Papers

Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We propose a belief-shift evaluation benchmark in Werewolf for analyzing communication skills through belief updating. Using LLM-played games, we annotate suspicion and accusation messages and measure how an observing village-side model's beliefs change after each message. We evaluate 40 open-weight LLM configurations on 1,224 annotated messages. Our results show that larger models better distinguish true wolves from villagers based on game history, but accusations still strongly influence their beliefs. Models become more suspicious of the accused target and less suspicious of the accuser, especially when the accuser is trusted, even if the accuser is wolf-aligned. Larger models better resist accusations from accusers they already distrust. Overall, our findings suggest that current open-weight LLMs up to 120B parameters still struggle to integrate accusation content with source trust in strategic communication. Our benchmark and code are available at https://rlg.iis.sinica.edu.tw/papers/werewolf-accusation-benchmark.

Community detection in bipartite networks is a fundamental problem in modern data analysis, with applications in recommendation systems, biological networks, and social network analysis. Unlike conventional unipartite graphs, bipartite networks consist of two distinct types of nodes with edges only connecting across types, so recovering latent communities requires estimating labels on the two node types. The stochastic co-blockmodel is a classical probabilistic framework for such networks, yet theoretical guarantees for exact community recovery in this setting remain limited, especially when the number of communities grows, the community sizes are unbalanced, or the degrees are heterogeneous. In this work, we prove that a simple spectral clustering algorithm based on the diagonal-deleted Gram matrix achieves exact recovery with high probability under mild conditions on sparsity, community balance, and the number of clusters. We further extend the result to the degree-corrected stochastic co-blockmodel, where each node carries its own degree heterogeneity parameter, and show that a row-normalized version of the same algorithm maintains the exact recovery guarantee. Extensive experiments validate our theoretical findings.

Simulated societies of large language model agents are used to study online polarization, and separately to study collective intelligence, but the two are rarely measured in the same system. It is therefore difficult to say whether a society's personality composition shapes both, or whether reducing polarization costs collective competence. We present TraitMix, an experimental design in which the Big Five composition of a simulated social network, both trait levels and trait heterogeneity, is a controlled experimental variable, and in which polarization and collective performance are measured in the same runs. Across 991 simulations of hundred-agent societies, spanning six contested topics and six language models, trait heterogeneity has the largest measured effects, acting in opposite directions on two faces of polarization: varied societies hold more dispersed opinions while being less segregated into camps, so homogeneous societies are not moderate but consensual echo chambers. Trait effects are not additive, as Agreeableness determines the sign of Openness, an interaction that replicates across models although the primary model's estimate is influence-driven. Contrary to the trade-off the study was designed to measure, no polarization measure predicts poorer collective performance, and cross-cutting interaction is the only one of four whose association with collective accuracy survives partialling on the aggregation identity. We report ablations removing two potential measurement circularities, an induction gate applied to every model, and the measures that failed them.

Automated gait analysis requires accurate classification and interpretable outputs. We propose an integrated framework for classifying healthy gait and multiple musculoskeletal impairment groups using bilateral ground reaction force (GRF) and center-of-pressure (COP) signals. The signals were normalized over the stance phase and standardized using training-set statistics. The model achieved a validation accuracy of 99.00% and a test accuracy of 90.07% under a session-level split. Class-specific $\epsilon$-LRP identified positive and negative contributions across both sides, multiple signal components, and different stance phases. Separately, the processed GRF signals and model predictions were synchronized within a Blender-based 3D visualization, enabling sample-level inspection of gait trials and classification results. The proposed framework integrates classification, explainability, and 3D visualization to improve model transparency. The source code is available in the following repository: https://github.com/nyoico/grf-gait-3d-visualization.git

