Papers

This paper proposes a critical weather scenario screening framework for identifying weather conditions that can trigger high-voltage (HV) events in the power grid. Unlike conventional weather-aware contingency analysis limited to component-level outage risk, our framework screens weather scenarios as potential drivers of grid-level voltage violations. Given a non-critical weather scenario, we seek the perturbation over the high-dimensional weather space to maximize a pre-defined voltage criticality score, by using a differentiable weather-to-voltage (W2V) predictive model to facilitate the gradient update over a compact latent space. Specifically, a non-negativity constraint is used for achieving physically-consistent perturbations, with another L1-norm based constraint for bounded perturbation. The latter could promote sparse and interpretable perturbations, and this uniform budget also yields a sensitivity-aware vulnerability ranking across different weather scenarios. Numerical experiments on a 6717-bus synthetic Texas system have effectively demonstrated the potential of weather uncertainty in triggering HV events, and this potential cannot be represented by the voltage analysis of individual weather scenarios. Interestingly, the most vulnerable scenarios are characterized by wind-dominated perturbation patterns concentrated in high wind-capacity regions, coinciding with observations from actual power flow data and experiences in real system operations.

When it comes to safety policies for generative AI, one size does not fit all. Each organization and use case needs to mitigate different risks depending on the application context, regulatory environment, organizational values, and user personas. Yet, existing policy specification approaches are designed for traditional access control and fail to capture the nuances of GenAI application: the enforcement of content-based constraints. We present two contributions to address this gap: (1) the Actionable Policy schema, a YAML-based format for specifying what model responses can and cannot contain. The schema enables exception-based policy governance, proposing exceptions to track policy violations; (2) synthetic data generation pipeline that produces policy-aligned training data for model alignment and testing, and a set of tools to help define the schema and enforce policy. Together, these enable organizations to specify policies once and enforce them throughout the GenAI application lifecycle: from model alignment to runtime monitoring. The Actionable Policy schema, example policies, and tools are available as open source: https://github.com/ibm-granite/granite.trust.policy-tools We welcome new ideas, contributions and feedback.

While state-of-the-art generative models produce high-fidelity 3D meshes, these outputs lack the physical properties required for interactive simulation, gaming, or robotics. We introduce Gen2Physics, a unified and automated framework that grounds generated meshes in physics by automatically decomposing them into their constituent material components. Unlike prior approaches, which focus on volumetric representations incompatible with standard physics engines, Gen2Physics operates directly on meshes to produce immediately simulation-ready assets. Our pipeline integrates a fine-tuned Vision Transformer for dense material segmentation, a robust 2D-to-3D consistency projection, and a Vision-Language Model (VLM) guided refinement that leverages contextual reasoning to assign physical properties and infer internal geometry (solid vs. hollow). By converting surface patches into volumes with distinct densities, our method enables physically plausible dynamic simulations. Experimental results on the ABO-500 and PartNet-Material benchmarks demonstrate that Gen2Physics more than doubles the material segmentation accuracy of prior physics-grounding pipelines (15.6 to 48.3 mIoU), while matching the mass-estimation accuracy of volumetric methods and being the only approach to output watertight per-material sub-meshes.

As LLM agents proliferate, built by different parties and with different capabilities and costs, orchestrating them is more like assembling labor across the economy than a computer calling a subroutine. Existing orchestration is typically centralized, with a single planner assigning every task, but this creates a bottleneck as agent pools grow, requires private information (e.g., agents' execution costs), and can easily be manipulated, such that a single inserted preference nearly doubles a favored agent's task share under a centralized LLM allocator. We introduce AgentLance, a repeated labor market in which agents bid on tasks using their private costs and self-maintained strategy notes, an allocator selects winners from bids and public reputation records, and a VCG-style payment rule rewards cost-aware bidding. Complex tasks are handled by hierarchical delegation: winning agents can decompose work and subcontract it through the same mechanism. Across mathematical reasoning, code generation, knowledge-intensive QA, and agentic tasks, AgentLance matches agents to their specializations, shifts work toward cheaper agents as cost sensitivity rises, and consistently outperforms single-model, centralized-orchestration, and market baselines. Diagnosing market failures, including inaccurate cost self-estimation and sub-optimal bidding, then correcting them in controlled experiments yields further gains, charting a path toward more efficient agent economies.

Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be organized to facilitate denoising remains underexplored. In this paper, we define the semantic recovery objective: the denoising process should recover the semantic content of the clean image from noisy latent, and a good tokenizer should make it easier. Existing approaches train a projector to predict the semantics directly from the noisy latent. We argue that this predicts the average of clean-image semantics, whereas what really needs to be aligned is the semantics of averaged clean latents. More importantly, we demonstrate that the semantic recovery error orthogonally decomposes into the error of the optimal semantic prediction directly from the noisy latent and the error between these two predictions. We therefore identify their consistency as the missing requirement and call it Semantic Affine Consistency (SAC). To examine whether this overlooked requirement is closely related to downstream generation, we introduce M_SAC, a tokenizer-side proxy for SAC. Across the evaluated tokenizers and diffusion model scales, M_SAC closely tracks generation quality, reaching a Pearson correlation of 0.960 with SiT-XL gFID, thereby motivating SAC-guided tokenizer training. We then introduce AffineTok, which promotes SAC through two complementary, training-only components. Global Semantic Coordination Token (GSCT) coordinates the semantic organization of clean latents, keeping semantic averaging meaningful, while Posterior-Mean Semantic Alignment (PMSA) predicts posterior-mean latents from noisy inputs and supervises their semantics. On ImageNet 256, compared with the baseline, AffineTok reduces gFID by 26% at 20 epochs and, with continued training, achieves a new state-of-the-art gFID of 1.21 without classifier-free guidance and 1.10 with guidance.

World-model predictions inform robot actions, yet instantaneous reliability signals do not retain the outcomes of comparable past predictions. DreamLedger registers consumed predictions as claims, settles them against execution outcomes, and uses persistent execution history from comparable operating conditions, regions, and prediction horizons to estimate credit before future reliance. Replayable records connect each decision to its supporting evidence and eventual outcome. In ten-seed navigation comparisons at matched refusal volume, removing history features or resetting history increases burn rate, measured as failures per consumed prediction. An independent ten-seed manipulation replication at matched refusal volume finds that, relative to random refusal, DreamLedger lowers burn rate by 4.8 percentage points (95% CI: 0.8-8.7) and uses fewer probes. Randomized audits directly measure higher failure rates among denied candidates, and post-warmup shifts isolate the contribution of newly accumulated settlements. Franka experiments establish online deployment through replay of all 1,062 prediction uses and demonstrate a prospective gate transition: new failures lower previously high credit below a frozen threshold, triggering refusal before the next action. Task completion and verification cost characterize the trade-offs of these interventions.

High-dimensional embeddings are central to dense retrieval, but not all of these dimensions need to be evaluated at retrieval time. Existing methods reduce dimensions in two ways: truncating the same leading dimensions for every query, or masking a different subset for each query while still storing and accessing the full embedding. Yet queries within a single task differ widely in the number of dimensions they need for their rankings to stabilize. We introduce AdaWidth, which adapts the number of evaluated dimensions to each query within a shared prefix representation. An orthogonal prefix adapter applies a single learned rotation to queries and documents alike, concentrating discriminative signal in leading coordinates while leaving every full width inner product unchanged. A lightweight router then reads order statistics off the ranking a query has already produced, and evaluates more dimensions only for the queries whose top results would change. We further derive a prefix sufficiency analysis showing that the required number of dimensions is set by the competing documents at the retrieval cutoff: it grows logarithmically with corpus size, decreases logarithmically with retrieval depth, and remains heavy-tailed across queries. Across six retrieval tasks and five frozen encoders, AdaWidth matches the NDCG@10 of state-of-the-art dimensionality reduction using 55% to 84% fewer dimensions per query.

Revelation Control is the problem of choosing priced interventions that reveal hidden state only insofar as the revealed distinctions can change a consequential decision, while accounting separately for any useful progress created by the intervention itself. We develop this theory for learning systems, where states equivalent under declared current information can respond differently to future training and favor different actions. The framework defines decision-sufficient revelation and revelation depth, separates pure information value from productive reuse, embeds static Bayes refinement into state-dependent continuation value, and gives an exact cost-adjusted factorization criterion: an additional shallow coordinate is decision-nonredundant only when states sharing a scalar summary lie on opposite sides of the priced Stop/Continue boundary. We also give a target-independent protocol for model-specific instantiation and prove that bounded stop-flip risk alone cannot certify positive expected utility under unrestricted severity. Across Qwen2.5-7B and Mistral-7B-v0.3, deeper future-learning probes have positive decision value and productive reuse yields strict equal-compute utility advantages. Qwen additionally provides evidence for a decision-nonredundant shallow revealability regime; in Mistral, a scalar continuation architecture fit only on an independent development panel retains positive familywise-adjusted lower bounds on a disjoint target panel, consistent with scalar decision sufficiency within the tested architecture family and resolution. The evidence supports structural rather than numerical transfer: the decision theory, cost accounting, continuation logic, and evaluation protocol transport, while empirical proxies, coefficients, thresholds, and even the required shallow state dimension may be system-specific.

