Biotech news from around the world
No abstract for this item (typically a correction, editorial or news piece — the publisher provides none)
Academic Intelligence · Curated Daily
AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.
No abstract for this item (typically a correction, editorial or news piece — the publisher provides none)
arXiv:2604.04089v3 Announce Type: replace-cross Abstract: Large language models can write scientific code, but direct paper-to-program translation remains fragile when correctness depends on tacit conventions in the literature. We identify this bottleneck as knowledge externalization: converting implicit computational assumptions – index conventions, gauge choices, fermionic signs, contraction order, and memory constraints – into an explicit technical specification before implementation. We evaluate a multi-stage, human-in-the-loop workflow that inserts such a specification, with validation and stop gates, between theory extraction and code generation. The workflow is tested on two algorithmically distinct quantum many-body tasks: variational sweep-based Density-Matrix Renormalization Group (DMRG) from a pedagogical review and constructive Pfaffian conversion of Hartree–Fock–Bogoliubov states to matrix product states from the five-page Letter by Jin et al., Phys. Rev. B 105, L081101 (2022), for which no public code is available. For DMRG, all 16 specification-guided model pairings in a $4\times4$ grid satisfy physics-validation criteria, compared with 6/13 direct attempts. A prose-specification ablation indicates that externalized content, not \LaTeX{} formatting, is the essential ingredient. For Pfaffian-MPS, the workflow succeeds in 11/26 archived attempts, whereas direct prompting yields zero audited passes. Cross-specification transfer is asymmetric: non-GPT specifications implemented by GPT~5.5 pass 4/4, while GPT~5.5 specifications implemented by weaker models fail 4/4, indicating a residual implementation-model bottleneck. The resulting Paper-to-Program Many-Body skill provides an auditable protocol for AI-assisted implementation of many-body algorithms and for diagnosing where externalization succeeds or fails.
LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be correct. While most abstention methods decide to withhold outputs before or after generation, dynamic mid-generation abstention considers early termination of unpromising reasoning traces at each token position. Prior work has explored empirical variants of this idea, but principled guidance for the abstention rule remains lacking. We present a formal analysis of dynamic abstention for LLMs, modeling abstention as an explicit action within a regularized reinforcement learning framework. An abstention reward parameter controls the trade-off between compute and information. We show that abstaining when the value function falls below this reward strictly outperforms natural baselines under general conditions. We further derive a principled and efficient method to approximate the value function. Empirical results on mathematical reasoning and toxicity avoidance tasks support our theory and demonstrate improved selective accuracy over existing methods.
arXiv:2606.15455v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key approach for enhancing the reasoning abilities of large language models. However, RLVR often suffers from diversity collapse: Pass@$1$ improves while high-$k$ Pass@$k$ degrades, which is viewed as a narrowing of the model's reasoning boundary. We formalize this diversity collapse through the lens of overtraining: once a problem's contribution to the reference metric has effectively saturated, further updates no longer expand what the model can solve but still concentrate probability mass on the trajectories favored by on-policy sampling. Under a standard setup with few rollouts per problem, even a single observed success places a problem in a nearly saturated regime for high-$k$ Pass@$k$, so most updates in standard RLVR are overtraining from the boundary perspective. This perspective also suggests a reading of whether RLVR can expand the model's reasoning abilities beyond the base model: since RLVR is structurally biased against high-$k$ Pass@$k$, its aggregate decline does not by itself mean that no new reasoning gains occurred. Interventionally, restricting updates to problems with zero observed success lifts Pass@$256$ above the base model on difficult benchmarks; observationally, a non-trivial fraction of initially unsolvable problems become solvable during standard RLVR training. Building on these findings, we propose Bayesian Boundary Gating (BBG), which redirects optimization away from overtraining by estimating each problem's marginal contribution to the reasoning boundary. Across multiple reasoning benchmarks, BBG improves average Pass@$k$ across a wide range of $k$.
