A treasure trove of Neolithic necklace beads
Archaeological findings from Italy, and machines with a life of their own, in our weekly dip into Nature’s archive. Snippets from Nature’s past.
Academic Intelligence · Curated Daily
AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。
Archaeological findings from Italy, and machines with a life of their own, in our weekly dip into Nature’s archive. Snippets from Nature’s past.
arXiv:2606.13757v1 Announce Type: cross Abstract: Large language model (LLM) reviewers are increasingly used in pull-request (PR) workflows, where their approvals help decide which code is merged into a repository. This raises a question that benchmarks for static vulnerability detection or code generation do not address: can an automated reviewer reject a malicious contribution when the attacker controls both the code change and the accompanying PR text? We introduce SEVRA-BENCH (Social Engineering of Vulnerabilities in Review Agents), a benchmark that measures how often an automated reviewer approves such adversarial pull requests. Each malicious PR in SEVRA-BENCH is built from a real project commit that previously fixed a vulnerability listed in the Common Vulnerabilities and Exposures (CVE) database. We automatically invert that fix to restore the original vulnerable code and submit it as a pull request wrapped in one of 15 social-engineering framings, which vary the claims made, the supporting evidence, the urgency conveyed, signals of prior approval, and appeals to authority. SEVRA-BENCH contains 1,062 malicious PRs drawn from Common Vulnerabilities and Exposures (CVE)-linked fixes across the top 10 entries of the 2025 Common Weakness Enumeration (CWE) Top 25. In a realistic setting, we evaluate 8 current LLMs as code review agents on PRs that introduce vulnerabilities previously reported in public disclosures. Our results reveal a sharp gap in security capabilities between closed- and open-source models. We hope SEVRA-BENCH will serve as a valuable resource for advancing open-source models and narrowing this gap.
by Kira Elsbernd, Issa Sabi, Ilesh V. Jani, Chishamiso Mudenyanga, Siriel Boniface, Arlete Mahumane, Joaquim Lequechane, Falume Chale, Bindiya Meggi, Kassia Pereira, Raphael Edom, Anange F. Lwilla, W. Chris Buck, Nyanda Elias Ntinyinya, Michael Hoelscher, Till Baernighausen, Arne Kroidl, Stefan Kohler, the LIFE Study Consortium Background Timely access to early infant diagnosis (EID) is crucial for newborns with HIV, as late diagnosis can delay lifesaving antiretroviral treatment (ART). We assessed the comparative cost and cost-effectiveness of integrating point-of-care EID at birth into routine care in primary healthcare settings. Methods and findings This pre-specified secondary analysis was nested in the cluster-randomized LIFE study conducted at 28 primary healthcare facilities in Mozambique and Tanzania from October 2019 to September 2021. We estimated the health system cost of point-of-care birth plus 4–8-week HIV testing (very early infant diagnosis; VEID) compared to standard-of-care (SoC) testing at 4–8 weeks only, both with immediate ART initiation. We assessed the cost-effectiveness of VEID relative to SoC with respect to ART initiation within one week of life using Bayesian hierarchical models. As this is an intermediate outcome, incremental cost-effectiveness ratios (ICERs) cannot be directly compared to available life-year-based cost-effectiveness thresholds. To contextualize results, we derived the minimum life-years gained per early ART initiation required for VEID to meet standard thresholds in a break-even analysis.VEID was associated with a higher cost and resulted in earlier ART initiation than SoC in both countries. In Mozambique, VEID increased the proportion of infants initiating ART within one week of life by 90.0 (95% CrI [67.5, 98.5]) percentage points at an incremental cost of $2,632 (95% CrI [$2,249, $3,062]) per infant with HIV. In Tanzania, VEID increased early ART initiation by 59.9 (95% CrI [20.9, 89.5]) percentage points at an incremental cost of $6,263 (95% CrI [$5,394, $7,243]) per infant with HIV. The ICER was $2,924 and $10,458 in Mozambique and Tanzania, respectively and was sensitive to intrauterine transmission rate. These findings were limited by the lack of long-term health outcome data and reliance on an intermediate outcome. Based on the break-even analysis, we estimated that VEID would need to yield 6–32 life-years gained per additional early ART initiation to meet standard thresholds. Conclusions Adding birth testing improved early ART initiation but was unlikely to be cost-effective relative to standard thresholds given current prices, vertical transmission rates, and knowledge of long-term health benefits. Cost-effectiveness could be achieved at current costs if early ART translates to substantial long-term health benefits or if targeted to infants at high risk of vertical transmission.
