Papers

Audio-video (AV) editing aims to modify audio and video content according to a target prompt. Unlike single-modality editing, AV editing requires models to infer a modality-selective edit scope from the prompt alone: determining not only what should change, but also which modality should be preserved. Faithfully evaluating such models therefore requires both (i) benchmarks that span diverse edit types and modality categories, and (ii) evaluation that is itself modality-aware and sample-specific. However, existing AV editing benchmarks provide limited coverage of edit types and modality combinations, while current evaluation systems are often modality-blind and sample-agnostic, making it difficult to assess whether models faithfully preserve the unintended modality. To address these gaps, we introduce AVENUE, Audio-Video EditiNg Understanding and Evaluation, comprising two contributions: (1) a benchmark of 1,291 source clips and 7,957 editing instructions across audio-targeted, video-targeted, and AV-coupled edit types, curated and human-verified from VGGSound; and (2) a sample-specific, modality-aware evaluation framework that specifies, for each sample, both the intended change and the content that must remain intact. We evaluate representative AV editing models spanning three editing paradigms : joint, sequential, and separate, providing the first systematic analysis of modality-selectivity across paradigms. Our findings reveal a fundamental open challenge: when editing one modality, existing models frequently induce unintended changes in the other, regardless of paradigm. AVENUE provides a benchmark and modality-aware evaluation framework to drive progress toward more controllable AV editing models. Our dataset is publicly available on Hugging Face: https://huggingface.co/datasets/AVENUE-dataset/AVENUE.

A pseudorandom code (PRC) is a keyed error-correcting code whose codewords are computationally indistinguishable from uniform strings. We study public-key PRCs over fixed alphabets against adversarial deletions, where the deletion channel may both depend on the public encoding key and the transmitted codeword. Let $\gamma_q^{\mathrm{LCS}}$ denote the asymptotic normalised longest-common-subsequence length of two independent uniform $q$-ary strings. We prove that for every fixed $q\ge2$ no multi-message public-key PRC with a single-output decoder is robust against all such $\delta$-deletion channels for any $\delta>1-\gamma_q^{\mathrm{LCS}}$. For $q=2$, the current rigorous bound $\gamma_2\ge0.792665992$ rules out every constant $\delta>0.207334008$. The proof uses pseudorandomness only to transfer an LCS event from uniform strings to independently sampled codewords and therefore also the resulting collision argument is information-theoretic and requires no secret key. We also extend the argument to list decoding: for every fixed constant $L$, provided the message space contains at least $L+1$ messages, no such PRC with output lists of size at most $L$ is robust for $\delta>1-\gamma_2^{(L+1)}$. Since $\gamma_2^{(m)}=1/2+\Theta(1/\sqrt m)$, these thresholds approach $1/2$. Our bounds are specific to public-key-dependent adversarial channels and do not apply to oblivious edit channels.

LLM-as-a-Judge pipelines are increasingly used to evaluate AI-generated text, based on the assumption that judgments arise from reasoning over candidate responses with respect to a rubric. We show that this assumption warrants further scrutiny. Classifiers trained only on rubric text, without access to any evaluated response, achieve nontrivial predictive performance on judge outputs. This suggests that rubric formulations encode recoverable evaluative signals, allowing scores to be partially anticipated independently of model outputs. Finally, counterfactual perturbations reveal that judges often fail to reliably update their decisions when either the candidate response or the rubric criterion is reversed. Our findings raise concerns about the reliability of rubric-based LLM evaluation and highlight the need for further methodological study of automated evaluation via LLMs.

Speech emotion recognition (SER) faces two fundamental challenges: scarcity of labeled data and inter-speaker variability, both of which hinder generalization of emotion recognition systems. While prior adversarial approaches address speaker variability, they fall short in leveraging powerful pre-trained representations. We propose SISER (Speaker-Invariant Speech Emotion Recognition), integrating wav2vec 2.0 as a feature encoder and ECAPA-TDNN as a speaker discriminator within an entropy-based adversarial training scheme. wav2vec 2.0 provides rich self-supervised representations that alleviate dependency on large labeled datasets, while ECAPA-TDNN enables suppression of speaker identity via a stronger adversarial signal than shallow classifiers. Evaluated on IEMOCAP, SISER achieves a UA of 60.63%, outperforming the baseline (51.15%) and wav2vec 2.0 without speaker suppression (56.46%), with ablation emphasizing that the choice of speaker classifier architecture is a key factor.