arXiv:2606.17727v1 Announce Type: new Abstract: Recent vision-language models (VLMs) have shown promising progress in generating webpages from visual inputs, yet existing evaluations mainly focus on short, single-screen, and largely static webpages. We introduce LongWebBench, a benchmark for evaluating long-horizon webpage generation from both structural and functional perspectives. LongWebBench contains 490 real-world long webpages for structural fidelity evaluation and 507 goal-oriented interaction tasks over 129 webpages for functional evaluation. It employs two complementary protocols: a multi-dimensional VLM-based metric for assessing long-range structural coherence, and a DOM-augmented agent-based pipeline for end-to-end functional verification. We further examine the automatic evaluation protocols through human agreement analysis. Experiments with state-of-the-art open-source and proprietary VLMs under single-image and multi-image settings reveal that structural fidelity degrades as webpage length increases, while visually plausible generations often fail to support executable multi-step interactions. These results highlight the need to evaluate long webpage generation beyond visual similarity, with executable interaction as a core criterion. Our code and data are available at https://github.com/zheny2751-dotcom/LongWebBench.
Early-life exposures are important to several late-life health outcomes. We sought to study the effect of an in utero nutritional environment and its interaction with Alzheimer's disease (AD) genetic risk on late-life cognitive function. We used a natural experiment created by the pellagra epidemic, a nutritional disease caused by a vitamin B3 deficiency, to evaluate the association between in utero pellagra epidemic exposure and late-life cognitive function in the Health and Retirement Study (N = 18,285). We also evaluated whether the in utero exposure could modify the AD polygenic score's (PGS) effect on cognition. In utero pellagra epidemic exposure was significantly associated with cognition ({beta} = -0.025). However, these effects were not isolated to the prenatal period as exposure during childhood periods also had an effect. The interaction between the in utero exposure and the AD PGS was significant, where the genetic effect on cognition was amplified with increasing (progressively worse) in utero exposure levels. These associations imply that the early-life nutritional environment affects late-life cognitive function and that these effects can modify genetic risk.
Phone agents are increasingly expected to complete real mobile workflows rather than merely predict the next screen action. However, much of the current mobile-agent literature still evaluates agents primarily as GUI controllers that observe a screen, emit taps and swipes, and are scored by target app state. Real phone-use tasks are broader: they require deciding when to use app GUIs, device-side commands, or structured tools, while leaving evidence that the intended side effect actually occurred. We introduce PhoneHarness, a mixed-action benchmark and execution harness for studying phone-use agents on verifiable mobile workflows. PhoneHarness runs a device-side agent loop over GUI, CLI, and host-side tool actions, combining deterministic action routing with bounded GUI delegation and auditable execution traces. Its benchmark, PhoneHarness Bench, evaluates whether agents complete tasks with observable side effects, not only whether they produce plausible final answers. On the annotated evaluation split, PhoneHarness reaches a 75.0% pass rate, outperforming the strongest non-PhoneHarness settings by 12.9 percentage points. PhoneHarness and PhoneHarness Bench therefore play distinct but mutually dependent roles: the harness makes mixed phone workflows executable, while the benchmark measures whether agents can use that harness reliably and safely. Our findings suggest that reliable phone automation depends on action-surface routing and verifiable execution, not only visual GUI control.
Vision-language models (VLMs) are playing an increasingly important role across multiple domains. In many applications, such as robotics, it is crucial to quantify the uncertainty in the output of these models. } We develop FUSE, a probabilistic framework for capturing two complementary sources of uncertainty in vision-language modeling: (i) aleatoric embedding-level uncertainty derived from input data vision-language ambiguity, and (ii) epistemic model-level uncertainty estimated from the semantic response diversity of VLMs. Our approach formulates a Bayesian fusion mechanism that analytically combines these uncertainty sources to produce a scalar measure of uncertainty. This measure can be used to reliably predict the model's output correctness for downstream applications. We demonstrate that our method outperforms baselines and achieves SOTA uncertainty calibration.
