Neural methods for Complex Query Answering (CQA) over knowledge graphs (KGs) are widely believed to learn patterns that generalize beyond explicit graph structure, allowing them to infer answers that are unreachable through symbolic query processing. In this work, we critically examine this assumption through a systematic analysis comparing neural CQA models with an alternative, training-free query relaxation strategy that retrieves possible answers by relaxing query constraints and counting resulting paths. Across multiple datasets and query structures, we find several cases where neural and relaxation-based approaches perform similarly, with no neural model consistently outperforming the latter. Moreover, a similarity analysis reveals that their retrieved answers exhibit little overlap, and that combining their outputs consistently improves performance. These results call for a re-evaluation of progress in neural query answering: despite their complexity, current models fail to subsume the reasoning patterns captured by query relaxation. Our findings highlight the importance of stronger non-neural baselines and suggest that future neural approaches could benefit from incorporating principles of query relaxation.

Diffusion models start generation from an isotropic Gaussian latent, yet changing only the random seed can lead to large differences in prompt faithfulness, composition, and visual quality. We study this seed sensitivity through the semantic map from initial noise to generated meaning. Although the sampling flow is locally invertible, the subsequent semantic projection is many-to-one, inducing a degenerate pullback semi-metric on the latent space: most local directions are nearly semantic-invariant, while semantic-sensitive variation is concentrated in a much smaller horizontal subspace. This provides an explanatory geometric view of the seed lottery. Motivated by this view, we introduce a training-free prompt-residual seed-shaping procedure. Rather than claiming to recover the exact horizontal space, the method uses a single high-noise cold-start prompt residual as a model-coupled proxy, injects only its tangential component, and retracts the seed to the original Gaussian radius shell. This keeps the initialization prior-compatible while adding only one conditional/unconditional probe before standard sampling. Across multiple generation benchmarks, the method improves alignment and quality metrics over standard sampling, supporting both the practical value of the proxy and the explanatory relevance of semantic anisotropy.

Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinterpretations, and regulatory or industrial updates make static alignment increasingly brittle. As policies evolve, deployed models can diverge from current alignment objectives, creating an Alignment-Reality Gap that is difficult to audit or correct. Existing remediation typically requires re-annotation under revised guidelines, which introduces systematic challenges, including guideline ambiguity, annotator interpretation drift, and reduced consistency at scale. We introduce TRACE (Triage and Re-align by Alignment Conflict Evaluation), a framework that transforms realignment into a structured optimization problem over existing data without requiring fresh human annotation. Leveraging a stronger model as a proxy judge, TRACE operates via a three-stage pipeline: (1) triaging preference pairs into inversion, suppression, or retention categories based on alignment conflicts; (2) computing an alignment impact score via bi-level optimization to prioritize high-leverage samples; and (3) executing updates using a hybrid objective that combines relational losses (e.g., IPO) for preference inversion and punitive losses (e.g., NPO) for response suppression. Experiments on Qwen2.5-7B, Gemma-2-9B, and Llama-3.1-8B demonstrate robust realignment on synthetic benchmarks and the PKU-SafeRLHF dataset without degrading general utility. This work provides a scalable approach for LLM realignment under evolving data annotation policies and alignment guidelines. We release our code: https://respailab.github.io/TRACE/

This paper presents the MOBIUS platform, a bipedal robot capable of walking, crawling, climbing, and rolling. MOBIUS features four limbs, two 6-DoF arms with two-finger grippers for manipulation and climbing, and two 4-DoF legs for locomotion--enabling smooth transitions across diverse terrains without reconfiguration. A hybrid control architecture combines reinforcement learning for locomotion and force control for compliant contact interactions during manipulation. A high-level MIQCP planner autonomously selects locomotion modes to balance stability and energy efficiency. Hardware experiments demonstrate robust gait transitions, dynamic climbing, and full-body load support via pinch grasp. Overall, MOBIUS demonstrates the importance of tight integration between morphology, high-level planning, and control to enable mobile loco-manipulation and grasping, substantially expanding its interaction capabilities, workspace, and traversability.