A world model asked what happens if an object is pushed at several speeds produces several futures. If the model has the object in mind, those futures agree about it: each implies the same mass and friction. The consistency checks now used to vet world-action models ask whether a model's futures agree with each other, and none of them knows any physics. We show that this is not enough, and what to do instead. IMPLY reads the physics each rollout implies by inverting a simulator and scores a set of rollouts by how well one object explains all of them, anchored to two calibration pushes the model has observed. In a controlled setting, self-consistency gives a perfect score to a model that ignores the object and always predicts a typical push; anchoring exposes it (AUROC 0.70 versus 1.00). On a real model, V-JEPA 2-AC adapted to the scene, the same thing happens. Given its own calibration pushes the model tracks the object (per-object correlation with the truth 0.91); given another object's, it does not (0.05). Self-consistency cannot tell these apart, preferring the right evidence on 52% of objects, chance level, while anchored disagreement prefers it on 73% and correlates 0.92-0.99 with the rollouts' error. Used to choose among candidate rollout sets, it comes within 0.003 of an oracle that sees the truth. A model that has internalised the wrong object is exactly as self-consistent as one that has internalised the right one; consistency has to be anchored to evidence.

LLM-as-a-judge protocols are commonly debiased by instructing judges to ignore presentation cues such as citation formatting, source labels, and evidence-display style. We show that this intervention can suppress bias while damaging the resolution of the measurement instrument. We introduce TraceJudgeBench, a diagnostic benchmark for auditing citation-like artifacts in RAG and agent-workflow evaluation, covering content-equivalent pairs, citation ablations, correctness conflicts, human-validated soft and moderate quality gaps, prompt-strength ladders, decoupled judging, and a controlled workflow-ranking probe. Across GPT-5.5, Claude Sonnet 4.6, and DeepSeek V4-Flash, stronger anti-citation prompts reduce worse-cited wins from up to 50.5% to 0%; yet some operating points already convert validated moderate-gap decisions into Tie before the strict stress-test endpoint, while correctness-conflict accuracy remains at or above 93.0%. A second, 50-pair FinQA moderate-gap construction reproduces the qualitative frontier, and open-weight Qwen2.5-14B-Instruct-AWQ and Gemma-3-12B-IT runs reproduce the central HotpotQA frontier. TRACE-style decoupling recovers 96.5-100.0% better-plain resolution across the reported settings. Human validation separates three meanings of Tie: correct equivalence Tie, calibrated soft-boundary Tie, and resolution-destroying Tie on validated quality gaps. We frame debiasing as a measurement intervention whose bias suppression, resolution retention, Tie cost, and protocol cost must be reported jointly. The supplementary artifact contains benchmark splits, prompts, raw judge outputs, validation summaries, and analysis.

Even with a fixed dataset and research question, data analysis involves many defensible decisions. Understanding how these choices influence the results is scientifically important but remains challenging. Crowdsourcing and agentic AI can generate hundreds of end-to-end analyses, but scaling generation alone can create a processing bottleneck and an analytic “black hole.” A common workaround is to impose a shared fixed decision taxonomy, which can limit insight and understate uncertainty. We present ForkSCOPE, a human-AI collaboration framework that induces structure bottom-up from the code corpus of end-to-end analyses, without a taxonomy fixed before or after generation, so the organization and evaluation of the garden can scale with the corpus. ForkSCOPE surfaces the charted garden of forking paths through a human-AI collaboration pipeline and an evidence-linked interactive viewer for steering and verification: it spotlights organically identified forks and structures and produces a derived taxonomy and decision map compatible with existing multiverse tools.

Adaptive RAG often uses retrieval-time signals to decide whether another retrieval, reranking, or multimodal step should run. We ask whether these signals add routing value once the query itself is already known. Across document, audio, and video RAG, we compare matched query-only and query+retrieval routers while holding the optional actions, router family, training procedure, and evaluation fixed. On the held-out final evaluation, adding the tested retrieval signals does not produce a reliable routing improvement over the query-only baseline. Some retrieval signals are associated with whether a later step will help, but that predictability does not consistently lead to bet- ter RUN/SKIP decisions. The main lesson is therefore methodological: retrieval-state features should not be credited with routing value unless they improve over a matched query-only control. Our results do not show that routing or retrieval state is generally useless; they show that the incremental value of retrieval signals must be demonstrated rather than assumed.