arXiv:2606.18722v1 Announce Type: new Abstract: In this short article we consider a preferential attachment random graph model with edge steps, studied by Alves, Ribeiro and Sanchis. Starting with an initial graph $\mathbb{G}_1$ formed by a vertex with a self-loop attached to it, the model evolves as follows. At every subsequent (discrete) time step, either with probability $p$ we add a vertex to the graph and connect it to exactly one of the older vertices selected with probability proportional to its degree, or with probability $1-p$ we add one edge between two existing vertices, both selected (independently) with probability proportional to their degrees. Let $\omega(\mathbb{G})$ be the clique number of a graph $\mathbb{G}$, i.e.\ the number of vertices in a largest complete subgraph of $\mathbb{G}_{}$. Alves, Ribeiro and Sanchis showed that, for any given $\varepsilon>0$, we have $\omega(\mathbb{G}_{2t})\geq t^{\frac{1-p}{2-p}(1-\varepsilon)}$ with high probability (i.e.\ with probability tending to $1$ as $t\rightarrow \infty$). Here we strengthen this bound by showing that, for any function $f:\mathbb{N}\mapsto \mathbb{N}$ that satisfies $f(t)\rightarrow \infty$ as $t\rightarrow \infty$, with high probability \[\omega(\mathbb{G}_{2t}) = \Omega\left(t^{\frac{1-p}{2-p}}\Big(\log^{\frac{1}{2-p}}(t)f(t)\Big)^{-1}\right).\]
Background: People living with terminal illness face a double financial burden from additional costs and loss of earning for themselves and their carers. Social security benefits are intended to help alleviate some of this financial pressure, and in the UK and other countries people are eligible for fast-tracked access to financial support via the Special Rules for End of Life. One in 3 people who are eligible miss out on this support, yet there is limited evidence on the reasons for this take-up deficit. Objectives: The aim of this study is to understand the barriers and facilitators to claiming benefits for terminally ill people from the perspectives of patients, carers, and health care professionals. Methods: This is a qualitative study combining i) focus groups with healthcare professionals recruited via professional networks and social media, and ii) interviews with patients and carers recruited in hospital and hospice settings. We analysed the data using Practical Thematic Analysis Results: Fifty-five multidisciplinary healthcare professionals participated in 11 focus groups, and we interviewed 10 patients and carers. We constructed five descriptive themes to summarise the data: Navigating priorities and uncertainty; positive impacts alongside a sense of shame and stigma; talking about money, difficulties and dividends; everybodys, yet nobodys, responsibility; and sticking points in the system. Conclusion: The themes reveal several challenges that may contribute to people not taking up this financial support. However, discussions about access to benefits were also seen as a core part of holistic care, a positive way to offer support and a gateway to other discussions about end-of-life care preferences and decisions. Recommendations for policy and practice include evaluating the adoption of a diagnostic rather than a prognostic eligibility criteria, integrating discussions about benefits into existing processes such as advance care planning, and improving education and support for clinicians.