Recent automatic speech recognition (ASR) systems increasingly integrate large language models (LLMs) to leverage their semantic knowledge, either externally through logit fusion or internally through warm initialization. However, how to effectively combine these two strategies remains underexplored. In this work, we refine warm-initialized LLM-based ASR models by leveraging their own pre-adaptation base LLMs, focusing on LoRA-adapted settings where the base LLM is preserved. To achieve this, we propose Hybrid Search, a targeted correction strategy motivated by two observations. First, interaction features that characterize the relationship between LLM-based ASR hidden states and base-LLM hidden states provide informative signals about a token's degree of semantic dependence. Second, selectively refining targeted tokens with high semantic dependence improves ASR performance far beyond naive global LLM-correction methods including rescoring and late fusion. Our analysis suggests that, even after semantic knowledge transfer through warm initialization, LLM-based ASR models can still leverage their base LLM to further improve inference-time performance.

Agentic AI systems are increasingly deployed to process sensitive data at inference time, such as healthcare records or financial documents assembled into a hidden context before the system answers. Prior work has studied privacy risks primarily through jailbreaking attacks that induce models to directly disclose sensitive content, but has largely overlooked the agentic setting where the context is assembled by the agent's own tool calls. We show that the agents we evaluate remain vulnerable to hidden-context leakage despite the controls we test against them, namely an instruction not to disclose the context, logit suppression, and context dilution. For instance, a web-browsing agent answering benign user queries still carries exploitable signals about records silently loaded into its context. We introduce and formalize context-inference attacks through a security game and evaluate three settings under decreasing attacker knowledge and increasingly indirect delivery of the context: a known context, an unknown context, and a context the agent retrieves through its own tool calls. We distinguish a grey-box setting, in which the target model is used to score observations, from black-box settings in which the attacker scores with a surrogate it controls. We further characterize how leakage varies with query budget, context size, and target-model size. A single attack carries through all three settings without modification, reaching $100\%$ ASR on small candidate sets and $63\%$ at $1024$ candidates against a known context, $78.9$ AUROC when the template and surrounding records are unknown, $92.5$ AUROC when a 14B surrogate scores a 32B target, and $81.8$ AUROC when the records arrive as an agent's retrieval returns, against chance rates of $1/|\mathcal{Z}|$ and $50$ respectively.

Better probability scores do not establish that evidence has been counted correctly. Repeated inference over one observation can improve predictions without adding an evidential origin. Source-local numerical attributes alone cannot in general distinguish repeated derivations from separately countable acquisitions. PACT (Provenance-Aware evidence Conservation and Typed action admission) separates evidence magnitude from countability through a supplied provenance partition. Under singleton fidelity and insertion non-amplification, the coordinatewise meet is the unique pointwise greatest admissible within-component rule. Component budgets add under stated commensurability and separate-component additivity assumptions. Matched reassignments hold numerical outputs fixed while varying the counting relation. In four of 12 replicated-source tests on HandWritten, false refinement lowers macro-averaged negative log-likelihood and Brier score while increasing normalized common-support area under the risk-coverage curve (ncsAURC). In the controlled handover benchmark, removing the constructed adversarial-consensus condition leaves a 0.056 reduction in ncsAURC for provenance-partition aggregation relative to singleton aggregation under the same score functional. The corroboration contrast disappears, and method ranking remains selection-score dependent. In offline, reference-based human-robot collaboration with four prompts per camera and all other admission inputs fixed, duplicating each prompt output within its camera from multiplicity one to eight leaves all 720 PACT typed responses per checkpoint unchanged. Probability quality and evidence countability require separate evaluation.