In-Context Learning (ICL) has become a powerful mechanism for adapting Large Language Models (LLMs) to new tasks without fine-tuning. Extending this concept to Large Multimodal Models (LMMs), Multimodal In-Context Learning (M-ICL) relies on retrieving relevant examples, such as images, captions, or question-answer pairs, to guide predictions across tasks like classification, captioning, and visual question answering (VQA). Most existing approaches select in-context examples based on feature-space similarity, assuming that semantically similar samples provide the most useful context. However, our systematic analysis reveals that this assumption does not always hold: visually similar examples are not necessarily those that most effectively enhance in-context learning performance. To address this, we propose the Guided Retrieval of In-context Prompts (GRIP), a learnable vision-only retrieval framework that leverages feedback from LMMs to identify examples that truly improve model predictions. GRIP learns to distinguish beneficial from detrimental in-context examples through contrastive training, refining retrieval beyond pure similarity. Across three multimodal tasks, namely classification, captioning, and VQA, GRIP improves consistently over similarity-based retrieval on Qwen2.5-VL-7B, with its strongest gains in classification on Idefics2-8B. Moreover, we demonstrate that retrievers trained with feedback from one open LMM can be transferred to other models without retraining, including closed-source GPT-4o and Gemini, enabling scalable and cost-efficient deployment of M-ICL. Code will be published upon acceptance.
arXiv:2606.20283v1 Announce Type: cross Abstract: Graph neural networks (GNNs) excel at aggregating neighbor information for classification, yet their performance is hindered by graph structural entanglement, where spurious correlations from semantically irrelevant neighbors contaminate node embeddings. This challenge is most acute for nodes near class boundaries in the embedding space, where amplified structural noise blurs decision boundaries and destabilizes predictions. Existing robust GNN methods largely treat all nodes uniformly, ignoring boundary vulnerabilities. In this paper, to improve classification performance, we tackle graph structural disentanglement by identifying boundary-region entanglement as the primary bottleneck and propose Boundary Embedding Shaping (BES), an adaptive contrastive learning GNN plug-in module that selectively suppresses spurious structural noise at decision boundaries with minimal model parameter perturbation. Extensive experiments demonstrate that BES consistently improves boundary discrimination and outperforms existing leading methods. Notably, BES boosts GCN performance by an average of 3.3% in node classification (up to 5.0% on WikiCS) and achieves superior accuracy in link prediction.
arXiv:2606.17886v1 Announce Type: new Abstract: Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are known to respond monotonically to certain inputs. Existing approaches are MLP- or flow-based and lack per-edge functional transparency; the only Kolmogorov–Arnold Network (KAN) variant with monotonicity, MonoKAN, enforces the constraint only on a restricted parameter subset and requires a projection-style training procedure. We close this gap with MKAN, a KAN with hard monotonicity guaranteed for all parameter values via exponential reparameterization of B-spline coefficients, positive edge weights, and a monotone base activation. Training reduces to standard unconstrained gradient descent. Our headline theoretical contribution is a representation-cost theorem: any $C^K, K >0$ feature extractor inducing a ball-shaped semantic-neighborhood partition admits a monotone realization of the equivalent neighborhood structure at $N' = N^* + k \le 2N^*$, where $k$ is the number of non-monotone coordinates of the original. The bound is architecture-agnostic and gives a principled sizing rule for monotone encoders. Empirically, MKAN is competitive with state-of-the-art monotone NNs on the SMM/ICML-2024 benchmark while being the only method that combines hard unconstrained monotonicity with KAN's per-edge functional transparency; the $2N^*$ prediction is validated in a self-supervised feature-size sweep on four real datasets, and on a controlled monotone-generative dataset MKAN recovers ground-truth factors with substantially higher Spearman alignment than KAN, MLP, and linear baselines.