Long-running LLM agents require memory mechanisms that maintain coherent internal states across interactions. We study a lifecycle-labeled memory setting in which write episodes provide lifecycle metadata during training, and phase-aware readout is used during evaluation. This setting reflects the need to distinguish information that should remain influential across future interactions from information that should affect only the current context. A mismatch between these lifecycles can cause temporary information to overwrite durable knowledge, leading to behavioral drift in persistent agents. Within this setting, we introduce LifeFuse-Mem, a lifecycle-aware neural memory framework that separates information according to its temporal commitment. LifeFuse-Mem uses dedicated memory components and lifecycle-aware updates to allow stable and transient knowledge to evolve locally without converting temporary context into durable state. On the controlled anti-overwrite benchmark, LifeFuse-Mem improves acquisition-controlled retention and reduces temporary overwrite; on two public long-memory benchmarks, it remains broadly competitive. These results suggest that explicit lifecycle signals can help diagnose and mitigate overwrite in compact online memory.

Post-treatment MRI in patients with glioma provides serial observations for updating patient-specific tumor-state proxy estimates, but variable appearances and trajectories complicate forecasting. We formulate forecasting as an observation-aware digital-twin update in which an intermediate observation anchors the patient-specific state. Among 203 patients and 594 follow-up time points, a predefined no-new-treatment criterion retained 120 of 236 candidate triplets, split into 81/24/15 training/validation/test triplets at the patient level. Each time point was represented by a continuous voxel-wise tumor-state proxy map in [0,1] derived from MRI lesion labels. A SegMamba-based single-step forecaster predicted update proposals from multimodal source-state tensors. Observation-Anchored Selective Assimilation (OASA) retained the observed intermediate proxy as the state anchor and selectively applied updates through a validation-selected tiered case-level rule and voxel-wise soft gate. We compared initial-scan forecasting, rollout without assimilation, latest-observation persistence, direct prediction, OASA, OASA + calibration, and morphological dilation. Checkpoints, OASA rules, and calibration thresholds were selected using validation data only. Across three seeds on 15 held-out test triplets, OASA maintained Dice at $\tau$ = 0.2 comparable to persistence (0.6071 $\pm$ 0.0025 vs. 0.6070) while yielding numerically higher Dice at $\tau$ = 0.5 (0.4269 $\pm$ 0.0079 vs. 0.3981), with a small RMSE increase. Calibration increased Dice at $\tau$ = 0.2 to 0.6178 $\pm$ 0.0025, increased false-positive (FP) support (11,836$\rightarrow$18,663), and reduced false-negative (FN) support (22,107$\rightarrow$17,536). This reflects near-threshold support calibration rather than improved biological predictive capability. Code is publicly available at https://github.com/jsudg436/longitudinal-proxy-forecasting.

Due to the highly deformable nature of garments, training a generalizable policy for robotic T-shirt folding and unfolding remains a significant challenge. In this work, we present a large-scale synthetic dataset for robotic T-shirt folding and unfolding, covering 6 robotic embodiments, 1K T-shirts, 1K environmental assets, and 120K episodes with rich annotations, which can be used to train a wide range of manipulation policies. We first follow the FoldNet pipeline to generate a large-scale dataset of physically simulatable T-shirts with diverse appearances and annotated semantic keypoints. Based on these semantic keypoints, we then generate manipulation demonstrations for different robotic embodiments through a unified rule-based framework. We use these demonstrations to train visuomotor policies, and experimental results demonstrate that models trained solely on our synthetic data can achieve over 90% end-to-end task success rates when directly deployed to unseen real-world environments and previously unseen T-shirts from arbitrary initial configurations. Project URL: https://pku-epic.github.io/FoldNetXX/.

Vision-based crack inspection depends on segmentation networks whose reliability depends on the quantity, diversity and label quality of their training data. Pixel-level annotations are costly, and crack images of specific structures are scarce. Generative augmentation can supply additional data, but existing methods address isolated steps. They reuse annotated masks, offer limited control over crack geometry, and adopt the conditioning mask as the label without checking it. This paper presents an end-to-end pipeline that produces labelled crack data without manual annotation and assesses the reliability of these data and of the detectors trained on them. Procedurally sampled Bézier skeletons with guaranteed geometric properties are converted into crack masks by a generative adversarial network (GAN). A dual-ControlNet Stable Diffusion model renders the masks as crack images, either on text-described surfaces or on user-provided backgrounds. An ensemble of segmentation networks trained on real images combines its agreement with the inherited label and its internal disagreement into a pixel-wise label confidence. This confidence weights the training loss instead of removing samples with a threshold. The trained detectors are evaluated with image-space probability of detection (POD) and calibration analyses. On CRACK500 and CrackTree200, the pipeline improves five segmentation networks over conventional, diffusion-based and flow-matching-based augmentation, and on CRACK500 confidence weighting yields a higher accuracy than threshold filtering at every tested threshold. On CRACK500, the crack width that U-Net detects with 90% probability at 95% confidence decreases from 8.0 to 4.3 pixels, and the expected calibration error decreases from 14.2% to 9.6%.

