Papers

In this paper, we study the existence of ground states for two-component attractive Bose–Einstein condensates with displaced harmonic trapping potentials \[ V_1(x)=|x-x_1|^2 \ \text{and}\ V_2(x)=|x-x_2|^2, \] where $x_1\neq x_2\in\mathbb R^2$. For intraspecies interactions $a_1,a_2\in (0,a^*)$, we focus on the critical interspecies coupling \[ \beta=\beta^*:=a^*+\sqrt{(a^*-a_1)(a^*-a_2)} \] and prove that there exists a separation threshold $d_c\in(0,\infty)$ such that the corresponding constrained minimization problem admits no minimizer when $0<|x_1-x_2|<d_c$, whereas it admits a minimizer when $|x_1-x_2|\geq d_c$. The threshold is given by $d_c=\Lambda_*^{-1/4}$, where $\Lambda_*$ is characterized by an auxiliary variational problem and attained. Our results extend the previous work of Guo et al. [J. Funct. Anal. 276 (2019)] and complete the existence classification of ground states for two-component attractive Bose–Einstein condensates with harmonic trapping potentials.

Infrared image super-resolution is currently led by Mamba-based networks with 26 to 37 million parameters, which are difficult to deploy on the airborne and handheld platforms where thermal imaging is most needed. This paper presents TIRMamba, a network with 896K to 910K parameters for single-channel thermal imagery. A Thermal Prior Highway computes gradient, local-contrast and spectral cues once at the input and, through one adapter per residual group, modulates a weight-tied bidirectional state-space trunk and gates its dual-scale detail branch; a tri-path reconstruction adds the learned residual to a bicubic radiometric baseline. Because the standard benchmark provides only 265 infrared training images and evaluates fusion products on full images, we train with a replay strategy: grayscale DIV2K pre-training followed by fine-tuning on 64-pixel patches drawn with equal probability from the infrared and natural corpora. At scale factor 4, TIRMamba matches the strongest protocol-trained methods on both official test sets with 29 to 40 times fewer parameters and 2.8 to 9.4 times lower latency; at scale factor 2 it gives the highest SSIM on both. A variant with prior-conditioned selectivity, TIRMamba-Rad, corrects a 3 dB raw-thermal failure of an intermediate size-invariant design and gives the best results at scale factor 4 on raw-thermal, unmanned-aerial-vehicle and independent-sensor test sets. Code and trained models will be released at https://github.com/julian135707/TIRMamba upon acceptance.

We prove Schwarz lemmas for \(\bar\partial_b\)-harmonic maps from complete pseudo-Hermitian manifolds into K"ahler manifolds of negative curvature. For maps of bounded generalized dilatation we bound the full and the horizontal differential. For CR maps a coupled Bochner identity yields rank-dependent horizontal estimates and a bound for the Reeb differential. On Sasakian sources and complex hyperbolic targets we classify the maps attaining the horizontal bound, bound the deviation from equality in integral form by the deficit at one point, and prove compactness of almost extremal sequences. As an application, a Siu-type divergence identity yields foliation, pluriharmonicity and rank rigidity under volume growth conditions.

Learning dexterous manipulation benefits from human demonstration datasets that capture diverse and natural hand-object interactions. In particular, contact points and forces provide supervision on where and how strongly to interact, which cannot be fully captured by motion trajectories alone. However, methods for jointly capturing hand and object motion, contact points, and forces remain limited. Moreover, severe occlusion from hand-object interaction challenges accurate tracking of both hands and objects. To address these limitations, we present a Visual-Inertial-CONtact based hand-object tracking (VICON) framework. It holistically captures both hand and object motion along with contact information during manipulation, even under severe occlusion. First, we adopt a visual-inertial glove and an RGB-D camera for accurate hand tracking, and redesign the glove to incorporate contact sensing. Specifically, force-sensitive resistors (FSRs) are placed on the glove based on human grasp frequency to synchronously record contact states and calibrated normal forces. Second, without requiring pre-existing CAD models, we estimate object poses using RGB-D images and a mesh reconstructed from a monocular video. We propose factor-graph-based object trajectory estimation that fuses object-pose estimates weighted by visibility under hand-object occlusion, FSR measurements, and a hand-motion prior. Across 40 motion-capture sessions with five objects, VICON achieves a 2.5% failed-frame rate compared with 50.9-64.6% for the baselines, with median errors of 3.9 mm and 3.0 degrees under occlusion. Using VICON, we construct a dataset containing synchronized hand-object motion, contact points, and normal forces, and will publicly release an expanded dataset covering 10 object categories at https://github.com/VICON-dataset/dataset.