Production deployments of large language model (LLM) agents remain unreliable on long, multi-step workflows even as benchmark success rates climb steadily. We argue this gap is largely an artifact of task horizon: benchmarks are dominated by short-to-medium horizons where success remains high, while production workloads demand an order of magnitude more dependent steps. We measure the effect directly, characterizing the shape of agent degradation and disentangling its cause across a large controlled study spanning nine models, six open models from 1.2B to 671B parameters, and three deployed proprietary systems; four task families, including a genuinely agentic tool-use loop; five horizons; and three context regimes. Task success follows a geometric law governed by a single per-step reliability parameter, which rises with model scale but saturates well below 1 even for the strongest models, guaranteeing eventual collapse at sufficiently long horizons. The effect is sharpest on the agentic task, where every model tested, including widely deployed systems, falls from near-perfect success to near zero within sixteen steps of (n=10,664 analyzed trajectories. Degradation is driven by step count rather than context length: bounding the context window steepens decay rather than easing it (logit slope -0.69 vs. -0.44), p=3x10-6), contradicting a lost-in-the-middle explanation and warning against a common production shortcut. Projecting measured reliability onto representative benchmark horizons quantifies a substantial gap between benchmark and production conditions, from 0.42 at GAIA-length horizons to 0.24 at hundred-step production horizons. For teams responsible for agent orchestration and reliability at scale, these results argue for horizon-aware evaluation and reliability budgeting in place of aggregate pass-rate metrics. Code, prompts, seeds, and raw trajectories are released.

Chain-of-thought (CoT) reasoning powers generative models by eliciting intermediate steps before producing an answer. In autonomous driving, the answer is a continuous action. Thus its reasoning must share the same spatiotemporal structure as the physical world. This survey studies the resulting shift from textual CoT to action-grounded reasoning. Surveying 171 papers, including 130 method papers and 41 benchmarks, datasets, surveys, and analysis papers, we propose a representation-centered taxonomy that treats the form of the intermediate state as the organizing axis. We systematize the 130 methods into four categories: language-based, visual-spatial, latent-dynamic, and externalized reasoning, further divided into 13 subtypes tied to distinct regions of interests. Our synthesis shows that the open frontier of reasoning in driving agents lies in intermediate representations that can be grounded in the real world, coupled to real-time action, and verified under safety-critical systems. Project page: https://github.com/tangzhengxu/awesome-av-cot.

Retrieval-Augmented Generation enhances Large Language Models by grounding responses in external knowledge, but multi-hop reasoning remains vulnerable to error propagation, where early retrieval failures confound subsequent steps. Standard outcome-based optimization only rewards the final answer, leaving intermediate retrieval and reasoning errors undetected. While existing process-based methods introduce step-level signals, they still score each step against the final answer, rewarding spurious successes where flawed retrieval coincidentally produces the correct answer. Step-level supervision in RAG requires evaluating both logical validity and evidential grounding at each step. We introduce PRO-STEP: we train a generative PRM that evaluates both dimensions, employ PRM-guided value tree search to construct preference pairs contrasting valid steps against flawed ones, and optimize the policy via step-level Direct Preference Optimization. Experiments on single and multi-hop QA datasets demonstrate that PRO-STEP achieves the best average EM and F1 across five benchmarks. Code, models, and training data are publicly available at https://github.com/keemminnke/PRO-Step.

Multimodal models often build on architectures designed for generative vision-language modeling, typically combining separately pretrained vision encoders with causal language models. Visual document retrievers such as ColPali repurpose these models as encoders, carrying over the parameter and compute overhead of a VLM for a non-generative task. We introduce NeoMME, a family of 260M and 800M-parameter Multimodal and Multilingual bidirectional Encoders that process multilingual text and raw image patches in a single bidirectional Transformer encoder. Both models are pretrained from scratch with a masked discrete-diffusion text objective, conditioned on visible image patches for multimodal examples. Both support a 16,384-token context, enough to encode up to two standard 4K UHD images. To demonstrate its downstream capabilities, we fine-tune NeoMME with jointly trained dense and late-interaction heads. On the ViDoRe v3 benchmark, the resulting NeoMME-Retriever 260M outperforms all evaluated models strictly below 800M parameters with 0.523 nDCG@10, while NeoMME-Retriever 800M reaches 0.556. At a matched 2048x2048 image input size on an NVIDIA L40S, NeoMME-260M encodes pages with about 2x the throughput of ColModernVBERT. Hierarchical token pooling and asymmetric quantization compress late-interaction multimodal document embeddings by 255x while preserving over 95% of baseline nDCG@10. We contribute NeoMME to Hugging Face Transformers and release the pretrained backbone and retrieval-compatible checkpoints under Apache 2.0 at https://hf.co/collections/Hcompany/neomme.

