph modeling depends on the backend and optimization level.
Shuyuan Hu, Deng-Ke Wu, Yifan Jin, Qianhang Luo, Mingchen Ju, Kai Ye, Bo Zhao
原文摘要
A bimanual demonstration specifies both what the robot should do and one particular schedule for when each arm should act. Standard imitation learning does not distinguish task-required cross-arm constraints from incidental scheduling choices, and may therefore exploit opposite-arm progress as a shortcut cue, creating spurious cross-arm coupling even where relative timing is irrelevant for the current task phase. We introduce Constraint-preserving Temporal Recombination (CTR), a training-time data intervention that preserves recorded arm-local sensorimotor content while retiming the corresponding segments to realize admissible schedules that preserve task-required cross-arm constraints. We use CTR to train Diffusion Policy, Action Chunking with Transformers, and $π_{0.5}$, and evaluate them on four simulated and four real-robot tasks. Across six real-robot bimanual progress-state initializations, CTR raises worst-state success from 56% for the strongest non-CTR schedule mixture to 76%. With $π_{0.5}$ on an Independent task, a 4 s pause transfers 2.56 s of delay to the opposite arm under the Concurrent schedule distribution, but only 0.25 s with CTR. On real robots, CTR violates task constraints in only 0--4% of trials, versus 36--98% for narrow-schedule baselines. Code will be released at https://github.com/MINT-SJTU/CTR.
Trade promotions consume a large share of consumer-goods revenue, yet most planners still set discounts with a single, often unreliable, price elasticity per item. We present an end-to-end Trade Promotion Optimisation (TPO) system built as one chain: analogue SKUs, point elasticity, elasticity curve, price recommendation, promotional lift and net lift. Elasticity is measured at post-promo time from directional price-dip events against a rolling regular price, and at promo time by a causal estimator that residualises trend, seasonality and promotion, handles stock-out censoring with a Tobit likelihood and updates itself from the first clean promotion week. Items with weak evidence borrow the point elasticity and the curvature from analogue SKUs chosen by a cross-validated ridge model over category, brand, sub-category, price line and description. The optimiser separates self-price lift from substitution and post-promo dips and adjusts for inventory and trade funding. In a four-week promotion experiment on a 39-SKU consumer brand (mean elasticity -3.06), the plan lifts units by 20.6% and revenue by 6.9% at flat margin. Analogue pooling halves elasticity error relative to hierarchy averaging.
LLM agents can expose private local context (e.g., paths, emails) and credentials (e.g., API keys) as agent observations (e.g., tool outputs, shell logs, and file reads) are appended to provider-bound transcripts. Existing placeholder redaction is brittle: it can miss embedded or cross-turn references, over-redact benign lookalikes, and destroy the structure useful for reasoning. We present SlotGuard, a local transcript boundary that can hide sensitive data while retaining agents' performance. SlotGuard rewrites structural bindings as typed, suffix-aware slots, replaces secrets with format-preserving synthetic values, links cross-turn references with a lightweight session graph, and restores raw values only inside the trusted runtime. On controlled repository-oriented agent transcripts, SlotGuard removes all 20,814 annotated structurally sensitive characters across 9,229 paths and reduces credential leakage to 0.0% across 852 planted values. It remains close to raw-transcript task success across four upstream models, while generic redaction drops to 2.5%. Deterministic transcript rewriting takes a median of 14.424 microseconds per agent turn, excluding the optional semantic detector. The code is publicly accessible at https://github.com/illinoisdata/SlotGuard.
Large language models (LLMs) turn writing into a live exchange between humans and software. We characterize this new medium as a discursive network that treats people and LLMs as equal nodes and tracks how their statements circulate. We define the generation of erroneous information as invalidation (any factual, logical, or structural breach) and show it follows four hazards: drift from truth, self-repair, fresh fabrication, and external detection. We develop a general mathematical model of discursive networks that shows that a network governed only by drift and self-repair stabilizes at a modest error rate. Giving each false claim even a small chance of peer review shifts the system to a truth-dominant state. We operationalize peer review with the open-source \emph{Flaws-of-Others (FOO) algorithm}: a configurable loop in which any set of agents critique one another while a harmonizer merges their verdicts. We identify an ethical transgression, epithesis, that occurs when humans fail to engage in the discursive network. The takeaway is practical and cultural: reliability in this new medium comes not from perfecting single models but from connecting imperfect ones into networks that enforce mutual accountability.
Routing a melanoma case to routine follow-up is a serious action error that diagnostic coverage alone does not rule out. We present Harm-Constrained Risk-Optimal Conformal Prediction (HC-ROCP), a training-free framework that uses frozen classifier probabilities and adds a harm penalty when choosing prediction sets and actions. We test the resulting policies on disjoint calibration splits with multiplicity adjustment. HC-ROCP certifies supported claims, reports descriptive fallback policies, and refuses unsupported subgroup claims. We evaluate these outputs retrospectively on COVID-19 radiographs, ISIC 2019 dermoscopy, and EyePACS-to-APTOS retinopathy transfer. Across ten calibration seeds, HC-ROCP reduces COVID-19 severe-action errors from the exact risk-optimal baseline's 4.68\% to 0.54\%. At a 5\% budget, global claims are certified for COVID-19 and ISIC, but the rare squamous-cell-carcinoma claim is refused. At 1\%, all settings receive descriptive reports. For each budget, we also report the minimum severe-case count needed to pass the global harm gate with zero errors, providing a starting point for further data collection.