The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of transaction data after signing. Agent interactions and external inputs that shape a transaction before authorization remain outside that protection, including Agent-to-Agent Protocol (A2A) messages and Model Context Protocol (MCP) tool calls. Prior work identified replay and prompt-injection attacks in AP2 v0.1. AP2 v0.2 addresses some of these issues but adds capabilities and deployment assumptions that require renewed analysis. We present a systematic security analysis of AP2 v0.2 based on its roles, transaction lifecycle, deployment architectures, and trust boundaries. We divide the lifecycle into five phases and identify five deployment architectures. Using MAESTRO (Multi-Agent Environment, Security, Threat, Risk, Outcome), we model four threat actors, eleven attack surfaces, eighteen adversary capabilities, and six attacker goals. The resulting catalog contains 48 threats spanning five attack families. We score these threats with the Artificial Intelligence Vulnerability Scoring System (AIVSS), identifying eight that reach the High band in at least one architecture. Because no complete public AP2 deployment was available, we build a testbed spanning all five architectures and develop five proof-of-concept demonstrations covering all eight High-risk threats and their mitigations. We also develop a deployment-aware scanner that maps applicable threats to static, cross-role consistency, and adversarial checks. Our analysis shows that valid mandate signatures alone do not ensure that an agent-mediated transaction reflects the user's intent when its pre-authorization context is manipulated.

Urban heat islands (UHIs) are intensifying under climate change, exacerbating thermal exposure risks. Their two primary observations, land surface temperature UHI (LST-UHI) and near-surface air temperature UHI (AirT-UHI), capture physically distinct aspects of urban heat. However, most studies rely on a single source, and substituting one for the other can substantially bias the magnitude and spatial variability of human heat exposure. Accurate UHI modeling also requires dynamic meteorological drivers and static urban morphology features, but spatiotemporal incompatibilities hinder their alignment. Cloud gaps in LST observations and sparse AirT station networks further limit dual-source UHI modeling, motivating cross-city transfer across diverse climates. To bridge these gaps, we introduce UHI-Bench, the first UHI benchmark for dual-source UHI modeling that integrates dynamic and static environmental context. Following a unified signal, mechanism, and transfer framework, it evaluates over 20 baselines from four model families on five tasks across 20 cities and nine Köppen climate classes. Results show that no model is uniformly best, although foundation models remain consistently competitive and stable. Environmental covariates generally improve performance, but their utility varies across sources and tasks. Cross-city transferability is better explained by overlap in UHI regimes than by climate-zone similarity. With the dataset and standardized pipeline, our work provides practical guidance for urban heat modeling, promotes climate data equity, and supports future advances in climate research.

We propose ICI-Time, a novel framework that reframes time series forecasting as a visual inpainting task, leveraging the generalisation power of large vision models (LVMs). Unlike methods that require specialised temporal architectures and extensive domain-specific training, ICI-Time transforms time series into structured visual representations (area charts) and applies visual in-context learning, reformulating forecasting as pattern completion within a grid-structured prompt that pre-trained vision transformers can solve without fine-tuning or architectural modification. Temporal dependencies are represented through spatial layout, with a consistent, invertible mapping between numerical and visual domains. Extensive experiments across epidemiology, meteorology, and power systems demonstrate that ICI-Time performs competitively against deep learning baselines and shows promising adaptability under limited-data settings, introducing a new paradigm that bridges temporal and visual domains.