Large Language Models (LLMs) training is prohibitively expensive, driving interest in low-precision fully-quantized training (FQT). While novel 4-bit formats like NVFP4 offer substantial efficiency gains, achieving near-lossless training at such low precision remains challenging. We introduce TetraJet-v2, an end-to-end 4-bit FQT method that leverages NVFP4 for activations, weights, and gradients in all linear layers. We identify two critical issues hindering low-precision LLM training: weight oscillation and outliers. To address these, we propose: 1) an unbiased double-block quantization method for NVFP4 linear layers with practically optimal convergence in LLM training, 2) OsciReset, the first effective algorithm to suppress LLMs' weight oscillation bottleneck, and 3) OutControl, a mix-precision algorithm to retain outlier accuracy. TetraJet-v2 outperforms prior methods on FP4 pre-training for LLMs across models up to 370M parameters trained up to 212B tokens, reducing the performance gap to BF16 by an average of 51.3% while enabling an 1.67x end-to-end speedup over FP8. The code is available at https://github.com/thu-ml/TetraJet-v2-NVFP4Training.

Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstream tasks with limited data. Its parameter efficiency makes it particularly suitable for Federated Learning (FL), where both communication and computation budgets are often constrained. However, global prompt tuning struggles to generalize across heterogeneous clients, while personalized tuning overfits to local data and lacks generalization. We propose PEP-FedPT (Prompt Estimation from Prototypes for Federated Prompt Tuning), a unified framework designed to achieve both generalization and personalization in federated prompt tuning of ViTs. Within this framework, we introduce the novel Class-Contextualized Mixed Prompt (CCMP) - based on class-specific prompts maintained alongside a globally shared prompt. For each input, CCMP adaptively combines class-specific prompts using weights derived from global class prototypes and client class priors. This approach enables per-sample prompt personalization without storing client-dependent trainable parameters. The prompts are collaboratively optimized via traditional federated averaging technique on the same. Comprehensive evaluations on CIFAR-100, TinyImageNet, DomainNet, and iNaturalist datasets demonstrate that PEP-FedPT consistently surpasses the state-of-the-art baselines under diverse data heterogeneity scenarios, establishing a strong foundation for efficient and generalizable federated prompt tuning of Vision Transformers.

Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activations more interpretable by exposing latent features that often align with human concepts. Yet, these features are fragile and passive, offering no mechanism for systematic reasoning or model control. To address this, we introduce ActivationReasoning (AR), a framework that embeds explicit logical reasoning into the latent space of LLMs. It proceeds in three stages: (1) Finding latent representations, first latent concept representations are identified (e.g., via SAEs) and organized into a dictionary; (2) Activating propositions, at inference time AR detects activating concepts and maps them to logical propositions; and (3)Logical reasoning, applying logical rules over these propositions to infer higher-order structures, compose new concepts, and steer model behavior. We evaluate AR on multi-hop reasoning (PrOntoQA), abstraction and robustness to indirect concept cues (Rail2Country), reasoning over natural and diverse language (ProverQA), and context-sensitive safety (BeaverTails). Across all tasks, AR scales robustly with reasoning complexity, generalizes to abstract and context-sensitive tasks, and transfers across model backbones. These results demonstrate that grounding logical structure in latent activations not only improves transparency but also enables structured reasoning, reliable control, and alignment with desired behaviors, providing a path toward more reliable and auditable AI.

Dropout is common in clinical studies, with up to half of patients leaving early due to side effects or other reasons. When dropout is informative (i.e., dependent on survival time), it introduces censoring bias, because of which treatment effect estimates are also biased. In this paper, we propose an assumption-lean framework to assess the robustness of conditional average treatment effect (CATE) estimates in survival analysis when facing censoring bias. Unlike existing works that rely on strong assumptions, such as non-informative censoring, to obtain point estimation, we use partial identification to derive informative bounds on the CATE. Thereby, our framework helps to identify patient subgroups where treatment is effective despite informative censoring. We further propose a novel model-agnostic meta-learner, called SurvB-learner, to estimate the bounds that can be used in combination with arbitrary machine-learning models, and that has favorable theoretical properties such as double-robustness and quasi-oracle efficiency. We finally demonstrate the effectiveness of our meta-learner across various experiments using both simulated and real-world data.