Over the past decades, superplatforms, digital companies that integrate a vast range of third-party services and applications into a single, unified ecosystem, have built their fortunes on monopolizing user attention through targeted advertising and algorithmic content curation. Yet the emergence of AI agents driven by large language models (LLMs) threatens to upend this business model. Agents can not only free user attention with autonomy across diverse platforms and therefore bypass the user-attention-based monetization, but might also become the new entrance for digital traffic. Hence, we argue that superplatforms have to attack AI agents to defend their centralized control of digital traffic entrance. Specifically, we analyze the fundamental conflict between user-attention-based monetization and agent-driven autonomy through the lens of our gatekeeping theory. We show how AI agents can disintermediate superplatforms and potentially become the next dominant gatekeepers, thereby forming the urgent necessity for superplatforms to proactively constrain and attack AI agents. Moreover, we go through the potential technologies for superplatform-initiated attacks, covering a brand-new, unexplored technical area with unique challenges. We have to emphasize that, despite our position, this paper does not advocate for adversarial attacks by superplatforms on AI agents, but rather offers an envisioned trend to highlight the emerging tensions between superplatforms and AI agents. Our aim is to raise awareness and encourage critical discussion for collaborative solutions, prioritizing user interests and perserving the openness of digital ecosystems in the age of AI agents.
Instruction-following text-to-speech (TTS) has emerged as an important capability for controllable and expressive speech generation, yet its evaluation remains underdeveloped due to limited benchmark coverage, weak diagnostic granularity, and insufficient multilingual support. We present \textbf{MINT-Bench}, a comprehensive multilingual benchmark for instruction-following TTS. MINT-Bench is built upon a hierarchical multi-axis taxonomy, a scalable multi-stage data construction pipeline, and a hierarchical hybrid evaluation protocol that jointly assesses content consistency, instruction following, and perceptual quality. Experiments across ten languages show that current systems remain far from solved: frontier commercial systems lead overall, while leading open-source models become highly competitive and can even outperform commercial counterparts in localized settings such as Chinese. The benchmark further reveals that harder compositional and paralinguistic controls remain major bottlenecks for current systems. We release MINT-Bench together with the data construction and evaluation toolkit to support future research on controllable, multilingual, and diagnostically grounded TTS evaluation. The leaderboard and demo are available at https://aslp-lab.github.io/MINT-Bench-Demo/
We examine what plan validation and execution reports establish in natural-language robot fleet control. Commands are traced through typed plans, deterministic corrections, fleet coordination and outcome checks in a three-level Robot Operating System 2 implementation with twenty simulated robots. An offline benchmark of 44 cases checks plan structure and selected command requirements. Across five local configurations without a response schema, 70.0-87.3% of responses pass. All runs in a selected 18-run simulation series meet their pose-based task conditions. This series includes two successful repeats that replaced incomplete runs after a software change. Saved plans and logs document duplicate pickup assignments and goal adjustments within the original task zones. Separate formation traces show a structurally accepted plan with the wrong formation shape and a rejected route, and an arrival report that omitted a requested robot after replanning. Carry completion records pickup and subsequent drop-off zone presence for the same robot. The cases distinguish changes to executable actions from changes to the requirements covered by a completion report. They motivate checking the effective assignments, goals and reported outcome against the original command.
Yue Zhang, Jilei Sun, Liqiang Jing, Yijie Wei, Ruohan Yang
原文摘要
Automating printed circuit board (PCB) routing requires coordinating board-level connectivity decisions with geometric execution under strict design rules. Although recent agents can interact with native routing tools, reliable routing on complex boards remains challenging. We present PCBRouteAgent, a multimodal PCB routing agent inspired by how human engineers coordinate global strategy with local execution. A Global Routing Planner combines board images and structured electrical and geometric information to specify connection topology, routing order, corridors, and layer transitions. A Detailed Routing Executor realizes these guides through KiCad's native routing engine and performs bounded local recovery. Unresolved failures are returned as structured feedback, enabling targeted guide revisions while preserving accepted routes. We evaluate PCBRouteAgent on 247 synthetic and real-world boards from four PCBWorld-Bench test splits. It achieves clean-pass rates of 100%, 94.9%, 100%, and 40% on D2, D3-A, D3-B, and D3-C, respectively. On the three real-world subsets, PCBRouteAgent outperforms the best evaluated baseline in clean-pass rate by 13.9, 36, and 10 percentage points, respectively.