For K-unstable toric varieties, Székelyhidi's optimal test-function $\Theta_{P}$ is a mysterious concave function over the moment polytope $P$, which gives the maximal destabilizer for K-stability, and encodes the limiting behavior of the divergent Calabi flow. As balanced norms quantize cscK metrics, we show that $\Theta_{P}$ can be quantized by the maximal destabilizers for Chow-stability, which are given by the shortest GKZ vectors, i.e., the least norm point on the secondary polytope for the set $P\cap k^{-1}\mathbb{Z}^{n}$. Properties and algorithm for general sGKZ vectors are given. Our result may provide a new method to detect the K-unstability of toric varieties.

Effective adaptive instructional systems require robust measures of learner engagement that go beyond static user profiles. This study employs Multimodal Learning Analytics (MMLA) to investigate the relationship between self-reported instructional modality preferences and objective neurophysiological markers of engagement. Thirty-seven participants engaged with learning content delivered via varying modalities (visual, auditory, reading/writing, kinesthetic). We captured real-time neural activity using two EEG devices: the Emotiv EpocX (14 channels, 128 Hz) and OpenBCI (16 channels, 125 Hz). Preferences were assessed using the VARK questionnaire. Consistent with literature challenging the "meshing hypothesis," aligning instructional modality with stated preferences did not significantly predict performance gains. However, spectral analysis of EEG data revealed divergent engagement patterns: when content aligned with preferences, distinct neural activity patterns emerged in theta and alpha frequency bands-markers associated with attention and cognitive processing. These signals were used to train a binary logistic regression classifier, achieving a mean accuracy of 83.21% with OpenBCI and 56.27% with Emotiv EpocX. These findings suggest that while self-reported preferences may not dictate learning outcomes, they significantly influence neurophysiological engagement, offering a viable, non-invasive input for adaptive educational algorithms.

We prove that every weakly group-theoretical modular fusion category, equipped with its canonical positive spherical structure, has generalized property F: the associated Reshetikhin-Turaev mapping class group representations have finite projective image for all compact oriented surfaces with labeled framed points. This generalizes earlier finite-image results for braid group representations associated with weakly group-theoretical braided fusion categories and for mapping class group representations associated with group-theoretical modular fusion categories and Ising categories. In the weakly group-theoretical setting, it also extends the known finiteness result for symmetric mapping class groups of closed surfaces to the full mapping class groups.

Large language model (LLM)-based multi-agent systems increasingly rely on memory to transform execution trajectories into reusable procedural knowledge. Yet repeated retrieval also makes memory errors persistent: memory pollution arises when outdated, weakly supported, or spuriously successful procedures become recurring components of future reasoning. Multi-agent execution introduces an additional structural risk. Scope collapse occurs when procedural knowledge escapes the coordination scope in which it was shown effective and is repeatedly reused at incompatible decision levels, allowing local errors to influence cascades of downstream decisions. Meanwhile, task-level failures provide ambiguous supervision because they rarely reveal which recalled knowledge was responsible. We introduce AECG, a framework for asymmetric experience consolidation and governance for multi-agent systems. AECG turns memory from static experience storage into a dynamic reliability-governance loop, preserving coordination scope and using multi-scale, confidence-aware reliability to detect degradation. It then combines degradation with downstream impact to prioritize high-risk knowledge under a bounded review budget, applies targeted interventions, and reactivates revised skills only after paired replay. Across three multi-agent frameworks and four benchmarks, AECG achieves the best score in 11 of 12 framework–benchmark settings and improves over the strongest competing memory method by as much as 10.23 percentage points; removing scope preservation reduces accuracy by up to 16.89 points. AECG thereby reframes multi-agent memory from passive accumulation into auditable reliability governance. Code is available at https://github.com/fenhg297/AECG

Ultrafast pump-probe spectroscopy is indispensable for investigating interactions, collective excitations, and nonequilibrium dynamics in superconductors and correlated electron systems. However, how a small gap opening near Fermi surface affects the spectral changes in the high-energy interband transition region remains elusive. To address this issue, we perform systematic studies of carrier relaxation dynamics in the prototype charge-density-wave (CDW) material EuAl4. We find that the CDW gap shrinks substantially under optical pumping. This band renormalization strongly modulates interband transitions associated with the gap edge, inducing a pronounced transient reflectivity change at the corresponding probe energies. These results establish a direct link between low-energy order-parameter dynamics and high-energy spectral responses, providing a general framework for interpreting transient signals in gapped quantum materials.