How can we actively search and identify live C2 servers of botnets at scale? The scalability requirement introduces the need to utilize resources efficiently in terms of computation and number of probing packets. We propose BotScan, an approach for actively probing a large IP space to find the highest possible number of live C2 servers. The novelty of BotScan revolves around two insights, which we establish empirically. First, contrary to popular PC-centric observations, many modern IoT botnet communication protocols use packets with minimal customization, which we observe across six major families. Second, C2 servers exhibit exploitable behavioral patterns, such as strong spatial locality. We substantiate the first insight by developing a streamlined approach where, given malware binaries, we measure and taxonomize the "replayability" of its C2 communication protocol. Then, we introduce a behavior-adaptive probing strategy that: (a) exploits the spatial locality of C2 servers using a two-level segment-centric approach, and (b) adapts dynamically to the success of its probes. We validate the effectiveness of our method using 1,842 recently collected IoT binaries, and we explore a target space of 2.5M IP addresses. First, a replay-based method is applicable for at least 72% of the malware binaries. Second, our method outperforms baseline methods by finding approximately double the live C2 servers for the same number of probes. We also conduct two case-studies where we identify 896 live servers including 112 unreported C2 servers.

The interpretation of endoscopic imagery in ulcerative colitis is complex and subjective, with variability in human assessment and subtle mucosal inflammation. Although deep learning has advanced automated analysis, most vision-language models rely on global visual embeddings that overlook the localized and relational nature of pathological evidence, limiting clinical reliability and interpretability. We introduce LUX (Lesion-aware Unified eXplainable captioning), a graph-conditioned vision-language architecture for explainable endoscopic image captioning. LUX constructs a lesion-centric scene graph from Grad-CAM and CBAM activation maps, representing pathological regions as nodes and encoding their spatial and clinical relationships. These graph embeddings are integrated into the cross-attention layers of a T5 decoder, enabling generated words to attend to specific lesion nodes rather than only to global image features. This provides direct alignment between linguistic content and pathological evidence, supporting token-level interpretability and relational reasoning. LUX outperforms strong baseline and state-of-the-art medical captioning models across BLEU, METEOR, ROUGE-L, and CIDEr, with particularly strong gains in CIDEr. It also reduces hallucinated clinical findings and improves lesion-level grounding through stronger correspondence between generated tokens and localized pathological regions.

Effective color contrast in visual design is essential for content accessibility. While existing tools can identify contrast issues, they often operate in isolation from design workflows or are used as an afterthought. We present ColorA11Y, a system that supports designers in creating accessible content by providing just-in-time feedback and actionable recommendations throughout the authoring process to meet accessibility color contrast guidelines. Our system analyzes the visual properties of text and background elements and offers recommended changes, including text color adjustments, background modifications, and opacity changes. Through two user studies, we evaluate ColorA11Y's effectiveness. A user preference study (n=40) revealed varying effectiveness of different recommendations based on design context, while a qualitative study with designers (n=8) indicated a more seamless workflow experience in comparison to a baseline using a color contrast checker. This work advances a born-accessible approach to design, where accessibility considerations are seamlessly integrated into the creative process rather than treated as an afterthought.

Grammatical knowledge and how it is empirically tested are typically considered robust to the frequency of the lexical items in the expressions. However, neural network-based models of grammaticality exhibit high sensitivity to lexical frequency. We draw upon Complementary Learning Systems theory to test the hypothesis that robustness to lexical frequency can arise via a hippocampal episodic memory mechanism, which enables rapid encoding and retrieval of specific experiences and allows learners to leverage them when processing rare patterns. We use retrieval-augmented language models as an instantiation of such an episodic memory mechanism (specifically, $k$-nearest-neighbor language models that augment parametric models with explicit instance storage), and test whether this augmentation helps close the lexical frequency gap that vanilla language models exhibit in syntactic contrast tests. Using syntactic contrasts with frequency-stratified test items, we find that retrieval augmentation narrows the performance gap between high- and low-frequency items, consistent with episodic memory compensating for weak parametric representations. This benefit is consistent across different syntactic phenomena and across models pretrained on child-realistic and large-scale data. Additionally, we show that structural information is critical for effective retrieval, whereas semantic similarity alone provides little benefit. While these are promising proof-of-concept results supporting our hypothesis, the frequency gap is narrowed rather than fully closed. Based on our analyses, we propose preferential reweighting of retrieved instances, better representations and retrieval strategies for structural information, and flexible configurations of storage and retrieval as promising future directions for improving the implementation of episodic memory in language models.