Insecure Direct Object Reference (IDOR), often modeled as Broken Object-Level Authorization (BOLA), remains prevalent in Java database applications because identity and authorization checks at the controller or service layer are disconnected from SQL execution based on resource identifiers. Existing work largely detects these vulnerabilities but offers limited low-intrusion runtime protection for legacy Java-SQL applications. We present IDORacle, a template-guided SQL-sink interception and rewriting framework for preventing horizontal privilege escalation at runtime. IDORacle propagates authenticated identity context across HTTP requests, asynchronous tasks, and data-access boundaries through a server-side trace identifier. At the MyBatis/JDBC boundary, it extracts SQL templates, computes dual fingerprints, and performs one-time template analysis to generate reusable mediation plans. During execution, it combines subject context, SQL ASTs, table metadata, and cached authorization proofs to permit, rewrite, or block operations. Its guard model supports direct ownership predicates, join-derived ownership, probes for group-owned resources, role-sensitive state transitions, and sensitive-column mediation. A Java-SQL benchmark grounded in real-world CVE reports shows that IDORacle prevents the tested horizontal authorization violations with a worst-case guard latency of 0.17 ms. Redundancy-aware optimization reduces average per-instance overhead by more than 90%, to 0.017 ms for hot SQL templates.

Long-horizon language-model agents trained with reinforcement learning oftenreceive sparse outcome rewards that do not reveal which decisions along a tra-jectory deserve credit. Episode-level advantages provide coarse trajectory-widecredit, while step-level comparisons offer finer resolution with context-dependentestimation noise. We propose Granularity-Adaptive Credit Assignment (GACA),a critic-free method that adaptively mixes episode- and step-level credit for eachdecision during policy optimization. GACA normalizes the sampled response'smean per-token negative log-likelihood (NLL) within each trajectory and uses theresulting criticality score to determine the step-specific mixture. The computationreuses rollout log-probabilities without additional training rollouts or model eval-uations. Our analysis characterizes optimal score-dependent mixing and derivesconditions linking expected NLL to a lower bound on the preferred step-levelweight. Across ALFWorld and WebShop with 1.5B and 7B backbones, GACAachieves the highest reported mean success rates among the compared methods,while introducing negligible additional computation.

Lux AI Season 3 requires agents to act under partial observability, randomized episode level dynamics, and a best of five match structure that rewards both tactical execution and fast adaptation. We present HORIZON, a hierarchical agent that combines symmetry aware spatial perception, dual memory belief tracking, relic centric graph attention, information gain driven exploration, and an opponent conditioned policy mixture. HORIZON separates short horizon control from cross match meta reasoning, while auxiliary belief and world model objectives stabilize learning. Trained with PPO in a large scale JAX simulator, the resulting agent explicitly infers hidden game parameters and opponent style. Experiments show consistent gains in match win rate, episode win rate, adaptation gain, and league rating over strong recurrent and feed forward baselines.

We study an online sketched Newton method that approximates the Newton direction at each step via a state-of-the-art sketching solver, called the generalized accelerated sketch-and-project solver (GAS), thereby mitigating the computational bottleneck of classical second-order methods. The GAS solver improves upon vanilla, unaccelerated sketch-and-project solvers by achieving accelerated convergence through Nesterov momentum updates, and accommodates a flexible projection metric whose proper choice further reduces computational cost. Building on this design, we establish asymptotic normality of the averaged sketched Newton iterates and characterize their limiting covariance matrix. The resulting covariance recovers that of the unaccelerated sketched Newton method under a specific choice of acceleration parameters, converges more rapidly (in the number of sketching steps) to the minimax-optimal covariance in general, and is smaller than that of the last iterate produced by the accelerated method. Finally, we strengthen these results by establishing a functional central limit theorem for the Newton iterates, which allows us to bypass explicit covariance estimation and develop an online inference procedure based on random scaling. Specifically, we construct a pivotal test statistic by appropriately rescaling the averaged iterates, so that its limiting distribution is free of any unknown parameters, enabling asymptotically valid online inference. Numerical experiments demonstrate superior performance of the proposed inference procedure.