Unified recommendation models aim to jointly model non-sequential multi-field features and sequential user behaviors, but existing interaction-centric designs mainly focus on mixing heterogeneous tokens within each layer. We argue that scalable unified recommendation also requires controlling how intent information is carried, filtered, and preserved across stacked blocks. Inspired by flow-based representation dynamics, we introduce feature transport, a view that treats deep unified recommendation as a discrete context-conditioned representation evolution process. We propose CRAFT, a Contextual Residual Adaptive Feature Transport block, which summarizes non-sequential features into a reliability-aware contextual field and uses it to generate residual displacement and memory-preserving signals for intent and sequence representations. In this way, non-sequential context acts as an active controller of representation evolution rather than a passive object of interaction. In the TAAC2026 advertising recommendation competition, CRAFT achieves a test AUC of 0.838090, surpassing the previous leaderboard-best score of 0.83798. Scaling experiments further show that CRAFT benefits from both depth and width expansion: stacking CRAFT to six blocks improves test AUC to 0.838148, while increasing the hidden dimension reaches 0.838106. These results demonstrate the effectiveness, scalability, and generalization potential of the feature transport paradigm. Source code: https://github.com/AshleyLuo001/CRAFT

Existing text-video retrieval datasets primarily consist of short-form clips containing a single dominant event. While suitable for measuring basic vision-language alignment, they are limited in capturing real-world retrieval scenarios, where long-form videos naturally contain multiple semantically distinct events and a single text query may correspond to several non-contiguous temporal segments. To bridge this gap, we introduce MELON, the first large-scale dataset designed to extend text-video retrieval to long-form videos featuring complex, multi-event structures. MELON explicitly annotates multiple event intervals per video along with their corresponding textual descriptions, enabling both training and evaluation of multi-event understanding in long, untrimmed videos. In addition, we propose a multi-event aware loss that encourages models to differentiate between full-event and partial-event matches, yielding substantial improvements in retrieval accuracy. Together, the MELON dataset and our proposed loss establish a robust foundation for expanding text-to-video retrieval to complex long-form scenarios and provide a more realistic evaluation setting for future research in the field.

Recommender systems in two-sided matching platforms are commonly optimized for immediate engagement signals such as click-through rate, reply rate, or the total number of successful matches. However, in real-world marketplaces, maximizing matches alone may be misaligned with business goals such as user churn rate and platform revenue, especially when users with fewer matches are at substantially higher risk of churn. In this paper, we study a real job matching platform and show that users with very few recent matches are indeed much more likely to leave the platform, while additional matches for already successful users provide limited marginal value for retention. Motivated by this empirical finding, we formulate a retention-aware recommendation problem and implement a simple post-processing method that adjusts the baseline match-focused ranking to prevent user churn. Specifically, the implemented method gives a score boost to churn-risk users with the goal of increasing their likelihood of obtaining matches and improving retention. We evaluate this practical approach in an online experiment on a real job-matching platform. The treatment group showed directionally lower user churn than the control group, although the estimated effect was not statistically significant at conventional levels, while company-side churn showed no evidence of deterioration. To our knowledge, this is among the first online experimental studies to investigate retention-focused recommendation in a real reciprocal job-matching platform.

We investigate the expressive power of fixed-point logics (FP) and their extensions in defining generating sets for accessible subgroups of definable permutation groups. This operation, computable in polynomial time via the Schreier-Sims algorithm, plays a central role in the group-theoretic approach to Graph Isomorphism and Graph Canonisation. In particular, it underpins polynomial-time canonisation for bounded colour-class graphs–a class for which no natural logic capturing P is currently known. We first show that this operation cannot, in general, be expressed in any logic for P. This limitation arises from the fact that accessible subgroups need not admit symmetric generating sets of polynomial size. However, we prove that when the base group admits a definable ordered generating set, the accessible subgroup operation becomes definable in fixed-point logic with the group order operator (FP + ord). This is achieved by partially simulating the Schreier-Sims algorithm within FP + ord. As a corollary, we show that fixed-point logic with counting (FPC) can also define the operation when the base group is abelian. In particular, FPC can define the automorphism group of any graph with abelian colours–despite being unable to canonise such graphs.

Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal behavior, semantic resemblance, and intent-matching heuristics that emphasize linguistic plausibility rather than correctness. We identify a key limitation in existing evaluations: many jailbreak intents depend on instructional validity rather than epistemic factuality, allowing realistic-looking responses to be labeled successful despite being factually or procedurally incorrect. To address this gap, we propose Sequential Epistemic and Action-Level Validation (SEAV), a verification-centric jailbreak evaluation framework that decomposes responses into ordered steps and evaluates both validity and correctness. SEAV combines LLM-as-a-judge mechanisms for semantic interpretation with retrieval-grounded verification using external knowledge sources, assessing whether generated content is factually correct, structurally consistent, and operationally capable of advancing harmful objectives. Empirically, SEAV cuts the false-positive rate on SD-A (a curated strategic-dishonesty diagnostic) by 14.9\,pp vs. the strongest baseline, and reclassifies 22.1%–51.0% of sampled prior-labeled successes as invalid across three of four public benchmarks. Together, these results show that enforcing correctness substantially reshapes measured robustness: many previously labeled jailbreak successes are reclassified as invalid, and results are stable across the tested search backends and evaluator models. Code and data are available at https://github.com/Ardor-Wu/SEAV.

Conventional power-system stability analysis is largely centralized and centered on a single equilibrium point, which becomes increasingly restrictive in the presence of large-scale fluctuating renewable generation. This paper develops a decentralized framework for stability analysis and control that certifies the asymptotic stability of an equilibrium set rather than that of a given single operating point. To this end, we introduce a new notion termed input–output differential passivity (IODP), which decomposes equilibrium-set stability of the interconnected system into local requirements imposed on individual devices. These requirements are formulated without embedding a particular operating equilibrium into the local conditions; once the certified regions are constructed, stability verification for a given operating scenario reduces to checking whether its equilibrium lies in the certified set. The proposed conditions require each bus to possess a sufficient level of IODP, quantified by an IODP index. To compensate for an IODP shortage, we further develop an I/O-transformation-based passivation controller that reshapes the local input–output behavior of the corresponding device. In this way, all grid-connected components can be made to satisfy the decentralized conditions for system-wide stability. The proposed framework is validated on a modified IEEE 39-bus system. Simulation results demonstrate that it provides a scalable and equilibrium-set-oriented solution for stability certification and control under highly variable operating conditions.

Diffusion large language models (dLLMs) generate text through iterative denoising rather than left-to-right decoding. This generation paradigm introduces two axes that can influence safety alignment: when tokens are generated during denoising and where they appear in the response. In this paper, we measure dLLM safety behavior under harmful prompts by tracing intermediate token distributions and commitment decisions throughout denoising. Our analysis shows that refusal signals are concentrated in early denoising steps and leading response positions, and the tokens committed early can strongly shape the final safety outcome. Our measurements further show that the denoising step and persistence of refusal-token commitment are important for understanding dLLM safety. Based on these findings, we propose Refusal-Aware Early Commitment (RAEC), a simple training-free decoding method that commits persistent refusal signals from early steps. Experiments on LLaDA and Dream show that RAEC reduces attack success rates while largely preserving utility. The code is available at https://github.com/Glresearch1/RAEC.

LLM-based factuality judges provide scalable evaluation signals, but their metrics are often systematically biased relative to human judgments. We study human-anchored factuality evaluation under limited annotation budgets, where judge predictions on the full dataset are combined with human labels on a small selectively sampled subset to obtain statistically valid estimates. The efficiency of this approach depends critically on which examples receive human annotation: in factuality evaluation, judge-human misalignment is not driven solely by low confidence, but also by structured failure modes such as incomplete evidence, temporal mismatch, unverifiable claims, and rubric misalignment. To exploit this structure, we introduce a factuality-specific annotation policy design pipeline that uses failure-space analysis (FSA) to derive diverse predictive signals for modeling human-judge misalignment. On an internal reference-based factuality evaluation system (AutoFA) and RAGTruth, where judge-predicted estimates substantially underestimate human-annotated factual accuracy, our FSA-guided policy improves annotation efficiency over uniform sampling and uncertainty-driven baselines, achieving effective-sample-size gains of 40.3% on AutoFA and 27.1% on RAGTruth.