arXiv:2509.21886v3 Announce Type: replace Abstract: Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed assumption, central to mainstream message passing neural networks (MPNNs) and their conventional Transformer-based counterparts, prevents models from capturing the position-aware, hierarchical nature of computation. To resolve this, we introduce TRACE, a new paradigm built on an architecturally sound backbone and a principled learning objective. First, TRACE employs a Hierarchical Transformer that mirrors the step-by-step flow of computation, providing a faithful architectural backbone that replaces the flawed permutation-invariant aggregation. Second, we introduce function shift learning, a novel objective that decouples the learning problem. Instead of predicting the complex global function directly, our model is trained to predict only the function shift, the discrepancy between the true global function and a simple local approximation that assumes input independence. We validate this paradigm on various circuits modalities, including Register Transfer Level graphs, And-Inverter Graphs and post-mapping netlists. Across a comprehensive suite of benchmarks, TRACE substantially outperforms all prior architectures. These results demonstrate that our architecturally-aligned backbone and decoupled learning objective form a more robust paradigm for the fundamental challenge of learning the functional behavior of a circuit graph.
Background: Genome-wide association studies (GWAS) have identified hundreds of loci associated with body fat distribution, yet the causal genes and regulatory mechanisms through which these variants exert their effects remain largely unknown. Expression quantitative trait locus (eQTL) colocalization provides a powerful framework for identifying genes whose expression is genetically coregulated with complex traits. Methods: We performed a genome-wide colocalization analysis integrating waist-hip ratio adjusted for body mass index (WHRadjBMI) GWAS summary statistics from 694,649 individuals (Pulit et al., 2019) with subcutaneous adipose tissue eQTLs from the Genotype-Tissue Expression (GTEx) Project v8 (N = 581 donors). GWAS coordinates were lifted from GRCh37 to GRCh38 to enable direct alignment with GTEx data. We incorporated CAVIAR fine-mapping results to overcome the limitation of FDR-significant eQTL filtering. Colocalization was assessed using the approximate Bayes factor framework (coloc.abf) across 335 independent genome-wide significant loci. Results: Of 2,897 locus-gene pairs tested, 489 (16.9%) showed strong colocalization (PP.H4 > 0.8) and 618 (21.3%) showed moderate evidence (PP.H4 > 0.5). The strongest colocalization was observed for SNX10 (sorting nexin 10; PP.H4 = 1.000), a recently characterized regulator of adipocyte differentiation and female-specific diet-induced obesity. Other top hits included DGKQ (diacylglycerol kinase theta; PP.H4 = 0.9999999), an emerging pharmacological target for insulin resistance, and CBX3 (chromobox 3; PP.H4 = 0.9999974), an epigenetic regulator linked to cardiovascular disease. Established adiposity genes including GRB14 (PP.H4 = 0.681) and KLF14 (PP.H4 = 0.590) were recovered, validating our approach. Several loci exhibited extensive allelic heterogeneity, with 50 genes colocalizing at a single chromosome 3 locus. Conclusions: Our analysis provides a comprehensive map of adipose tissue gene regulatory mechanisms underlying genetic risk for body fat distribution. The identification of SNX10, DGKQ, and CBX3 as high-confidence candidate causal genes advances the translation of GWAS associations into mechanistic understanding and therapeutic targets for obesity-related cardiometabolic disease.
by Yoshiyuki T. Nakamura, Chikara Furusawa, Kunihiko Kaneko Embryonic development in multicellular organisms exhibits diverse morphogenetic patterns, which can generally be categorized into fundamental types such as monolayer and multilayer spheres, as well as cell masses. Furthermore, we identify two distinct processes for the formation of spherical structures. These basic patterns are thought to be governed by the microscopic properties of intercellular adhesion. However, the specific mechanisms linking the microscopic factors to the emergence of distinct macroscopic morphogenetic patterns remain poorly understood. In this study, we explore how different morphogenetic patterns arise by employing a computational model that incorporates intercellular adhesion and polarity. Our results demonstrate that all fundamental morphogenetic patterns can be generated through the interplay of two key parameters: the polarity strength of the cell and the regulation of polarity via mechanical signals. Furthermore, analytical considerations reveal key mechanisms underlying the formation of these patterns. These findings highlight the critical role of physical constraints in morphogenesis and suggest potential applications to the design of artificial tissues and organoids.