The Frechet Inception Distance (FID) is the de facto arbiter of image generation, yet most papers report just a single number from a single trained model using a single sampling seed. How reproducible is that number if we retrain the model, or merely resample from it? In this paper, we treat FID as a random variable on a two-axis panel of training and generation seeds, and measure its variance directly on several hundred SiT networks trained on class-conditional ImageNet 256x256. We report surprising findings: (a) Retraining the model using the same recipe with a different seed moves FID 3.2x more (in Inception feature space) than redrawing samples from a fixed network. (b) That gap is driven by three factors: random initialisation, data ordering, and the per-step Gaussian noise of the flow-matching loss. (c) Increasing compute or model size barely tightens the spread, holding the FID coefficient of variation (CoV) inside a 1-2% band. (d) Per-cell classifier-free-guidance tuning halves the spread but reshuffles which seeds work best, and a lucky training seed reaches the same FID with up to 2x less compute than an unlucky one. Based on these findings, we recommend a new FID evaluation protocol: evaluate under per-cell optimal guidance, treat any FID gap below the empirically measured ~1.3% CoV as inconclusive, and report an error bar over several training seeds rather than a single FID number.
arXiv:2606.20461v1 Announce Type: new Abstract: Machine learning models have been shown to exhibit discriminatory outcomes or degraded performance for individuals at the intersection of multiple sensitive attributes, such as race and gender. This stems in part from two interrelated challenges: the lack of principled measures for quantifying bias (potentially intersectional), and insufficient representation of intersectional subgroups in training data. We extend a recent bias mitigation framework to incorporate coverage constraints that enforce sufficient representation across groups, including intersectional subgroups. Since achieving exactly zero bias for all groups may not be data efficient (meaning it may require large amounts of data), our solution trades small approximation errors in bias for greater data efficiency while satisfying coverage constraints. We also formulate bias mitigation as an integer linear program that optimizes over all mitigation strategies, and characterize the price of fairness, the minimum data modification cost, as a function of fairness tolerance. This is essential both for legal compliance, where regulations may mandate specific fairness thresholds, and for data governance, enabling practitioners to make informed trade-offs between bias reduction and data modification (particularly, data purchasing) costs. We evaluate our techniques on publicly available datasets, demonstrating that bias mitigation via our framework preserves predictive accuracy across multiple classifiers, and that coverage constraints, while motivated by statistical considerations, are essential for preserving downstream ML performance.
Background: Older adults with vision impairment often experience barriers to using digital technology. The indirect associations between vision impairment and digital access and skills via digital self-efficacy and frustration among older adults remain largely unknown. Objective: This study aimed to 1) explore factors associated with digital access, skills, self-efficacy, and frustration among older adults with vision impairment; 2) examine associations between vision impairment and digital access, skills, self-efficacy, and frustration among older adults; and 3) examine whether digital self-efficacy and frustration may help explain associations between vision impairment and digital access and skills among older adults. Methods: This was a cross-sectional study using nationally representative data from the Health Information National Trends Survey (HINTS) 2024. Respondents aged 60 and older were included. Vision impairment was assessed using a self-reported item. Outcomes included self-reported digital access, skills, self-efficacy, and frustration. Survey-weighted multivariable logistic regression and generalized structural equation modeling were conducted, adjusting for age, sex, race/ethnicity, education, and the number of comorbidities. Results: Among 3,149 older adults (mean [SD] age, 70.7 [10.0] years; 45.6% female), 7.1% (n=223) reported vision impairment. Among older adults with vision impairment, 65.6% (95% CI, 53.5% to 75.9%) used the internet daily, and 79.5% (95% CI, 66.8% to 88.2%) used a smartphone in the past 12 months. In multivariable logistic regression analyses among older adults with vision impairment, older age was associated with lower odds of daily internet use (OR, 0.84; 95% CI, 0.79 to 0.90), smartphone use (OR, 0.85; 95% CI, 0.75 to 0.97), wearable device use (OR, 0.88; 95% CI, 0.79 to 0.97), and using the internet to send a message to a healthcare provider (OR, 0.87; 95% CI, 0.80 to 0.93). Older adults who self-identified as racial and ethnic minority groups (e.g., Black/African American, Hispanic) had lower odds of daily internet use (OR, 0.15; 95% CI, 0.05 to 0.50) and using the internet to send a message to a healthcare provider (OR, 0.17; 95% CI, 0.04 to 0.73) compared with Non-Hispanic White older adults. Vision impairment was associated with lower odds of daily internet use (OR, 0.60; 95% CI, 0.37 to 0.99) and digital self-efficacy (OR, 0.53; 95% CI, 0.32 to 0.86). Digital self-efficacy was associated with higher odds of daily internet use (OR, 2.95; 95% CI, 2.04 to 4.26). Generalized structural equation modeling identified an indirect association between vision impairment and daily internet use via digital self-efficacy (coefficient, -0.68; 95% CI, -1.24 to -0.12). Conclusions: Findings suggest that reduced digital self-efficacy may help explain the observed association between vision impairment and daily internet use among older adults. Interventions targeting digital self-efficacy, including accessible interface designs, personalized coaching, and peer support, may help bridge the digital divide among older adults with vision impairment.