Depression is a pressing global public health issue, yet publicly available Chinese-language resources for depression risk detection remain scarce and largely focus on binary classification. To address this limitation, we release CNSocialDepress, a benchmark dataset for depression risk detection on Chinese social media. The dataset contains 44,178 posts from 233 users; psychological experts annotated 10,306 depression-related segments. CNSocialDepress provides binary risk labels along with structured, multidimensional psychological attributes, enabling interpretable and fine-grained analyses of depressive signals. Experimental results demonstrate the dataset's utility across a range of NLP tasks, including structured psychological profiling and fine-tuning large language models for depression detection. Comprehensive evaluations highlight the dataset's effectiveness and practical value for depression risk identification and psychological analysis, thereby providing insights for mental health applications tailored to Chinese-speaking populations.

We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Ensemble Sampling (GLM-ES) for generalized linear bandits and Neural Ensemble Sampling (Neural-ES) for neural contextual bandits. Both methods maintain multiple estimators for the reward model parameters via maximum likelihood estimation on randomly perturbed data. We prove high-probability frequentist regret bounds of $\widetilde{O}(d^{3/2} \sqrt{T} + d^{4})$ for GLM-ES and $\widetilde{O}(\widetilde{d}^{3/2} \sqrt{T})$ for Neural-ES, where $d$ is the dimension of feature vectors, $\widetilde{d}$ is the effective dimension of a neural tangent kernel (NTK) matrix and $T$ is the number of rounds. The regret bound of GLM-ES matches the state-of-the-art result of randomized exploration algorithms in generalized linear bandit setting. In the theoretical analysis, we introduce techniques that address challenges specific to nonlinear models. Practically, we remove fixed-time horizon assumption by developing anytime versions of our algorithms, suitable when $T$ is unknown. Finally, we empirically evaluate GLM-ES, Neural-ES and their anytime variants, demonstrating strong performance. Overall, our results establish ensemble sampling as a provable and practical randomized exploration approach for nonlinear contextual bandits.

Post-training Large Vision-and-Language Models (LVLMs) typically involves Supervised Fine-Tuning (SFT) for knowledge injection or Reinforcement Learning with Verifiable Rewards (RLVR) for performance enhancement. However, SFT often leads to sub-optimal performance, while RLVR remains constrained by the model's internal knowledge base. While a sequential SFT $\rightarrow$ RLVR pipeline can be used, it introduces significant computational overhead and suffers from catastrophic forgetting. To address these limitations, we propose ViSurf (\textbf{Vi}sual \textbf{Su}pervised-and-\textbf{R}einforcement \textbf{F}ine-Tuning), a unified, single-stage paradigm that integrates the strengths of both SFT and RLVR. By analyzing their training objectives, we establish a unified framework that injects ground-truth labels directly into RLVR rollouts, facilitating simultaneous external supervision and internal reinforcement. Furthermore, we introduce three novel reward control strategies to ensure training stability and optimization. Extensive experiments demonstrate that ViSurf consistently outperforms standalone SFT, RLVR, and the traditional two-stage pipeline across diverse benchmarks. In-depth analysis corroborates these findings, validating the derivation and design principles of ViSurf.

We study black-box detection of machine-generated text under practical constraints: the scoring model (proxy LM) may mismatch the unknown source model, and per-input contrastive generation is costly. We propose SurpMark, a reference-based detector that summarizes a passage by the dynamics of its token surprisals. SurpMark discretizes surprisals into interpretable states, estimates a state-transition matrix for the test text, and scores it via a generalized Jensen-Shannon (GJS) gap between the test transitions and two fixed references (human vs. machine) built once from existing corpora. Theoretically, we derive design guidance for how the discretization bins should scale with data and provide a principled justification for our test statistic. Empirically, across multiple datasets, source models, and scenarios, SurpMark consistently matches or surpasses baselines, demonstrating strong robustness across domains and generators; our experiments on hyperparameter sensitivity exhibit trends that our theoretical results help to explain.