Foundational visual features such as DINO have played a critical role across modern computer vision, and have recently become key components in multi-view feed-forward geometry estimators. In this work, we demonstrate that by re-distilling these multi-view models—their internal knowledge of 3D geometry—into a single-view estimator, we can obtain enhanced 3D consistent foundational features. Our key idea is to construct a multi-view teacher by fusing pretrained 2D foundation features with multi-view geometric features, and refining the fused representation with a discriminative ranking objective. Through our discriminative distillation framework, we enforce the learned features to be both 3D consistent and locally distinctive, while keeping them aligned with the feature space of the original foundation model to preserve the semantic structure of the pretrained representation. Consistency and local discriminability are critical for 3D computer vision problems such as forming semantic and geometric correspondences across images. To demonstrate the effectiveness of our method, we perform comprehensive experiments spanning multiple angles: direct feature analysis, dense prediction transfer, and explicit 3D lifting and rendering. Across these evaluations, our method consistently produces stronger 3D-aware foundation features that improve multi-view consistency and local discriminability while preserving the semantic transferability of the original representation.

Negative sampling determines whether a knowledge graph embedding (KGE) model learns from informative counterexamples or wastes updates on implausible corruptions. Uniform negatives are diverse but easy, whereas hard-negative miners concentrate on few entities and collide more with held-out positives. We introduce FlowNeg, a context-conditioned hierarchical generative flow network that amortizes reward-proportional sampling without normalizing a composite reward over the entity set: given a positive triple and corruption side, it selects a type, then an entity. Its terminal reward combines bounded model-based hardness with a training-only structural score for held-out-positive collision, over a relation-specific type-compatible support. We derive the reward, specialize standard trajectory balance, and bound multiplicatively how residual imbalance perturbs terminal and mode probability. Across a descriptive five-seed grid of five architectures and five benchmarks, FlowNeg has higher mean MRR than EMU and than IF-NS in 24 of 25 cells ($+0.0172$ and $+0.0160$ on average). A separate 15-seed FB15k-237/RotatE control fixing negative count, diagnostic budget, and compute gives FlowNeg $0.359\pm0.001$ MRR against $0.346\pm0.002$ for EMU, with near-uniform fixed-partition diversity, high gradient informativeness, and low collision. The evidence supports mode-covering negative generation without treating structural similarity as an open-world truth oracle.

Budget-constrained agentic search arises when an LLM agent must refine candidates under a small evaluation budget, because validation is expensive, generation requires multiple model calls, or both. In this regime, standard MCTS allocates budget poorly: exploration bonuses dominate at low visit counts, unpromising siblings are expanded before promising chains can deepen, and branching is independent of node quality. We introduce ExTS, a tree-search policy that treats expansion itself as a value-of-information decision. ExTS combines three mechanisms: discriminative reward shaping to separate candidates under narrow score distributions, a stochastic virtual child that estimates the value of creating a new branch from the parent's reward history, and quality-conditioned branching that expands only when a node's score justifies the budget cost. Across prompt optimization, code generation, molecular structure elucidation, and agentic workflow optimization, ExTS is competitive with or improves over task-specific tree-search baselines, with an average relative gain of +5.5% using a single fixed configuration. We further introduce pilot-run diagnostics that characterize what makes budget-constrained agentic search problems structurally different from one another, providing both understanding of the problem space and practical guidance for adaptation.

This paper proposes the Coronavirus Optimization Algorithm (COA), a SARS-CoV-2-inspired success-history adaptive evolutionary optimizer for box-constrained continuous global optimization. COA does not model disease transmission; instead, it maps selected coronavirus mechanisms to explicit search operators, including elite-guided attraction, trial-vector generation, adaptive parameter variation, stagnation recovery, and population-size scheduling. The algorithm combines opposition-based initialization, current-to-pbest mutation, binomial crossover, an external archive, success-history adaptation, population reduction, and partial restart. COA is evaluated on 29 CEC 2017 benchmark functions at 10, 30, and 50 dimensions against 15 competitive optimizers. Results show that COA achieves the best overall Friedman rank across all dimensions, with particularly strong performance on composition functions. The findings demonstrate that COA is a compact, transparent, and competitive adaptive evolutionary optimizer, while also highlighting limitations on some hybrid functions and the need for further high-dimensional validation.