Reinforcement learning with verifiable rewards is typically performed on-policy, keeping training data close to the current policy but limiting learning to trajectories that the policy can discover itself. Off-policy methods such as supervised fine-tuning, on the other hand, can leverage external knowledge beyond the base model's capabilities, but may suffer from large distribution shift. The key challenge is thus to expand exploration without sacrificing learnability. In this work, we introduce Minimal Intervention Reinforcement Learning (MInTRL), which expands the exploration frontier through sparse, local interventions in otherwise on-policy rollouts. During generation, a judge-intervention policy periodically reviews the current policy's output, replaces erroneous suffixes with short corrections, and immediately returns control to the policy. During training, MInTRL adopts a sequence-level advantage-regression objective that eliminates the need for importance sampling. We show that sparse, local interventions can substantially improve coverage beyond finite-budget on-policy sampling while preserving the overall on-policy nature of the resulting trajectories. Across math and code benchmarks, MInTRL consistently outperforms standard on-policy and off-policy baselines. Ablations show that MInTRL remains effective with self-intervention and across different judge policies, while performance peaks at moderate intervention intensity, highlighting the importance of intervening minimally. These results establish minimal intervention as an effective paradigm for enhancing on-policy RL.

Neural architecture search (NAS) evaluates candidate networks, but fully training enough architectures to rank an entire space is expensive. Zero-cost proxies score architectures at initialization, yet their ranking quality varies across search spaces. Learned predictors reduce evaluation cost but typically require fully trained labels or partial-training features for individual candidates. We introduce $\textbf{RiPPLE}$, $\underline{\textbf{R}}$anking v$\underline{\textbf{i}}$a $\underline{\textbf{P}}$refix-$\underline{\textbf{P}}$ropagated $\underline{\textbf{L}}$abel $\underline{\textbf{E}}$xtrapolation, which treats partial training as a source of labels for a small coverage set of anchors. RiPPLE trains these anchors to an early prefix, extrapolates their learning curves to surrogate labels, and propagates the labels over label-free architecture features. The early-training signal remains a label on the anchors rather than a per-candidate feature. Feature, readout, and encoding rules are selected without held-out accuracy and reused across search spaces. We evaluate the method on twelve benchmark cells from four search-space families and on the larger DARTS space. The results examine ranking quality, label efficiency, architecture selection, and the roles of readout, coverage, and propagation. RiPPLE provides a whole-space ranking from a fractional anchor-training budget, with comparisons interpreted under their respective evaluation and cost protocols.

Multiview point cloud registration is particularly challenging in low-overlap scenes, where reliable correspondences are limited and incorrect pairwise transformations can affect global pose estimation. In addition, registering all scan pairs is computationally expensive because many pairs provide weak geometric information. To address these problems, we propose GMPCR, a non-learning-based spectral consistency-guided framework for efficient and robust multiview point cloud registration. GMPCR builds a refined second-order compatibility structure from initial correspondences and uses its dominant spectral response to evaluate both correspondence reliability and scan-pair confidence. This allows unreliable correspondences to be filtered and informative scan pairs to be selected before relative transformation estimation, leading to a sparse pose graph and reduced pairwise registration cost. For each retained scan pair, maximal-clique-based hypothesis generation is used to estimate reliable relative transformations. The resulting pose graph is further refined by an adaptive history-aware synchronization scheme, in which the effect of residual history is adjusted according to changes in the global rotation residual. A recovery mechanism also allows down-weighted edges to regain confidence when their global consistency improves. Experiments on 3DMatch, 3DLoMatch, ScanNet, and ETH demonstrate the effectiveness of GMPCR. It achieves registration recalls of 97.2% and 89.6% on 3DMatch and 3DLoMatch, respectively, while maintaining competitive performance on ScanNet and ETH. The results show that GMPCR provides a favorable balance among registration accuracy, robustness to low overlap, and computational efficiency. The code is publicly available at https://github.com/swccj/gmpcr.