This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic biases and drift to the target model. To address this, we formulate multi-source reasoning alignment as a constraint satisfaction problem under concept drift theory. We propose Autonomous Preference Optimization (APO), a novel framework that treats inter-model divergences not as noise, but as dynamic negative constraints. APO operates via a two-stage protocol: first, supervised bootstrapping projects the target model into the capability union of source models; second, constraint-aware optimization synthesizes a consistent consensus manifold by explicitly suppressing drifting trajectories via a multi-negative Plackett-Luce objective. Extensive experiments on chest X-ray interpretation demonstrate that our 7B model achieves superior robustness, outperforming even proprietary source models in average accuracy. Furthermore, we release CXR-MAX, a large-scale benchmark comprising 170,982 reasoning trajectories from seven large-scale MLLMs to facilitate research on reasoning alignment under drift. Code and data are available at: https://github.com/XiaoyuYoung/APO.

Vision-Language-Action (VLA) models represent a pivotal advance in embodied intelligence, yet they confront critical barriers to real-world deployment, most notably catastrophic forgetting. This issue stems from their overreliance on continuous action sequences or action chunks, which inadvertently create isolated data silos that disrupt knowledge retention across tasks. To tackle these challenges, we propose the Narrowing of Trajectory VLA (NoTVLA) framework: a novel approach that narrows its focus to sparse trajectories, thereby avoiding the catastrophic forgetting associated with dense trajectory fine-tuning. A key innovation of NoTVLA lies in its trajectory planning strategy: instead of centering on the target object's trajectory, it leverages temporal compression and spatial reasoning pruning specifically for the robot end effector's trajectory. Furthermore, training is conducted using these sparse trajectories rather than dense action trajectories, an optimization that delivers remarkable practical advantages with better performance in zero-shot. In multi-task evaluation scenarios, NoTVLA achieves superior performance and generalization compared to pi0 while operating under two critical constraints: it uses over an order of magnitude less computing power than pi0 and requires no wrist-mounted camera. This design ensures that NoTVLA's operational accuracy closely approximates that of single-task expert models. Crucially, it also preserves the model's inherent language capabilities, enabling zero-shot generalization in specific scenarios, supporting unified model deployment across multiple robot platforms, and fostering a degree of generalization even when perceiving tasks from novel perspectives.

In this work we introduce GreenLightningAI (GLAI), a new architectural block designed as an alternative to conventional MLPs. The central idea is to separate two types of knowledge that are usually entangled during training: (i) *structural knowledge*, encoded by the stable activation patterns induced by ReLU activations; and (ii) *quantitative knowledge*, carried by the numerical weights and biases. By fixing the structure once stabilized, GLAI reformulates the MLP as a combination of paths, where only the quantitative component is optimized. This reformulation retains the universal approximation capabilities of MLPs, yet achieves a more efficient training process, reducing training time by ~40% on average across the cases examined in this study. Crucially, GLAI is not just another classifier, but a generic block that can replace MLPs wherever they are used, from supervised heads with frozen backbones to projection layers in self-supervised learning or few-shot classifiers. Across diverse experimental setups, GLAI consistently matches or exceeds the accuracy of MLPs with an equivalent number of parameters, while converging faster. Overall, GLAI establishes a new design principle that opens a direction for future integration into large-scale architectures such as Transformers, where MLP blocks dominate the computational footprint.