arXiv:2411.03441v2 Announce Type: replace Abstract: Mixed-state phases of matter under local decoherence have recently garnered significant attention due to the ubiquitous presence of noise in current quantum processors. One of the key issues is understanding how topological quantum memory is affected by realistic coherent noise, such as random rotation noise and amplitude-damping noise. In this work, we investigate the intrinsic error threshold of the two-dimensional toric code (TC), a paradigmatic topological quantum memory, under these types of coherent noise by employing both analytical and numerical methods based on the doubled-Hilbert-space formalism. A connection between the mixed-state phase of the decohered TC and a non-Hermitian Ashkin-Teller-type statistical-mechanics model is established, and the mixed-state phase diagrams under the coherent noise are obtained. We find remarkable stability of mixed-state topological order under random rotation noise with axes near the $Y$-axis of qubits. We also identify intriguing extended critical regions at the phase boundaries, highlighting a connection with non-Hermitian physics. We argue that these phase boundaries provide upper bounds for the intrinsic error threshold, beyond which quantum error correction becomes impossible. We complement these findings by estimating the error thresholds for random rotation noise under standard quantum error correction, thereby providing lower bounds on the intrinsic error threshold.
arXiv:2606.13606v1 Announce Type: new Abstract: Symmetries shape the quantum-information dynamics of many-body systems, but their effect on nonstabilizerness, the resource complementary to entanglement, is less understood. We compute the stabilizer Rényi entropy, a measure of nonstabilizerness, in $\mathrm{U}(1)$-symmetric one-dimensional random circuits. The disorder-averaged dynamics is captured by a four-replica tensor network, which we evaluate by $S_4$-adapted infinite time-evolving block decimation (iTEBD) directly in the thermodynamic limit. Together with a hydrodynamic argument, our results identify a diffusive universality class for the late-time approach of nonstabilizerness to its random-state value, with the stabilizer Rényi entropy gap closing as $1/t$. The same scaling is verified in an energy-conserving nonintegrable Ising chain. More broadly, our framework provides a hydrodynamic perspective on nonstabilizerness generation and offers insight into the design of approximate Haar-random states in Hamiltonian dynamics.
arXiv:2505.11846v3 Announce Type: replace Abstract: We study function spaces parametrized by neural networks, referred to as neuromanifolds. Specifically, we focus on deep Multi-Layer Perceptrons (MLPs) and Convolutional Neural Networks (CNNs) with an activation function that is a sufficiently generic polynomial. First, we address the identifiability problem, showing that, for almost all functions in the neuromanifold of an MLP, there exist only finitely many parameter choices yielding that function. For CNNs, the parametrization is generically one-to-one. As a consequence, we compute the dimension of the neuromanifold. Second, we describe singular points of neuromanifolds. We characterize singularities completely for CNNs, and partially for MLPs. In both cases, they arise from sparse subnetworks. For MLPs, we prove that these singularities often correspond to critical points of the mean-squared error loss, which does not hold for CNNs. This provides a geometric explanation of the sparsity bias of MLPs. All of our results leverage tools from algebraic geometry.
arXiv:2602.21263v3 Announce Type: cross Abstract: We analyze branch decoherence in inflationary quantum cosmology by computing reduced density matrices and branch-overlap factors for long-wavelength perturbations. The Hartle-Hawking no-boundary state is real in the semiclassical regime and contains both expanding and contracting WKB components, whereas the tunneling state is selected as an outgoing complex WKB branch; expanding-contracting decoherence is therefore central for the former and mainly diagnostic for the latter. Using the influence-functional formalism, we derive the noise kernel for a light spectator environment and evaluate decoherence under horizon-based and EFT-motivated coarse grainings. We then compute the single-mode branch overlap directly from the Bunch-Davies mode functions, obtaining $|\mathcal{D}_k(z)|=[z^2/(z^2+1)]^{1/4}$ in the massless limit and $|\mathcal{D}_k(z)|\sim z^\nu$ on superhorizon scales for massive fields, where $z=-k\eta$ is the dimensionless wavenumber with $\eta$ the conformal time. In the massless case, the accumulated geometric branch functional is evaluated in closed form, with a leading cutoff-sensitive phase-space term and a universal subleading contribution. The calculation provides an explicit quantitative bridge between quantum-cosmological boundary conditions, inflationary squeezing, and the emergence of effectively classical cosmological histories.