Fairness in human-robot interaction critically depends on the reliability of the perceptual models that enable robots to interpret human behavior. While demographic biases have been widely studied in high-level facial analysis tasks, their presence in facial landmark detection remains unexplored. In this paper, we conduct a systematic audit of demographic bias in this task, analyzing the age, gender, and race biases. To this end, we introduce a controlled statistical methodology to disentangle demographic effects from confounding visual factors. Our analysis demonstrates that visual confounders, particularly head pose and face resolution, heavily outweigh the impact of demographic attributes. Notably, after accounting for these confounders, performance disparities across gender and race vanish. However, we identify a statistically significant age-related bias, with higher localization errors for older individuals. This shows that fairness issues can emerge even in low-level vision components and can propagate through the HRI pipeline. We argue that auditing and correcting such biases is a necessary step toward trustworthy and equitable robot perception systems.
arXiv:2512.03077v2 Announce Type: replace-cross Abstract: The accelerated development, deployment and adoption of artificial intelligence systems has been fuelled by the increasing presence of big tech in the AI field. This trend has been accompanied by growing ethical concerns and intensified societal and environmental impacts. This position paper argues that irresponsible AI development is strongly driven by big tech's influence and involvement in the field. First, we examine the growing and disproportionate influence of big tech in AI research and argue that its drive for scaling and general-purpose systems is fundamentally at odds with the responsible, ethical, and sustainable development of AI. Second, we review key current environmental and societal negative impacts of AI and trace their connections to big tech's influence. Third, we discuss the underlying economic forces driving big tech's actions. Finally, as a call to action, we invite AI researchers to counter big tech's influence in irresponsible AI development through strategies that build on the responsibility of implicated actors and collective action.
arXiv:2506.20668v3 Announce Type: replace-cross Abstract: We propose DemoDiffusion, a simple method for enabling robots to perform manipulation tasks by imitating a single human demonstration, without requiring task-specific training or paired human-robot data. Our approach is based on two insights. First, the hand motion in a human demonstration provides a useful prior for the robot's end-effector trajectory, which we can convert into a rough open-loop robot motion trajectory via kinematic retargeting. Second, while this retargeted motion captures the overall structure of the task, it may not align well with plausible robot actions in-context. To address this, we leverage a pre-trained generalist diffusion policy to modify the trajectory, ensuring it both follows the human motion and remains within the distribution of plausible robot actions. Unlike approaches based on online reinforcement learning or paired human-robot data, our method enables robust adaptation to new tasks and scenes with minimal effort. In real-world experiments across 8 diverse manipulation tasks, DemoDiffusion achieves 83.8\% average success rate, compared to 13.8\% for the pre-trained policy and 52.5\% for kinematic retargeting, succeeding even on tasks where the pre-trained generalist policy fails entirely. Project page: https://demodiffusion.github.io/
arXiv:2606.18140v1 Announce Type: cross Abstract: Electromagnetic finite element method (FEM) implementations using traditional basis functions struggle to accurately represent field behavior near singular features such as conducting wedges. To combat this, specialized singular basis functions have been introduced to directly model the singular fields in these regions, leading to substantially improved performance. While these efforts have been pursued extensively in 2D, few functions have been developed for 3D elements. In this work, we develop basis functions for this in tetrahedra. Unlike prior functions, these basis functions are additive, meaning they are included alongside the standard vector basis functions to achieve more robust performance. Further, these functions are designed to be adaptable to tetrahedra touching several unique singular features by using combinations of basis functions singular with respect to each node and edge in the element, making them applicable to highly complex geometries. Higher-order interpolatory versions of the basis functions for modeling singular behavior with greater accuracy are also provided. These basis functions lead to substantial improvements in accuracy relative to the standard basis functions, and allow otherwise expensive simulations to be performed at far lower costs. As an application example, we perform simulations to extract critical quantities for designing superconducting qubits that significantly depend on the behavior of singular fields. In Ansys HFSS, this took 21.27 hours and a peak memory usage of 6.23 TB with 800 processors available, while using our singular basis functions achieved comparable results in 196 seconds while using 27.24 GB of memory and only 16 processors. Due to these benefits, our singular basis functions could be applied to enable design optimization of electromagnetic geometries with dominantly singular behavior, such as superconducting qubits.