Public VR game leaderboards contain tracked motion recordings uploaded by hundreds of thousands of users. Once uploaded, these recordings are accessible to anyone and create privacy risks (i.e., identification and profiling). Prior work has proposed mechanisms that modify tracked movement to reduce these risks. Their utility is commonly evaluated through physical deviation, where smaller deviations indicate better utility, while user studies are less common. However, it remains unclear how well physical deviation explains users' acceptance of a mechanism compared to user studies. We examine this through a user study of three VR motion privacy mechanisms at five physical deviation levels. We find that user studies explain substantially more variation in mechanism acceptance than physical deviation, although physical deviation remains significant. We also find that prior VR experience and exposure to VR privacy mechanisms significantly affect acceptance. We recommend combining physical deviation with user studies and reporting participants' prior experience.

Large language models (LLMs) are rapidly evolving from conversational assistants into agentic AI systems that reason, plan, invoke tools, maintain persistent memory, communicate with other agents, and execute multi-step tasks. At the same time, modern models exhibit substantially stronger native safety alignment than earlier generations on which many jailbreak attacks and defenses were originally studied. This shift raises a fundamental question: which established jailbreak-security findings remain valid in the era of modern LLMs and agentic AI? We address this question through a Systematization of Knowledge (SoK) that reframes jailbreak security around the full agentic execution pipeline. We develop unified taxonomies of attacks and defenses spanning user interaction, planning and reasoning, memory, tool use, and inter-agent communication, and introduce a security–utility–efficiency evaluation framework that separates native harmful-prompt safety, adversarial jailbreak robustness, and agent-level security outcomes. We further conduct a controlled empirical study of representative attacks and defenses within a common agentic framework. Our results reveal three important gaps. First, strong native alignment does not imply robustness to adversarial jailbreaks. Second, defense effectiveness is highly model-, attack-, and component-dependent and can come at substantial cost in over-refusal, utility, and latency. Third, low final-response attack success can mask severe intermediate compromise: planning, memory, and tool interactions may remain unsafe even when the final response is successfully filtered. These findings motivate a shift from response-centric jailbreak defense toward cross-layer, execution-aware security that protects agent state, component transitions, and external actions while preserving practical utility and efficiency.

Foundation models, including large language models, vision-language models, and time-series foundation models, are increasingly deployed on embedded and edge platforms for CPS and IoT applications, where energy, latency, and memory are as critical as task accuracy. Existing benchmarking tools evaluate model capability in isolation, reporting accuracy assuming sufficient compute, while hardware profiling tools remain platform-specific and mutually incompatible. As a result, users lack a unified workflow for making deployment decisions across heterogeneous devices. We present HoliBench, a modular benchmarking and deployment toolkit that jointly characterizes accuracy, latency, and energy across platforms from single-board computers to GPU servers. Its platform abstraction layer calibrates cross-device measurement, and the toolkit supports multiple model modalities, inference engines, concurrencies, and existing evaluation harnesses. An interactive interface exposes constraint-aware configuration selection over a design space that is profiled once and reused across studies. Using HoliBench, we characterize 20 models across 7 device types, 3 quantization levels, 8 inference backends, and over 30 tasks, surfacing tradeoffs that existing tools miss: quantization reduces latency only on hardware with low-precision support, accuracy gains show diminishing returns relative to energy, and for autoregressive workloads, average inference power is approximately constant across output lengths. We further find that single-model profiles compose under sequential co-resident execution. In a multi-model CPS deployment, standalone profiles predict combined-pipeline latency and power within 1.2% and 2.5%, enabling deployment exploration without exhaustively profiling every pipeline configuration. We release HoliBench as open-source infrastructure for deployment-aware evaluation of foundation models.

Prohibited-item detection in X-ray imagery remains challenging due to object superposition, weak texture, and material clutter which obscure both semantic appearance and object boundaries. We propose DERA, a Detached Edge-Residual Adaptation framework for prohibited item detection under X-ray imagery. DERA combines hierarchical visual features with a parallel pixel-difference edge pyramid and learns an object-specific boundary prior from training-time contours of the instance masks. The detached prior gates edge-sensitive features, which are injected into the early visual stages through residual heads. This staged design preserves the foundation detector at the start of adaptation, isolates boundary supervision from semantic feature learning, and restricts the final adaptation stage to only \(14.7\)K trainable parameters. Evaluated on PIDray, CLCXray, and STCray, DERA improves the baseline by 3.1, 1.6, and 2.4 AP points, respectively.