Neural texture compression (NTC) stores material textures compactly, but the dominant feature-pyramid design receives no filtering from the GPU texture unit: it learns each material at a fixed UV and level of detail and has no explicit anisotropic-filtering (AF) mechanism. Setting the filter from the footprint aspect ratio alone is not enough: a single input cannot carry both the shape of the footprint and its size, so the image is too blurry near the camera by the same amount at every distance. Our method, AF-NTC, instead conditions the decoder on the same three bounded values a hardware sampler uses: minor-axis scale (LOD), aspect ratio, and major-axis orientation. These drive a tap line along the major axis and a level blend across the minor axis, and we train against anisotropically filtered ground truth. At $25\%$ of a full BC7 mip chain, AF-NTC beats the no-AF trilinear-BC7 baseline on all ten material--scene pairs we compare ($+1.3$ to $+7.6$\,dB), and it is $0.0$ to $3.4$\,dB below the $4\times$-larger anisotropic-BC7, depending on the material.
We determine the maximum number of common zeros in projective space of any set of linearly independent homogeneous polynomials of the same degree, when the degree is smaller than the cardinality of the finite field. This proves the conjecture of Beelen, Datta, and Ghorpade, resolving a longstanding problem on common zeros and determining the complete weight hierarchy of the corresponding projective Reed-Muller codes. The proof uses Green's hyperplane restriction bound, combined with a footprint argument that reduces the problem to the affine case solved by Heijnen and Pellikaan. Wei duality then determines the hierarchy in sufficiently large degrees, recovering the complete hierarchy in every degree for the projective plane. Finally, we prove an upper bound valid in every degree, and conjecture that it is always sharp.
Dake Bu, Wei Huang, Andi Han, Si Wu, Hau-San Wong, Qingfu Zhang, Taiji Suzuki, Atsushi Nitanda
原文摘要
Discrete diffusion models admit many token orders, yet most systems rely on confidence-based decoding. Confidence is a strong and efficient heuristic, but it can be myopic because local certainty does not measure a position's effect on terminal quality. We introduce DPRM (Doob h-transform Process Reward Model), a plug-in token-ordering module induced by a terminal-reward-tilted trajectory distribution. The Doob transform converts terminal reward into a process reward for each candidate position. A compact estimator indexed by generation progress, confidence, and optional positional or task state makes this correction reusable across partial states. DPRM changes only token order; the host architecture, denoising objective, supervision, and token sampler remain fixed. We derive the exact reward-tilted law and bound its shortlist and online approximations. Across nine recent open-source hosts spanning language, multimodal generation, and scientific sequences, DPRM improves reasoning, numeric VQA, visual-codebook ordering, and preference-conditioned generation. Relative to confidence, it improves PUMA GSM8K by 14.6%, Omni-Diffusion CLIP-L/14 by 13.2%, Prism voted accuracy from 82.41% to 83.85%, and RealWorldQA numeric/count accuracy by 8.97 points. Matched scientific gains include 8.3% in DCM nonzero recovery, 15.0% in GenMol QED, and 53.3% in SDPO-DNA total utility. Entropy and random-order controls show that the gains do not come from favoring uncertain tokens indiscriminately. Token-order traces and shared-state interventions instead show how terminal reward can correct a locally confident but globally poor choice. Code is available at: https://github.com/DakeBU/DPRM-DLLM.
Trung-Khang Tran, Tuan A. Hoang, Viet-Hoang Tran, Tan M. Nguyen
原文摘要
Conformal Prediction (CP) provides a model-agnostic framework for constructing finite-sample prediction sets with coverage guarantees and has become a tool for reliable decision-making in high-risk settings. Recent advances have extended Split Conformal Prediction to increasingly complex learning problems, including multilabel, high-dimensional, and functional outputs. In this work, we study CP for Distribution-to-Distribution Regression, a setting of growing interest across many application domains. We show that a naive application of Split CP yields prediction sets that, while marginally valid, are non-interpretable, e.g., lacking a well-defined volume or a tractable sampling procedure, and of limited practical value. To overcome this, we propose a new conformal framework that operates in an orthogonal basis space, producing interpretable prediction sets while preserving coverage guarantees. We further develop an adaptive variant with asymptotic conditional coverage under mild assumptions. Empirical results on synthetic and real-world datasets validate the effectiveness of the proposed approach. The code is publicly available at https://github.com/tuanhacs/conformal_d2d.
Pin-Hsun Lin, Linda Senigagliesi, Eduard A. Jorswieck
原文摘要
In this work, we investigate Maurer-inspired two-way physical-layer authentication. Alice seeks authentication by Bob in the presence of a multi-antenna impersonator, Trudy. Trudy may replace the challenge to Alice, the response to Bob, or both. To create an information advantage, Bob adds artificial noise (AN) to his challenge, and Alice adds spatial AN while forwarding the received mixture. Bob predicts the response from trusted preparation, whereas Trudy observes only a noisy version of the challenge, and Alice's AN interferes with Trudy's preparation reception. Impersonation thus requires matching Bob's fresh randomness beyond the channel consistency checked by public-pilot one-way authentication. For quasi-static Gaussian multiple-input multiple-output channels with time-division duplex (TDD) reciprocity, we derive missed-detection bounds for attacks that replace the authentication challenge, the response, or both. These bounds assume attack-free initial training and preparation and account for estimation error and AN leakage. With equal antenna numbers at all nodes, we show scenarios where the proposed scheme has lower worst-case missed detection than specified one-way tests with/without AN.