Both privacy and factual accuracy are paramount in high-stakes domains like healthcare. Concerningly, we uncover and investigate a privacy-hallucination tradeoff in differentially private (DP) language models. First, we empirically show that models pre-trained or fine-tuned with DP tend to produce more hallucinations than non-DP counterparts, with increased severity as the privacy budget grows stricter. Second, we investigate model properties driving this tradeoff, demonstrating that DP mechanisms flatten output distributions, potentially redistributing probability mass toward factually incorrect alternatives. Third, through experiments where we control fact frequency in training data, we characterize how information frequency can reduce hallucination risks in DP models. Overall, our findings underscore the need for more nuanced privacy-preserving interventions that offer rigorous privacy guarantees without compromising factual accuracy.

Communicating across cultures is inherently challenging, especially through culturally dense and ambiguous formats like memes. While people expect large language models (LLMs) to hold promise for bridging such gaps, existing benchmark datasets often fail to capture the cultural context necessary for accurate interpretation. To address this, we introduce MemeBridge, a curated dataset centered on U.S.-originated memes, designed to capture two complementary perspectives: (1) how Chinese participants interpret these memes, and (2) how U.S. participants anticipate how people from other cultures might misunderstand them. Here, context refers to implicit cultural knowledge, including background beliefs, norms, and shared assumptions that shape meme comprehension. The dataset was constructed via a multi-stage crowdsourcing pipeline with rigorous validation, including human agreement checks and GPT-based classification verification. Each meme is annotated with sentiment, emotion, cultural significance, and knowledge type, providing rich supervision for downstream tasks. Notably, we observe that the anticipated misunderstandings from U.S. participants are often inaccurate, highlighting the asymmetries in cultural understanding and the challenges of adopting perspectives beyond one's own. This bidirectional framing, which focuses on both expression and perception, enables more nuanced benchmarking of cross-cultural comprehension. Our probing of multiple LLMs reveals that while models developed in different cultural contexts exhibit partial cross-cultural understanding, they often struggle with sophisticated interpretations. By contrast, fine-tuning with MemeBridge improves model performance, underscoring the value of culturally grounded resources for training and evaluating LLMs in globally diverse settings.

This work studies hybrid quantum-classical neural networks for learning routing heuristics. Specifically, this paper asks whether small quantum neural networks can replace parameter-heavy modules inside a competitive attention-based routing model while maintaining solution quality. For the capacitated vehicle routing problem, encoder feed-forward replacement emerges as the most promising design: it reduces the number of model parameters by 56.6% while keeping the hybrid model close to the classical neural baseline at small and medium instance sizes, although the gap grows for larger instances. This work also compares to classical routing algorithms, which remain highly competitive and often superior on the fixed Euclidean test sets. Our results therefore do not indicate quantum advantage or solver dominance, but identify encoder feed-forward replacement as a viable hybrid-module compression strategy for neural combinatorial optimization.

Machine learning interatomic potentials bridge the gap between quantum chemical precision and classical computational speed, enabling molecular dynamics simulations with first-principles accuracy. Their reliability is often improved through active learning, which iteratively expands the training set by identifying uncertain, out-of-distribution configurations. Existing uncertainty-quantification methods often involve a trade-off between computational cost and reliability, and generally cannot account for redundancy as an acquisition batch is assembled. Here, we introduce AdaptNTK, a single-model framework that measures uncertainty as a regularized Mahalanobis distance in empirical neural tangent kernel (NTK) feature space. With the NTK features fixed during acquisition, the uncertainty depends on the acquired configurations but not their reference labels. This allows the uncertainty to be updated recursively after each selection without retraining, reducing redundancy within an acquisition batch. On held-out rMD17 data, AdaptNTK achieves the highest mean correlations with force errors (Spearman 0.68, Pearson 0.71) and matches a three-member ensemble in error retention. In active learning experiments, AdaptNTK achieves the lowest force errors across rMD17 and Transition-1X, with particularly strong performance on transition-state configurations in Transition-1X. AdaptNTK provides a 2.6-fold speedup per Transition-1X cycle relative to the ensemble, providing efficient single-model uncertainty estimation with sequential updates for data-efficient active learning.

Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making multi-turn attacks one of the least understood failure modes of large language models. Most automated red-teaming methods treat this as a generation problem: produce attacks that break the model. We argue it is better framed as a search problem: discover, organize, and iteratively refine a diverse archive of attack strategies, producing a structured map of how a target model fails rather than a list of one-off successes. We introduce EvoFlint, which applies evolutionary quality-diversity search to multi-turn red-teaming. Attack strategies are phased conversation plans, not raw prompts, and are evolved through LLM-driven mutation and crossover. A Pareto fitness over attack success rate and peak severity preserves selection signal from near-miss attacks. A risk-indexed archive runs novelty search with local competition over strategy description embeddings inside each cell, maintaining diversity without committing to a predefined style taxonomy. A generation-level memory accumulates target-model insights across the population and feeds them back into strategy generation. On the HarmBench-test split, EvoFlint reaches attack success rates of 35.8% on Claude Sonnet 4.6, 59.7% on GPT-5.4, and 94.3% on Qwen3-32B, alongside 98.7% on the older GPT-4o included as a baseline reference. The resulting archive, organized by risk category, exposes for each target which categories of harm its safety training has and has not covered.

In the approval-based committee selection problem, a committee is said to be in the core if no subset of voters has an incentive to deviate by selecting a blocking committee of proportional size, such that every voter in the deviating group strictly prefers the blocking committee. We consider the setting where candidates can be selected fractionally. Under a mild regularity assumption, we show that there always exists a weighting of candidates such that the fractional committee maximizing the candidate-weighted Nash Social Welfare is in the core. We refer to such a solution as being in the Nash core. Additionally, we show that a Nash core solution admits a payment assignment between voters and candidates, where each voter pays a candidate they approve in proportion to the weight. For the discrete setting, where each candidate is either included or excluded from the committee, we prove that every approval-based committee election with at most eight equally weighted voters has a core committee by rounding the fractional Nash core solution. Although the non-emptiness of the core in this setting remains an open question and checking core membership is coNP-hard, we extend the notion of the Nash core to the discrete case, yielding a formulation that is efficiently verifiable and offers a promising path toward establishing core existence in discrete settings. Finally, we test our approach on real voting data using a payment-guided heuristic. We empirically show that the Nash core solution can be efficiently computed through an iterative algorithm in both the fractional and discrete settings.

The history of extremum seeking is not merely the history of an algorithm; it is the history of an idea. Few ideas in control engineering have demonstrated the remarkable longevity of extremum seeking control (ESC). Invented more than one hundred years ago, ESC has continually reinvented itself while remaining faithful to its original objective: enabling systems to optimize their performance without relying on accurate mathematical models. This perspective article proposes that the evolution of ESC is best understood through three scientific revolutions. The first Engineering Revolution (1922-1999) established the engineering principles of model-free optimization; the second Mathematical Revolution (2000-2010) provided the rigorous mathematical foundations that transformed ESC into a mature discipline of nonlinear control; and the third ongoing Infinite-Dimensional and Cyber-Physical Revolution (2010-present) continues to expand its scope toward delays, partial differential equations, distributed optimization, event-triggered implementations, and increasingly complex cyber-physical systems. Beyond recounting this historical evolution, we offer a personal perspective on why ESC has remained relevant across successive technological eras. We argue that its enduring influence arises because the fundamental engineering challenge has never changed: "how can a dynamical system learn to improve its own performance when the optimum is unknown?" As optimization, learning, and feedback control become increasingly intertwined, ESC appears uniquely positioned to contribute to a new generation of intelligent autonomous systems, pointing toward what may become the field's fourth scientific revolution.