Dementia is a major and growing global health burden, with Alzheimer's disease (AD) accounting for most cases. Timely and accurate diagnosis is central to managing this burden and increasingly depends on integrating complementary clinical and imaging information. Multimodal deep learning can combine these modalities for AD diagnosis, but how its explanations behave across modalities, fusion strategies, and cohorts remains unclear. We developed an explainable multimodal framework pairing a 3D CNN encoder for T1-weighted MRI with a feedforward network for harmonized clinical and demographic data, comparing varied model setups on three-way and pairwise diagnostic tasks using 6,479 internal records from the ADNI and 1,703 independent records from the OASIS-3. On ADNI, the tabular-only model achieved the highest three-class AUC-ROC of 0.879 and best discriminated cognitively normal (CN) versus mild cognitive impairment (MCI; 0.903), while cross-attention performed best for MCI versus AD (0.861); CN versus AD was highly discriminative overall. On OASIS-3, the vision-only model performed best (three-class AUC-ROC 0.910); CN versus MCI remained difficult, and no fusion strategy consistently outperformed single modalities across tasks and cohorts. SHAP and Integrated Gradients identified the MMSE as the dominant tabular feature in both cohorts, with global feature rankings agreeing strongly in ADNI ($\rho=0.94$) and OASIS-3 ($\rho=0.96$); CAM-based explanations, however, changed with model configuration and cohort. These findings show that multimodal performance and explanations are task, modality, fusion, and cohort-dependent: a dominant cognitive signal persisted across cohorts, but feature contributions and CAM explanations did not, underscoring the need to evaluate explainability under cohort shift rather than as a stable, intrinsic property.

High-frequency surgical maneuvers in ophthalmology necessitate high-fidelity temporal modeling, yet characterizing long-range procedural dependencies remains computationally prohibitive for attention-based architectures. Existing models often require aggressive temporal downsampling, which compromises the detection of fine-grained action boundaries and instrument-tissue interactions. To address these scalability constraints, we present OphBiWSSD, a framework that reformulates surgical temporal action localization leveraging Bidirectional State Space Duality. By employing a weight-tied selective scan mechanism that incorporates both preceding and succeeding surgical contexts, our approach facilitates the global synthesis of non-causal temporal cues with linear complexity. This streamlined architecture is well-suited to capture the bidirectional dependencies present in ophthalmic workflows, effectively bridging the gap between local boundary precision and long-range procedural context without incurring the quadratic memory overhead of traditional Transformers. Extensive experiments on the OphNet benchmark demonstrate that OphBiWSSD achieves state-of-the-art temporal localization performance, with mean Average Precisions of 44.42% on phases and 43.08% on operations, surpassing the baselines by 6.80% and 6.66%, respectively. Empirical validation indicates that our approach ensures precise temporal localization and offers a computationally viable pathway for deploying surgical intelligence systems in clinical environments. The code is publicly available at https://github.com/yo3nglau/OphBiWSSD.

Hazardous-freight operations at petrochemical logistics nodes are safety-critical for intelligent transportation systems, yet existing vision benchmarks rarely address procedural compliance under realistic deployment constraints. In large infrastructure networks, cameras often operate under sparse round-robin polling, so transfer status must be inferred from incomplete observations and localized evidence. We present GSO-Net, a large-scale benchmark for visual understanding of standard operating procedures (SOPs) in petrochemical unloading scenarios. To our knowledge, GSO-Net is the first public benchmark dataset dedicated to visual SOP understanding in petrochemical hazardous-freight transfer scenarios. It contains over 50,000 independently sampled frames from 64 real expressway petrochemical logistics nodes and adopts an SOP-derived hierarchy linking 9 macroscopic procedural steps with 15 microscopic operational states. Two tasks are defined: joint detection of microscopic states and macroscopic steps as the core benchmark, and frame-level step classification as a diagnostic reference. Experiments with lightweight, transformer-based, open-vocabulary, and holistic models reveal a clear gap between object perception and transfer-stage understanding. Current models remain weak on contact-level state grounding, transient step recognition, and stage consistency, especially under sparse polling, tiny critical targets, and long-tailed operational evidence. GSO-Net provides a practical benchmark for fine-grained state perception and vision-based safety monitoring in hazardous freight transportation. The dataset is publicly available at https://github.com/yuxieHarrison/GSO-Net