Data-driven models are increasingly adopted in critical scientific fields like weather forecasting and fluid dynamics. These methods can fail on out-of-distribution (OOD) data, but detecting such failures in regression tasks is an open challenge. We propose a new OOD detection method based on estimating joint likelihoods using a score-based diffusion model. This approach considers not just the input but also the regression model's prediction, providing a task-aware reliability score. Across numerous scientific datasets, including PDE datasets, satellite imagery and brain tumor segmentation, we show that this likelihood strongly correlates with prediction error. Our work provides a foundational step towards building a verifiable 'certificate of trust', thereby offering a practical tool for assessing the trustworthiness of AI-based scientific predictions. Our code is publicly available at https://github.com/bogdanraonic3/OOD_Detection_ScientificML

We study empirical scaling laws for language model merging measured by cross-entropy. Despite its wide practical use, merging lacks a quantitative rule that predicts returns as we add experts or scale the model size. We identify a compact power law that links model size and expert number: the size-dependent floor decreases with model capacity, while the merging tail exhibits clear diminishing returns in the number of experts. The law holds in-domain and cross-domain, tightly fits measured curves across diverse architectures and methods (Average, TA, TIES, DARE), and explains two robust regularities: most gains arrive early, and variability shrinks as more experts are included. Building on this, we present a simple theory that explains why gains fall roughly as 1/k and links the floor and tail to properties of the base model and the diversity across domains. This law enables predictive planning: estimate how many experts are needed to reach a target loss, decide when to stop adding experts, and trade off scaling the base model versus adding experts under a fixed budget--turning merging from heuristic practice into a computationally efficient, planable alternative to multitask training. This suggests a scaling principle for distributed generative AI: predictable gains can be achieved by composing specialists, offering a complementary path toward AGI-level systems.

Mixture-of-Experts (MoE) models typically fix the number of activated experts $k$ at both training and inference. However, real-world deployments often face heterogeneous hardware, fluctuating workloads, and diverse quality-latency requirements, while training separate models for each scenario is costly. Considering that MoE models already operate with sparse activation, adjusting the number of activated experts offers a natural path to serving diverse budgets with a single model. Yet, we find that activating more experts $k'$ ($> k$) at inference does not yield the expected gains. Instead, performance degrades rapidly after only a slight increase, a phenomenon we term the \textit{inference-time scaling wall}. Further investigation reveals that this degradation stems from a lack of learned collaboration among experts. To address this, we introduce \textbf{Elastic Mixture-of-Experts (EMoE)}, a novel training framework that enables MoE models to elastically vary the number of activated experts at inference. By simultaneously training experts to collaborate in diverse combinations and encouraging the router to make high-quality selections, EMoE ensures robust performance across inference budgets. Extensive experiments across four MoE architectures (7B--21B) and nine benchmarks show that EMoE significantly expands the effective scaling range to 2-3$\times$ the training-time $k$, while also achieving higher peak performance.

Integer Linear Programs (ILPs) are central to real-world optimizations but notoriously difficult to solve. Learning to Optimize (L2O) has emerged as a promising paradigm, with Graph Neural Networks (GNNs) serving as the standard backbone. However, standard anonymous GNNs are limited in expressiveness for ILPs, and the common enhancement of augmenting nodes with globally unique identifiers (UIDs) typically introduces spurious correlations that severely harm generalization. To address this tradeoff, we propose a parsimonious Local-UID scheme based on d-hop uniqueness coloring, which ensures identifiers are unique only within each node's d-hop neighborhood. Building on this scheme, we introduce ColorGNN, which incorporates color information via color-conditioned embeddings, and ColorUID, a lightweight feature-level variant. We prove that for d-layer networks, Local-UIDs achieve the expressive power of Global-UIDs while offering stronger generalization. Extensive experiments show that our approach yields substantial and robust gains across ILP benchmarks.

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains challenging, as they lack precise probability estimates at each denoising step. While the diffusion mechanism enables the model to reason over entire sequences, it also makes the generation process less predictable and often inconsistent. This highlights the importance of controlling key tokens that guide the direction of generation. To address this issue, we propose GIFT, an importance-aware finetuning method for diffusion language models, where tokens are assigned different importance weights based on their entropy. Derived from diffusion theory, GIFT delivers substantial gains: across diverse settings including different mainstream training datasets ranging from 1k to 10k in size, utilizing LoRA or full parameter fine-tuning, and training on base or instruct models, GIFT consistently achieves superior overall performance compared to standard SFT on four widely used reasoning benchmarks (Sudoku, Countdown, GSM8K, and MATH-500).