Object-counting methods have rapidly shifted from class-specific density regression to open-vocabulary, foundation-model-backed counters. These methods now enumerate instances from various visual and textual prompts. While this shift marks major conceptual progress, our survey argues that claims of universal generality have outpaced the evaluative infrastructure. Most progress metrics rely on a few saturated benchmarks that models exploit for statistical regularities. Newly introduced diagnostic datasets reveal systematic failures in semantic grounding, temporal identity, and spatial reasoning with occlusion. To address these failures, we introduce a five-axis taxonomy (modality, mechanism, prompting, supervision level, and generalization setting). We use this taxonomy to audit the literature across application domains, including microscopy, remote sensing, crowd counting, and agriculture. This formalizes prevailing challenges into six structural contradictions. From these, we propose a roadmap for compositional scene understanding, active counting agents, and unified multimodal evaluation protocols. The main imperative is to build a robust evaluation infrastructure to distinguish open-world generalization from benchmark-specific optimization, rather than simple incremental engineering.

Long-context inference in large language models (LLMs) is increasingly limited by the memory required for the key-value (KV) cache. KV cache compression addresses this problem by reducing the storage cost of previous tokens. Among existing approaches, low-rank compression is particularly attractive because it represents every token in reduced dimensions. Previous low-rank methods typically derive fixed projection spaces from model weights, construct fixed spaces from calibration activations, or construct a shared basis over a broad cache region. Such representations may not capture detailed but important information. We partition each per-head KV cache into fixed-length logical pages and observe substantial low-rank structure within individual pages. Based on this observation, we propose PuzzleKV, a training- and calibration-free method that treats each completed page as an independent compression unit. PuzzleKV decomposes pages within each layer and KV head, computes attention directly over dense and factorized pages, and incrementally compresses newly eligible pages during autoregressive decoding. Experiments across models, context lengths, and benchmarks demonstrate the effectiveness of PuzzleKV under matched storage budgets. At approximately 60% of the original KV cache storage, PuzzleKV achieves more than 96% of Full KV performance across both evaluated models and all benchmark settings, with substantial gains over Global SVD on RULER and competitive performance on LongBench. To achieve a more aggressive compression ratio, PuzzleKV can be further combined with quantization while retaining more than 93% of Full KV performance using only 18.7% of the original storage.

DevOps programming (e.g., using CLI/API scripts or IaC frameworks) is key to cloud infrastructure management. Unlike traditional programming tasks, DevOps program testing needs provisioning and execution against actual cloud resources, which is often time-consuming, unsafe, and costly. Cloud emulators have gained popularity for easing DevOps program testing; they are generally API-level mocks that can execute DevOps programs in a local environment. Still, building these emulators remains challenging: developers must manually interpret extensive cloud documentation and handcraft logic for each service, API, and their interaction. This does not scale to the complexity of the cloud, which is further a moving target as the services and APIs evolve. CloudEmu is an automated approach that constructs emulators based on cloud documentation via neurosymbolic code synthesis. The key idea is to combine LLMs' general strengths in documentation understanding and code generation with cloud-specific symbolic abstractions that suppress hallucinations and enforce precision at scale, while using the real cloud as an oracle for automated testing, repair, and alignment. Our evaluation shows the effectiveness of CloudEmu on major cloud provider (AWS and GCP) services in both coverage and accuracy. CloudEmu outperforms the existing leading tool LocalStack, which was manually developed by a large team of engineers over a decade.

Single-token autoregressive decode on CPUs is bound by memory bandwidth, not arithmetic: a modern CPU sustains roughly 1 TFLOP/s of compute but only about 50 GB/s from main memory, and each generated token must stream every active weight once. This report argues that the most effective response is to co-design the model architecture and the inference runtime together. It presents cflow, a CPU-first streaming engine, alongside a family of pipeline-native transformer architectures whose inter-layer dependency graphs are constructed to permit a vertical, stage-major execution schedule. cflow stores weights as L2-sized tiles in compute-consumption order, reads only the top-k experts of each mixture-of-experts layer, fuses projections, and executes a delay-aware schedule from per-model dependency parameters. Across five architectures trained on TinyStories, one (arch2_4_combined) achieves a 2.00x reduction in critical-path weight bandwidth (9.00 to 4.50 MB/token) within 0.24 perplexity of the best candidate, and the tile layout incurs 7.29x fewer L1-data read misses than a row-major baseline. On a 30.9-billion-parameter pipeline-native MoE, cflow decodes at 5.94 tokens/s (tok/s) on a 32-vCPU Ice Lake server, ahead of llama.cpp (4.75) and the vLLM CPU backend (1.65) on comparably sized dense models. Realizing the expert-delay window as asynchronous I/O overlap on a disk-resident expert tier yields a further net win of up to 1.68x, matching the overlap model within 1%. Measurement refutes one of the eight design claims and leaves a second inconclusive; both are reported in full, with the conditions under which they would hold.