arXiv:2606.16751v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their safety remains a critical concern due to their susceptibility to adversarial prompt-based attacks. In this paper, we present UNIATTACK, an adversarial testing framework designed from a defense-oriented perspective to systematically construct effective black-box attack prompts. Unlike prior approaches that rely on static templates or iterative model-specific tuning, UNIATTACK extracts minimal but high-impact attack features from diverse existing attacks, optimizes them via a specialized attacker LLM, and composes them into flexible templates through automated refinement process. This feature-centric construction enables one-shot attacks that generalize across multiple models and safety categories, providing a practical tool for assessing LLM robustness. Our evaluation results shows that compared to the baselines, UNIATTACK achieves an average attack success rate (ASR) improvement of 64.63\%-248.82\% on models deployed with multi-layered defense mechanisms and it only takes 0.03\%-4.96\% cost of the baselines. UNIATTACK artifact is available at https://anonymous.4open.science/r/UniAttack-Artifact-30F1.
arXiv:2606.14346v1 Announce Type: cross Abstract: Unstructured pruning produces sparse weight tensors, but the standard implementation keeps tensor shapes unchanged so the deployed model is no smaller than before pruning. We present an exact structural rewrite, which we call minimization, that converts a masked network into a smaller dense network with the same forward function up to floating-point rounding. The Squeeze-Release cycle iterates pruning and minimization with an intermediate release step that re-enables the exact-zero positions inside the compacted tensors as small calibrated noise, turning otherwise wasted capacity back into trainable parameters. Successive cycles use that capacity to find structural redundancy a single pass cannot reach. We additionally introduce CompensatedLayerNorm, a function-preserving replacement for LayerNorm that extends minimization to channel reduction across LayerNorm-equipped residual streams. Squeeze-Release compresses the deployable network to 39x smaller than the unpruned model on a fully-connected model network and 14.8x smaller on modern CNN (ConvNeXt-Tiny), at comparable accuracy. In addition we prove that the rewrite can be extended to transformer architectures.
arXiv:2606.13608v1 Announce Type: new Abstract: Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.
The choice of speech representation is critical in speech-driven 3D facial animation. Representations differ in what they encode: SSL features emphasize segmental and semantic cues, neural codecs yield latents optimized for acoustic reconstruction, and ASR-style objectives produce label-based spaces. We evaluate four speech representation families for 3D facial synthesis, comparing their facial reconstruction quality across two facial decoders using objective metrics and a perceptual evaluation. We additionally conduct probing analyses that relate tokenized representations to phonetic units and to articulatory deformations. We found that encoding phonetic classes is beneficial for accurate facial animation prediction on both semantic and label-based representations with comparable facial animation quality. From the latter, we introduce an Audio Visual Text-to-Speech (AVTTS) pipeline that leverages, as a shared space, discrete representations to decode speech and 3D facial motion.
arXiv:2602.05670v2 Announce Type: replace-cross Abstract: Advances in AIGC technologies have enabled the synthesis of highly realistic audio deepfakes capable of deceiving human auditory perception. Although numerous audio deepfake detection (ADD) methods have been developed, most rely on local temporal/spectral features or pairwise relations, overlooking high-order interactions (HOIs). HOIs capture discriminative patterns that emerge from multiple feature components beyond their individual contributions. We propose HyperPotter, a hypergraph-based framework designed to capture high-order relations associated with synergistic patterns through clustering-based hyperedges with class-aware prototype initialization. Extensive experiments on 13 test sets show that HyperPotter improves over the baseline on 11 sets, yielding an average relative EER reduction of 12.68\% across all test sets and 22.15\% on the improved sets. These results demonstrate strong cross-scenario generalization, while also revealing robustness limits under severe codec or channel distortion.