We study spectral algorithms in the setting where kernels are learned from data. We introduce the effective span dimension (ESD), an alignment-sensitive complexity measure that depends jointly on the signal, spectrum, and noise level $σ^2$. The ESD is well-defined for arbitrary kernels and signals without requiring eigen-decay conditions or source conditions. We prove that for sequence models whose ESD is at most $K$, the minimax excess risk scales as $σ^2 K$. Furthermore, we analyze over-parameterized gradient flow and prove that it can reduce the ESD. This finding establishes a connection between adaptive feature learning and provable improvements in generalization of spectral algorithms. We demonstrate the generality of the ESD framework by extending it to linear models and RKHS regression, and we support the theory with numerical experiments. This framework provides a novel perspective on generalization beyond traditional fixed-kernel theories.

Global optimization, particularly for non-convex functions with multiple local minima, poses significant challenges for traditional gradient-based methods. While metaheuristic approaches offer empirical effectiveness, they often lack theoretical convergence guarantees and may disregard available gradient information. This paper introduces a novel gradient-based swarm particle optimization method designed to efficiently escape local minima and locate global optima. Our approach leverages a "Soft-min Energy" interacting function, $J_β(\mathbf{x})$, which provides a smooth, differentiable approximation of the minimum function value within a particle swarm. We define a stochastic gradient flow in the particle space, incorporating a Brownian motion term for exploration and a time-dependent parameter $β$ to control smoothness, similar to temperature annealing. We theoretically demonstrate that for strongly convex functions, our dynamics converges to a stationary point where at least one particle reaches the global minimum, with other particles exhibiting exploratory behavior. Furthermore, we show that our method facilitates faster transitions between local minima by reducing effective potential barriers with respect to Simulated Annealing. More specifically, we estimate the hitting times of unexplored potential wells for our model in the small noise regime and show that they compare favorably with the ones of overdamped Langevin. Numerical experiments on benchmark functions, including double wells and the Ackley function, validate our theoretical findings and demonstrate better performance over the well-known Simulated Annealing method in terms of escaping local minima and achieving faster convergence.

Self-adaptive robots (SARs) in complex, uncertain environments must proactively detect and address abnormal behaviors, including out-of-distribution (OOD) cases. To this end, digital twins offer a valuable solution for OOD detection. Thus, we present a digital twin-based approach for OOD detection (ODiSAR) in SARs. ODiSAR uses a Transformer-based digital twin to forecast SAR states and employs reconstruction error and Monte Carlo dropout for uncertainty quantification. By combining reconstruction error with predictive variance, the digital twin effectively detects OOD behaviors, even in previously unseen conditions. The digital twin also includes an explainability layer that links potential OOD to specific SAR states, offering insights for self-adaptation. We evaluated ODiSAR by creating digital twins of two industrial robots: one navigating an office environment, and another performing maritime ship navigation. In both cases, ODiSAR forecasts SAR behaviors (i.e., robot trajectories and vessel motion) and proactively detects OOD events. Our results showed that ODiSAR achieved high detection performance -- up to 98\% AUROC, 96\% TNR@TPR95, and 95\% F1-score -- while providing interpretable insights to support self-adaptation.