Microwave ablation (MWA) is a percutaneous ablation that induces thermal necrosis by generating localized high-temperature regions within tumor tissue. However, when a tumor is located close to a large vessel such as the aorta, blood flow continuously removes heat from the ablation zone. This phenomenon causes the vascular heat-sink effect and thereby increases the risk of incomplete ablation. This study constructs an ANSYS-based numerical framework to investigate the heat-sink effect during MWA of tumors located close to the aorta. The computational model consists of the tumor, surrounding tissue, vessel wall, blood flow domain, and microwave antenna. Microwave-induced heating was represented by an equivalent heat source mapped from the High-Frequency Structure Simulator (HFSS)-derived volume loss density, rather than by direct electromagnetic-thermal coupling within the thermal-fluid solver. Two parametric studies were performed to quantify the heat-sink effect. First, the tumor-aorta distance was varied at D = 0 mm, 4 mm, and 8.5 mm to assess how vessel proximity affects temperature elevation and ablation zone formation. Second, at each tumor-aorta distance, three blood-flow conditions were compared: no blood, stagnant blood V = 0 m/s, and normal aortic blood flow V=0.65 m/s. This comparison enabled the heat-sink effect of blood flow to be independently evaluated. The results highlight the clinical need for simulation-based treatment planning in patients with tumors located close to major vessels.

Learning from trial and error is a promising way to improve language agents on complex tasks such as computer control. Reflexion introduced verbal reinforcement learning, which turns failed trials into text that guides later attempts without updating model parameters. We introduce VRL-Bench, a harness for fair evaluation of trial-and-error learning under finite trial budgets. Across three models on MiniWoB and WebShop, we evaluate updates from several prominent verbal-memory methods spanning Reflexion and later work: each improves observed success over memory-free retry in some settings but reduces it in others. Replay experiments show that using reflection can reduce success rates, revealing a trade-off between exploiting experience and continued exploration. We propose VEX$^2$, a verbal exploration–exploitation scheduler that uses a language model to jointly select policies and allocate the remaining trial budget. VEX$^2$ is the only evaluated update to achieve positive observed success-rate gains over retry in all six settings.

Cognitive Diagnosis Models (CDMs) play a pivotal role in personalized online learning. Traditional CDMs rely on discrete, ID-based embeddings to represent students, exercises, and concepts. This paradigm diverges from the nature of learner cognition, where knowledge is not stored and retrieved as isolated symbols. As a result, CDMs suffer from semantic limitations when new exercises or concepts appear. In this paper, we propose a Process-aware Language Cognitive Diagnosis (PLCD) framework that uses language-derived structures as cognitive priors and response records to calibrate student posterior states. PLCD leverages large language models (LLMs) to construct concept schemas and cognitive process graphs, and uses target-conditioned semantic memory to retrieve historical responses that are relevant to each target exercise. A process-grounded Language-to-Cognition Mapper with DA-MoE experts and process-level contrastive learning then maps the textual evidence into a unified cognitive space. Experimental results show that PLCD not only outperforms traditional baselines in predicting student performance but also exhibits strong cognitive transfer capabilities. These results connect the computational power of LLMs with the psychometric goal of measuring latent knowledge states, suggesting that structured language priors calibrated by response records can improve cold-start robustness and cognitive grounding.

This paper presents a novel approach to hexapod locomotion by evolving each leg's gait independently through a decentralized evolutionary algorithm. Using the Webots simulator and the Mantis hexapod robot, we optimize individual leg controllers without centralized coordination, allowing emergent behaviors to drive the development of efficient, coordinated locomotion. Our decentralized method is benchmarked against cooperative coevolution, demonstrating improved efficacy in generating stable and adaptive gaits while showing interesting emergent coordination. By enabling independent evolution of leg controllers, this method reduces the complexity of gait optimization and highlights the potential of decentralized strategies for scalable and adaptive robotic systems.