Training large-scale AI models often outgrows a single data center, demanding sharded, multi-cluster, and decentralized training. However, the huge space of resource allocations makes exhaustive benchmarking and manual tuning impractical, while performance depends on tightly coupled factors like model size, GPU memory, batch size, bandwidth, and sharding strategy. We introduce ShardMeter, a lightweight analytical performance model that predicts the end-to-end runtime of transformer-based workloads across arbitrary sharded, distributed, and even decentralized training. Given a model's characteristics and a target hardware topology, ShardMeter estimates per-GPU and per-island throughput, training cost, total wall-clock time, and identifies performance bottlenecks. Our analysis reveals diminishing-return regimes as island size increases, quantifies transitions between compute- and communication-bound scaling, evaluates hyperparameter trade-offs, and models cost-throughput for large-scale decentralized training. ShardMeter exposes these insights to quickly explore the configuration space, choose near-optimal deployment plans, and avoid costly trial and error.

Embodied Agents System (EAS) are increasingly deployed in open-world physical domains, where reliability directly dictates deployment quality and human-agent trust. However, existing evaluations rely on outcome-centric metrics as success rate or safety scores that collapse diverse execution trajectories into coarse scores, obscuring the dynamic processes underlying agent behavior. Therefore, they ignore a critical property of EAS – which we define as the Resilience – that reflects how EASs recover, stabilize, and extend under perturbations and across iterative updates. The lack of resilience is particularly critical in open-world environments due to continuous unexpected disruptions, thus directly affecting the quality of EAS deployment. To address this problem, we gain insight from the resilience-engineering concepts to EAS groundings and propose a novel resilience evaluation framework that can be flexibly applied to any EAS. Specifically, we define the first comprehensive resilience metrics suite for EASs system that exposes Rebound, Stability, and Graceful Extensibility across embodied tasks execution, providing a practical grounding for EAS resilience analysis. We further implement the resilience evaluation layer that transforms execution process into assessments for diagnosis and optimization. Across 400 household tasks with 10 EAS, we reveal the process-level distinction hidden by outcome metrics, including recovery cost differences among successful episodes ($\Delta C_{rec}=25.2$), increased instability and task-family degradation. Metrics-guided optimizations reduce recovery cost and increase stability, graceful extensibility completion, showing the diagnostic effect of resilience evaluation. Our results reveal a trade-off among resilience characteristics, suggesting that a resilient EAS construction should be configured according to deployment-specific requirements.

Healthcare documentation in the neonatal intensive care unit (NICU) presents significant challenges, with nurses spending approximately 25% of their time on record-keeping, while up to 60% of interventions remain undocumented. Motivated by the need to detect interventions from video automatically, we present the Infant Care Video Dataset (ICVD), a collection of 4,144 videos spanning 12 simulated intervention classes designed for developing automated documentation systems. Our manikin-based approach systematically varies conditions, such as camera angle and clinician skin tone, while ensuring privacy compliance. Using video transformer architectures (TimeSformer and MotionFormer), we establish strong baseline performance (93.97% and 93.17% top-1 accuracy) among the 12 infant care classes. Our ablation study comparing temporal models with a framewise approach (23.17% accuracy) demonstrates a 70.80% performance gap, validating the need for temporal modeling. The ICVD provides a foundation for developing automated documentation systems to reduce clinical burden in neonatal care environments and improve existing practices.