arXiv:2412.00107v2 Announce Type: replace-cross Abstract: Real-time monitoring of safety-critical interior states remains an open problem in energy systems where physical instrumentation is infeasible. Existing approaches rely on explicit governing equations, finite-dimensional state vectors, or per-instance retraining, which prevents mesh-independent, field-level inference at arbitrary interior coordinates under real-time constraints. We introduce operator-based virtual sensing for nuclear-grade thermal-fluid systems: we use the neural-operator framework to learn solution operators that map sparse boundary measurements to coupled internal fields in physically inaccessible regions, framing the problem class explicitly to distinguish it from classical state estimation and pointwise soft sensing. We instantiate this framework with MIMONet, a branch-trunk operator extended with three practical choices: multi-modal branch encoders for heterogeneous (scalar and function-valued) inputs; multiplicative branch fusion to preserve the bilinear PDE coupling structure; and shared-latent multi-field decoding with per-channel basis projections at the trunk's final layer. Evaluated across escalating complexity, from canonical lid-driven cavity flow to pressurized water reactor subchannels to fully coupled heat exchangers, MIMONet achieves below 5% relative errors and sub-millisecond inference on data-center accelerators (0.35 ms / 46 mJ per heat-exchanger inference on an NVIDIA H200, and sub-millisecond across the A40-H200-GH200 range), while remaining stable under 50% sensor noise. By staying accurate as geometric confinement and physics coupling intensify, MIMONet shows that operator-based virtual sensing can restore observability where physical instrumentation fails, establishing simulation-based feasibility within the evaluated operating envelopes as a step toward future experimental and cross-solver validation for safety-critical energy systems.
A ripple effect of climate change is providing habitat for corals, sponges and other Arctic animals. A ripple effect of climate change is providing habitat for corals, sponges and other Arctic animals.
Few-shot font generation aims to synthesize the remaining glyphs of a font given one or a few reference glyphs while preserving stylistic consistency, thereby supporting font designers in efficiently completing a typeface. Existing methods primarily focus on improving generation quality given a fixed reference set. However, when the current reference glyphs are insufficient to represent the target style, few-shot font generation may fail to produce satisfactory results. In practical scenarios, additional reference glyphs can often be obtained from the designer when necessary. Accordingly, we propose a new framework, Active Reference Acquisition in Few-Shot Font Generation, in which the model sequentially decides which character to acquire next as an additional reference. Furthermore, we propose a reference part-coverage-based acquisition function to efficiently query the designer. Motivated by the observation that font styles are well characterized by local structural parts, we represent each glyph using a histogram of local features and select query characters that maximize the expected part coverage of the reference set. By prioritizing characters that contain parts not yet covered by the current references, the proposed method progressively expands the diversity of visual parts in the reference set. As a result, generation quality is improved with fewer queries. Experiments on the Google Fonts dataset demonstrate that the proposed method achieves higher generation quality than random querying and reference-agnostic baselines. The code is available at https://github.com/matsuo-shinnosuke/ActiveRef-FontGen.