Disinformation spreads rapidly across linguistic boundaries, yet most AI models are still benchmarked only on English. We address this gap with a systematic comparison of five multilingual transformer models: mBERT, XLM, XLM-RoBERTa, RemBERT, and mT5 on a common fake-vs-true machine learning classification task. While transformer-based language models have demonstrated notable success in detecting disinformation in English, their effectiveness in multilingual contexts still remains up for debate. To facilitate evaluation, we introduce PolyTruth Disinfo Corpus, a novel corpus of 60,486 statement pairs (false claim vs. factual correction) spanning over twenty five languages that collectively cover five language families and a broad topical range from politics, health, climate, finance, and conspiracy, half of which are fact-checked disinformation claims verified by an augmented MindBugs Discovery dataset. Our experiments revealed performance variations. Models such as RemBERT achieved better overall accuracy, particularly excelling in low-resource languages, whereas models like mBERT and XLM exhibit considerable limitations when training data is scarce. We provide a discussion of these performance patterns and implications for real-world deployment. The dataset is publicly available on our GitHub repository to encourage further experimentation and advancement. Our findings illuminate both the potential and the current limitations of AI systems for multilingual disinformation detection.

Large Audio Language Models (LALMs) are rapidly advancing, but evaluating them remains challenging due to inefficient and non-standardized toolkits that limit fair comparison and systematic assessment. Existing evaluation frameworks exhibit three critical limitations: (1) slow and inefficient processing pipeline that bottlenecks large-scale studies, (2) inadequate multi-turn dialogue support, leaving fundamental questions about cross-turn context integration and performance dynamics over extended conversations in LALMs unanswered; and (3) the absence of unified and scalable evaluation framework capable of keeping pace with the rapid growth of both LALMs and audio benchmarks. To address these issues, we introduce AU-Harness, an efficient and comprehensive evaluation framework for LALMs. Our system achieves a speedup of up to 151% over existing evaluation toolkits through optimized batch processing and parallel execution, enabling large-scale evaluations previously considered impractical. We provide standardized prompting protocols and flexible configurations for fair model comparison across diverse scenarios. AU-Harness unlocks a range of in-depth analyses difficult to conduct without a unified foundation, including multi-turn dialogue dynamics, enabling the study of true audio reasoning capabilities in existing LALMs. AU-Harness provides both practical evaluation tools and insights into model limitations, advancing systematic LALM development.

As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted significant societal and regulatory concerns. In response, governments have issued ethics guidelines to promote the development of trustworthy AI. However, these guidelines are typically high-level demands for developers and testers, leaving a gap in translating them into actionable testing questions to verify LLM compliance. To address this challenge, we introduce GUARD (Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics), a testing method designed to operationalize guidelines into specific guideline-violating questions that assess LLM adherence. To implement this, GUARD uses automated generation of guideline-violating questions based on government-issued guidelines, thereby testing whether responses comply with these guidelines. When responses directly violate guidelines, GUARD reports inconsistencies. Furthermore, for responses that do not directly violate guidelines, GUARD integrates the concept of ``jailbreaks'' to diagnostics, named GUARD-JD, which creates scenarios that provoke unethical or guideline-violating responses, effectively identifying potential scenarios that could bypass built-in safety mechanisms. Our method finally culminates in a compliance report, delineating the extent of adherence and highlighting any violations. We empirically validated the effectiveness of GUARD on eight LLMs, including Vicuna-13B, LongChat-7B, Llama2-7B, Llama-3-8B, GPT-3.5, GPT-4, GPT-4o, and Claude-3.7, by testing compliance under three government-issued guidelines and conducting jailbreak diagnostics. Additionally, GUARD-JD can transfer jailbreak diagnostics to vision-language models (MiniGPT-v2 and Gemini-1.5), demonstrating its usage in promoting reliable LLM-based applications.