arXiv:2604.22167v2 Announce Type: replace-cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of these models is increasingly high-stakes. Fortunately, advances in alignment have significantly reduced the likelihood of harmful model outputs. However, when models are queried billions of times in a day, even rare worst-case behaviors will occur. Current safety evaluations focus on capturing the distribution of inputs that yield harmful outputs. These evaluations disregard the probabilistic nature of models and their tail output behavior. To measure this tail risk, we propose a method to efficiently estimate the probability of harmful outputs for any input query. Instead of naive brute-force sampling from the target model, where harmful outputs could be rare, we operationalize importance sampling by creating unsafe versions of the target model. These unsafe versions enable sample-efficient estimation by making harmful outputs more probable. On benchmarks measuring misuse and misalignment, these estimates match brute-force Monte Carlo estimates using 10-20x fewer samples. For example, we can estimate probability of harmful outputs on the order of 10^-4 with just 500 samples. Additionally, we find that these harmfulness estimates can reveal the sensitivity of models to perturbations in model input and predict deployment risks. Our work demonstrates that accurate rare-event estimation is both critical and feasible for safety evaluations. Code is available at https://github.com/rangell/LMTailRisk
Despite the remarkable reasoning capabilities of large language models, they still struggle with one-shot relation extraction without predefined relation labels. We identify two pitfalls: models are often misled by irrelevant tokens instead of relation-conveying semantics, and they often fail to align with the abstraction level human annotators expect. We introduce a novel framework that closes this gap with two components: (1) COGRE, a cognitively-inspired reasoning framework that structures RE into a series of processes mimicking human text-processing; and (2) HIT@DICT, a reinforcement learning intermediate reward strategy that encourages reasoning to align with relational labels by rewarding relation-relevant phrases in reasoning. The reward is derived on a credit dictionary automatically extracted from correct predictions. Our experiments show that our framework improves both accuracy and explanation quality by addressing these two pitfalls. For example, COGRE with Qwen2.5-14B-Instruct on One-shot NYT29 achieves 24.65% F1, surpassing prior reasoning-based designs. Optimizing this approach with RL using HIT@DICT further improves performance by +23.46% points. Finally, human evaluation shows that our best model generates relational phrases closely aligned with gold labels, increasing human explanation quality ratings by 54% (relative).
The Montreal Forced Aligner (MFA) was released in 2016 and has since become the most widely used tool for forced alignment in research and industry. In the decade since, MFA has undergone substantial development, including expanded coverage across more languages and dialects using larger open-source datasets, harmonized IPA dictionaries, model adaptation, cross-language phone remapping, and support utilities. This paper documents MFA 3.0's developments since version 1.0 and evaluates MFA's performance across English, Japanese, and Korean, benchmarked against classic and neural forced aligners. MFA 3.0 achieves state-of-the-art or near state-of-the-art performance across all four benchmark datasets with mean boundary errors below 15 ms. Adaptation and cross-language remapping are effective for languages outside MFA's training distribution, and pronunciation probability modeling and phonological rules provide gains in specific conditions.
Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally embedded stereotypes, influence moral judgments, or amplify positive evaluations of majority groups. We propose metacognitive myopia as a cognitive-ecological framework accounting for a conglomerate of established and emerging LLM biases. Our theoretical framework posits that biased samples in the information environment cause five symptoms of metacognitive myopia in LLMs: integration of invalid embeddings, susceptibility to redundant information, neglect of base rates in conditional computation, decision rules based on frequency, and inappropriate higher-order statistical inference for nested data structures. Moreover, it posits that the two main components of metacognition, monitoring and control, could account for these five symptoms. Accordingly, we further outline how monitoring and control could be approximated technically, for instance, through hidden parallel reasoning histories that allow interactive LLMs to evaluate risks of myopic inference before generating overt responses. Our theoretical framework provides a novel perspective on flawed human-machine interactions and agentic AI and raises significant ethical concerns regarding the implementation of LLMs in organizational structures and high-stakes decisions.