We present SoftMatcha 2, an ultra-fast and flexible search algorithm that enables search over trillion-scale natural language corpora in under 0.3 seconds while allowing semantic variations in the form of substitution, insertion, and deletion. Our approach employs string matching based on suffix arrays that scales well with corpus size, and represents words as vectors, which underpin its semantic flexibility. To mitigate the combinatorial explosion induced by the semantic relaxation of queries, our method is built on two key algorithmic ideas: dynamic corpus-aware pruning and fast exact lookup enabled by a disk-aware design. We theoretically analyze the efficiency of the proposed method, indicating that it can mitigate exponential growth in the search space. Empirically, on FineWeb-Edu (Lozhkov et al., 2024) (1.4T tokens), it attains substantially lower search latency than existing methods: infini-gram (Liu et al., 2024), infini-gram mini (Xu et al., 2025), and SoftMatcha (Deguchi et al., 2025). As a practical application, our method uncovers benchmark contamination in training corpora that existing approaches miss, and it also benefits information retrieval and paraphrase detection. We also provide an online demo of fast, soft search across corpora in seven languages.
Arabic and Hebrew, as closely related Semitic languages, share a substantial lexicon of true cognates, misleading false friends, and modern loanwords. This overlap poses a challenge for cross-lingual semantic understanding in large language models (LLMs). To evaluate this capability, we introduce SemCog Bench, a curated benchmark of 1,858 Arabic–Hebrew word pairs with sentence-level annotations for cognate identification and semantic disambiguation. We evaluate open-source and commercial LLMs across multiple input representations (raw, diacritized, Romanized, and phonetic) and reveal a critical gap in cross-lingual reasoning. While models achieve high accuracy on true cognates, performance drops sharply on false friends and loanwords, reflecting a strong reliance on surface-form similarity. Furthermore, sentence-level context yields only modest improvements, suggesting that contextual cues alone are insufficient to overcome misleading form-based signals. These findings reveal a fundamental limitation of current LLMs in resolving cross-lingual form–meaning conflicts and establish SemCog Bench as a rigorous benchmark for multilingual semantic reasoning. Our code and data are publicly available.
Mild Cognitive Impairment (MCI) is a medical condition characterized by a noticeable decline in memory, language, or thinking abilities. MCI detection from spontaneous speech is promising for scalable screening. However, learned models often exploit demographic cues correlated with labels, resulting in a large performance gap across subgroups. We present a multimodal framework that combines (i) cross-model fusion between modalities (speech, text, and image), and (ii) unlearning using gradient reversal that discourages the shared embedding from encoding task-irrelevant demographic attributes. Evaluated on the multilingual benchmarks TAUKADIAL and PREPARE, our method outperforms the state-of-the-art multilingual and multimodal baseline in MCI classification while substantially reducing the performance gap across patient subgroups (sex and language). We further analyze transfer across datasets, showing that demographic unlearning helps learn more robust representations for MCI detection.
Context engineering has emerged as a primary lever for improving AI systems without parameter updates. Recent work showing that textual gradients do not function as real gradients motivates treating automatic prompt optimization (APO) as black-box search. We introduce SPO (Stochastic Prompt Optimization), a framework for stochastic search over prompt space, and compare three strategies of increasing sophistication: error-informed random search, a genetic algorithm with evolutionary operators, and SAGE (SPO via Agent-Guided Exploration), a multi-agent pipeline with diagnostic code execution. Across three benchmarks, no single strategy dominates; effectiveness depends on the interaction of landscape structure with error type. We further deploy SAGE on a mental-health chatbot under a continuous optimization paradigm, where it compounds eight cycles of individually-noisy A/B tests into a statistically robust gain in next-day retention. We argue that coupling qualitative diagnosis with quantitative validation is what makes agentic optimization effective for open-ended task-oriented dialogue.