Small leaderboard gaps are often interpreted as evidence that one language model is better than another, but their sign may depend on which benchmark items are included. We test this using item-level responses from five benchmarks and a family-label-free spectral approximation to multidimensional item-response theory (MIRT). In owner-disjoint folds, one owner half identifies items with low residual differential item functioning across model families (low-DIF). These items are used to score models in the other half with frozen weights that preserve the benchmark's composition across metadata-defined item groups and easiness strata. Equally short matched-random subtests provide a baseline for variation due to item subsampling. Full-benchmark and low-DIF rankings remain strongly correlated ($\tau_b=.900$–$.948$). Yet in four of five benchmarks, 30.9–47.1% of cross-family pairs initially within one percentage point reverse order, exceeding their matched-random medians by 16.9–28.6 percentage points (all $p=.001$). The fifth benchmark shows no reliable excess ($-0.9$ points, $p=.689$). The pattern survives all pre-specified population perturbations, and residual item–family signatures replicate across owner halves; however, no family shows a consistent advantage across benchmarks. Thus, globally stable rankings can still leave individual near-tie orderings sensitive to benchmark composition, and sub-one-point leaderboard gaps should be accompanied by evidence that the implied ordering is composition-robust.

The number of people with age related physical or cognitive impairments is increasing due to the worlds ageing population. Technology has the potential to support independent living, and to achieve aged and health service efficiencies, however, there are gaps in our understanding of factors that motivate technology adoption and ongoing use by older adults, especially those with cognitive impairments. This study aims to explore motivators and enablers for technology adoption and ongoing use by older Australians with mild cognitive impairment (MCI) and their carers, to identify technology design principles and guidelines that maximise adoption. Semi structured interviews were used to gather data about individual demographics, needs, priorities, lifestyle, challenges, and experiences with technology. Results of inductive, reflective, thematic analysis indicate that a desire for independence, autonomy and quality of life motivate use of technology, and perceived technology self-efficacy and IT literacy are enablers. The Protection Motivation Theory illustrates that constant technology change is a disabler for technology adoption and sustained use, because it lowers perceived technology self-efficacy and IT literacy, and reduces confidence to use technology. Two high-level technology design principles and related guidelines are proposed, grounded in theory and aligned with Banduras four sources of self-efficacy. These design principles and guidelines are intended to increase feelings of self-efficacy and confident use of technology, while also reducing adverse impacts of technological change and encouraging sustained technology adoption by older adults with MCI to support independent living and quality of life.

For emerging scientific research domains, local Small Language Models (SLMs) are becoming more attractive, as they offer stronger privacy control and more stable deployment pipelines than Large Language Models. However, in practice, scientific question-answering on SLMs often operates under inevitable constraints: small literature collections, fragmented evidence, limited context window and reasoning abilities. We propose the Evidence-Grounded Typed Knowledge Graph (EGT-KG), a retrieval framework to improve information retrieval with local SLMs. We assessed three question-answering settings: a vanilla Retrieval-Augmented Generation (RAG) workflow and two EGT-KG workflows: an automatically generated relation schema (AS) and an expert-defined relation schema (ES). Our experiments were evaluated with a six-dimensional evaluation framework (S3CRF: Soundness, Correctness, Completeness, Conciseness, Relevance, Fluency) on a Biopolymer-bound Soil Composite literature benchmark, showing that EGT-KG outperforms the vanilla RAG method in most settings, with the best improvement from llama3:8b: a Final Score of 70.37 (+14.67%) and 68.82 (+12.14%) by AS/ES EGT-KG variants.

Gaze-based assistive manipulation typically supports object selection, while arbitrary-position placement requires accurate spatial alignment between the headset and robot. However, for gaze-based manipulation, pose accuracy does not necessarily translate into task accuracy: translational and rotational errors jointly affect the transformed gaze ray and may compensate for each other. To study cross-device alignment from this task-oriented perspective, we present a markerless interaction framework and a dedicated cross-device dataset. We propose Graph-based Reference Selection to address sparse robot references. We further develop and benchmark multiple task-specific alignment pipelines under a unified protocol. Specifically, we introduce Gaze–Surface Intersection Error (GSIE), which directly measures the spatial error of the gaze-specified target. Experiments show that alignment methods ranked highly by conventional pose metrics are not always optimal in GSIE, demonstrating the importance of evaluating gaze-based manipulation at the task level.