The Macroscopic Fundamental Diagram is a popular tool used to describe traffic dynamics in an aggregated way, with applications ranging from traffic control to incident analysis. However, estimating the MFD for a given network requires large numbers of loop detectors, which is not always available in practise. This article proposes a framework to alleviate the data scarcity challenge harnessing Meta-Learning, a subcategory of Machine Learning that trains models to understand and adapt to new tasks on their own. We use Meta-Learning to identify and exploit transferable patterns from data-rich cities to cities where not enough data is available to estimate the MFD. The developed model is trained and tested by leveraging data from multiple cities and exploiting it to model the MFD of other cities with different shares of detectors and topological structures. The proposed Meta-Learning framework is applied to an ad-hoc Multi-Task Physics-Informed Neural Network, specifically designed to estimate the MFD. Results show an average MAE improvement in flow prediction of around 50% across cities (depending on the subset of loop detectors tested). The Meta-Learning framework thus successfully generalises across diverse urban settings and improves performance on cities with limited data, demonstrating the potential of using Meta-Learning when a limited number of detectors is available. We directly test this assumption by applying the Meta-Learning outputs to unseen cities to simulate a real-life application scenario and the wide applicability of the proposed methodology. Finally, the proposed framework is validated against traditional Transfer Learning approaches and tested with FitFun, a model for FD estimation from the literature, to prove its transferability.

As AI systems increasingly rely on training data, assessing dataset trustworthiness has become critical, particularly for properties like fairness or bias that emerge at the dataset level. Prior work has used Subjective Logic to assess trustworthiness of individual data, but not to evaluate trustworthiness properties that emerge only at the level of the dataset as a whole. This paper introduces the first formal framework for assessing the trustworthiness of AI training datasets, enabling uncertainty-aware evaluations of global properties such as bias. Built on Subjective Logic, our approach supports trust propositions and quantifies uncertainty in scenarios where evidence is incomplete, distributed, and/or conflicting. We instantiate this framework on the trustworthiness property of bias, and we experimentally evaluate it based on a traffic sign recognition dataset. The results demonstrate that our method captures class imbalance and remains interpretable and robust in both centralized and federated contexts.

The generalization of deepfake detectors to unseen manipulation techniques remains a challenge for practical deployment. Although many approaches adapt foundation models by introducing significant architectural complexity, this work demonstrates that robust generalization is achievable through a parameter-efficient adaptation of one of the foundational pre-trained vision encoders. The proposed method, GenD, fine-tunes only the Layer Normalization parameters (0.03% of the total) and enhances generalization by enforcing a hyperspherical feature manifold using L2 normalization and metric learning on it. We conducted an extensive evaluation on 14 benchmark datasets spanning from 2019 to 2025. The proposed method achieves state-of-the-art performance, outperforming more complex, recent approaches in average cross-dataset AUROC. Our analysis yields two primary findings for the field: 1) training on paired real-fake data from the same source video is essential for mitigating shortcut learning and improving generalization, and 2) detection difficulty on academic datasets has not strictly increased over time, with models trained on older, diverse datasets showing strong generalization capabilities. This work delivers a computationally efficient and reproducible method, proving that state-of-the-art generalization is attainable by making targeted, minimal changes to a pre-trained foundational image encoder model. The code is at: https://github.com/yermandy/GenD

Neural networks excel across a wide range of tasks, yet remain black boxes. In particular, how their internal representations are shaped by the complexity of the input data and the problems they solve remains obscure. In this work, we introduce a suite of five data-agnostic probes-pruning, binarization, noise injection, sign flipping, and bipartite network randomization-to quantify how task difficulty influences the topology and robustness of representations in multilayer perceptrons (MLPs). MLPs are represented as signed, weighted bipartite graphs from a network science perspective. We contrast easy and hard classification tasks on the MNIST and Fashion-MNIST datasets. We show that binarizing weights in hard-task models collapses accuracy to chance, whereas easy-task models remain robust. We also find that pruning low-magnitude edges in binarized hard-task models reveals a sharp phase-transition in performance. Moreover, moderate noise injection can enhance accuracy, resembling a stochastic-resonance effect linked to optimal sign flips of small-magnitude weights. Finally, preserving only the sign structure-instead of precise weight magnitudes-through bipartite network randomizations suffices to maintain high accuracy. These phenomena define a model- and modality-agnostic measure of task complexity: the performance gap between full-precision and binarized or shuffled neural network performance. Our findings highlight the crucial role of signed bipartite topology in learned representations and suggest practical strategies for model compression and interpretability that align with task complexity.