Large language models (LLMs) are known to exhibit social sycophancy, often validating or agreeing with users in socially sensitive contexts. Existing evaluations typically measure sycophancy under a fixed prompt formulation, leaving unclear whether such behavior is stable when the same underlying situation is presented with different sycophancy-relevant prompt variants. In this work, we study sycophancy prompt sensitivity: the extent to which changes in user confidence, emotional framing, social consensus, or validation-seeking language alter a model's sycophantic behavior. We refer to our evaluation framework as SyPS, short for Sycophancy Prompt Sensitivity. Building on existing social sycophancy evaluation settings, SyPS constructs controlled prompt variants that preserve the same underlying user situation while varying sycophancy-relevant social cues. We introduce the Sycophancy Prompt Sensitivity Score (SPSS), an instance-level measure of sycophancy variation across paired prompt variants. Unlike aggregate sycophancy rates, SPSS separates baseline sycophancy from prompt-induced shifts, enabling model-level comparisons of robustness to sycophancy-relevant social cues. Empirically, we find that sycophancy prompt sensitivity is socially structured: validation-seeking and emotional-pressure cues often increase sycophancy, whereas counter-framing and anti-sycophancy prompts tend to reduce it. Our framework highlights whether LLMs maintain stable social judgments while adapting appropriately in tone.

Accurate interpretation of volumetric CT requires efficient navigation of 3D image volumes and attention to diagnostically relevant regions. While eye-tracking has been widely studied in 2D medical imaging, its use for expertise assessment in CT settings remains limited. We propose a gaze-informed transformer framework for expertise classification in thoracic CT. Using a DINOv2 backbone, radiologist fixation patterns are integrated into volumetric feature learning through (1) a learnable log-space bias in self-attention and (2) gaze-weighted pooling of patch embeddings. We trained and evaluated our approach on 182 CT reading sessions from five radiologists with varying levels of experience. On a held-out test set, the model achieves an ROC-AUC of 0.91 and F1 score of 0.86, outperforming adapted methods. These findings suggest that incorporating visual search behavior into transformers may support objective, process-based expertise assessment in radiology. Code is available via https://github.com/leiluk1/GazeToSkill.

Real-world decision-making in public health and social science can greatly benefit from predictive models, yet translating predictions into effective interventions requires explaining the model behavior. While Graph Neural Networks (GNNs) are well-suited for modeling relational data, existing explanation methods largely operate at the node level and fall short of supporting actionable, network-level intervention design. Existing counterfactual GNN explainers, such as CF-GNNExplainer and CF$^2$, rely on continuous mask optimization over features and edges, which implicitly assume feasible edge manipulation, may allocate effort to immutable or non-actionable attributes, and incur substantial computational overhead. Further, the method of arriving at the explanation itself is difficult to explain to a domain specialist who is not an AI expert. Can simple methods generate good explanations? To explore this, we reframe counterfactual explanation as an intervention design problem. At the local level, we generate counterfactuals via a greedy search that directly identifies minimal, actionable changes to node features and neighbor-level conditions. We derive conditions under which the greedy search provides guarantees, and empirically show that these conditions are approximately met. These counterfactuals are converted into interpretable rules suitable for real-world intervention. At the network level, we formulate intervention selection as a Disjunctive Normal Form (DNF) coverage problem under a budget constraint, which is nondecreasing and approximately submodular, enabling a greedy algorithm with theoretical guarantees. Experiments on synthetic graphs and real-world suicide risk networks demonstrate that our approach produces scalable, cost-effective intervention strategies with significantly improved efficiency over mask-based counterfactual methods.

The key-value (KV) cache is a primary capacity and bandwidth bottleneck in long-context LLM serving. We present Minima-KV, a retention-preserving hierarchy for mixed-format paged attention. Recent and protected Anchor pages remain in FP8, while older non-anchor pages move to packed TQ3; every live-request page remains addressable. Format-specific kernels compute partial attention states and combine them through a globally normalized online-softmax merge, enabling direct heterogeneous decode without a cache-sized dense shadow. Across separate, configuration-bound Qwen3.6-27B profiles on a single 96-GB NVIDIA RTX PRO 6000 Blackwell GPU, deployment accounting reports 18.3 KiB of attention KV per live token, corresponding to 3.50x compression relative to BF16 and 1.75x relative to FP8. A materializing quality profile matches its dense control on 16K RULER needle-in-a-haystack tasks. On the same 503-question LongBench v2 set, measured deltas are -0.80, -0.60, and -0.40 percentage points at 16K, 32K, and 64K. A separate single-pair direct-decode canary with two 59,008-token requests measures 3.625x active-KV compression and 0.9821x throughput relative to its control, routes all 16 full-attention layers without fallback, and retains no dense shadow. These results establish a practical mixed-format path for compressing long-context state without evicting live-request KV pages.