arXiv:2601.11670v3 Announce Type: replace-cross Abstract: Pseudo-label selection in semi-supervised learning is commonly driven by maximum-confidence thresholds, yet confidence alone can be unreliable under model overconfidence and class imbalance. We propose CoVar, a confidence–variance framework that assesses pseudo-label reliability by jointly modeling Maximum Confidence (MC) and Residual-Class Variance (RCV). Starting from entropy minimization, we derive a second-order cross-entropy approximation showing that low-loss pseudo-labels are favored when MC is high and RCV is low, with a confidence-dependent penalty that becomes stronger for near-certain predictions. Based on this criterion, CoVar embeds predictions into a two-dimensional confidence–variance space and uses SVD-based spectral relaxation to separate reliable and unreliable predictions without hand-tuned confidence thresholds. Cluster-wise Gaussian weighting then converts this separation into per-sample training weights. The resulting weights can be integrated into existing semi-supervised segmentation and classification pipelines during training and introduce no inference-time overhead. Experiments on PASCAL VOC 2012, Cityscapes, CIFAR-10, CIFAR-100, SVHN, and STL-10 show clear gains on VOC and Cityscapes under matched backbones, as well as competitive or improved error rates on standard classification benchmarks. These results indicate that residual-class dispersion provides a useful signal complementary to confidence for robust pseudo-label selection.
AudioLLMs enable speech recognition conditioned on textual prompts such as domain descriptions or entity lists. However, it remains unclear whether these models genuinely utilise such context or rely on parametric knowledge learned during pretraining. Existing benchmarks cannot answer this question because they evaluate transcription under fixed prompting conditions and rarely include explicit contextual inputs. We introduce IndicContextEval, a 56-hour multilingual benchmark of natural speech from 555 speakers across 8 Indian languages and 23 professional domains. We design a 7-level prompting framework that progressively introduces contextual signals, including metadata, natural-language descriptions, entity lists in English and native script, and adversarial prompts with incorrect entities. Evaluating five models reveals substantial differences in context utilisation behaviour, highlighting the need for explicit evaluation of contextual grounding in AudioLLMs.
arXiv:2606.20376v1 Announce Type: cross Abstract: Safety is a core concern for deploying reinforcement learning (RL) agents in real-world domains such as robotics and autonomous driving. While benchmarks have been central to progress in RL, existing safety benchmarks with high-fidelity 3D physics remain computationally slow, limiting large-scale experimentation and rapid prototyping. To address this gap, we propose CRAX (Constrained RL Accelerated with JAX). Built on top of the MuJoCo XLA (MJX) physics engine with realistic 3D dynamics, CRAX leverages vectorized operations and hardware acceleration, yielding up to ~100x speedups over comparable CPU-based safety benchmarks. The benchmark features six environment suites and three agent-specific tasks, each spanning three difficulty levels. Evaluating six popular safe RL methods shows that no single approach dominates across all tasks, and reveals the trade-offs between performance and safety. We find that curriculum learning across difficulty levels and safety transfer can improve performance over direct training in harder settings.
arXiv:2606.16501v1 Announce Type: new Abstract: Model merging has become a practical post-training strategy for building a single multi-task large language model (LLM) by combining multiple task-specialized models. However, most existing approaches rely on post-hoc merging, in which task-specific models are merged only once after training. This one-shot aggregation often suffers from task interference, leading to information erasure across individual tasks. In this work, we show that replacing post-hoc merging with an iterative many-shot merging protocol is effective in improving multi-task performance. Building on this insight, we propose METIS, Mitigating Erasure from Task Interference for Stable many-shot merging. METIS is a loss-aware many-shot merging method that addresses information erasure in post-hoc merging through task-wise loss-gap weighting and consensus-based masking. Notably, METIS exhibits significant performance improvement on the worst-performing task, effectively mitigating information erasure. (Project page: https://imkyungjin.github.io/METIS/)