A kernel $k(x,y)$ is LSHable if there exists a locality sensitive hashing scheme $H$ such that $k(x,y)=\Pr_{h\sim H}[h(x)=h(y)]$ for all $x,y$. This notion plays a key role in efficient kernel methods in high dimensions. In this work, we show that the $p$-exponential kernel $k(x,y)=\exp(-\lVert x-y \rVert_p)$ is LSHable in bounded regions for all $1<p\leq2$. Previously, this was known only for $p=1$. Our new "mosaic LSH" scheme is based on a Poisson hyperplane process with hyperplanes sampled as $\ell_1$-biased $p$-stable vectors, for which we develop efficient sampling procedures. As applications, our results yield new and efficient density estimation methods based on LSHability for those $p$-exponential kernels.

In this short note, we study the behavior of the algebraic entropy of birational automorphism groups in families of projective hyper-Kähler manifolds.

Odd girth and the sum of the largest and smallest adjacency eigenvalues are two common indicators of how close a graph is to being bipartite. This paper investigates the asymptotic behavior of this eigenvalue sum under odd-girth constraints. We study the associated abstract moment problem over finite real lists satisfying the vanishing odd-moment identities imposed by odd girth at least $g$ and the standard second-moment bound for graph spectra. We prove that the supremum of $(\lambda_1+\lambda_n)/n$ over these lists lies between $(1-o(1))(\log g)^2/g^3$ and $(10/7+o(1))(\log g)^2/g^3$ as $g\to\infty$ through the odd integers. The upper bound applies in particular to graphs of odd girth at least $g$. For regular graphs of odd girth $g\geq5$, we obtain a stronger bound $(\lambda_1+\lambda_n)/n \leq 12/((g-1)(g-2)(g-3))$, which is optimal up to a constant factor.

We analyse a divergence form stochastic differential equation featuring a Leray-Lions flux function that satisfies standard Carathéodory, growth, monotonicity, and coercivity conditions. We consider two types of noise: multiplicative Lipschitz continuous noise and a transport noise. Our approach utilises the gradient discretisation method, a generic framework encompassing various numerical schemes such as conforming and nonconforming finite element methods, hybrid mimetic mixed methods, and hybrid high order methods. For both types of noise, we propose a stable generic scheme, prove that scheme solutions converge to a strong solution in the probabilistic sense. For the multiplicative Lipschitz continuous noise, we establish the rate of convergence.

Test-time compute has become a central way to improve code generation: systems sample multiple candidate programs and use verifier-visible evidence to select the final output. This paradigm implicitly assumes that the verifier provides a corrective signal independent from the generator. We challenge this assumption under misleading task premises. When the generator and verifier share a false premise, they become coupled through a mistaken belief: the generator produces premise-consistent shortcuts, while the verifier supplies evidence that fails to expose them. Consequently, the selector may choose a hidden-test-wrong candidate even when a hidden-test-correct program exists in the pool. We call this failure mode Verification Trap. Across three code-generation benchmarks and five code models, false premises consistently degrade first-sample correctness, reduce selector-chosen correctness after 64-sample test-time selection, and amplify recoverable mis-selection. Mechanistically, verifier-written tests inherit the premise-level blind spot, reshaping verifier-visible candidate space away from hidden-test correctness. These traces make Verification Trap predictable before hidden execution: a lightweight gold-free predictor using verifier-visible features reaches 0.846 AUROC. Our results identify decoupled evidence as a key mitigation axis: coupled scaling provides limited recovery, whereas premise-agnostic robustness auditors recover substantial oracle headroom.

Problem definition: Automated operations research (OR) depends on correctly understanding the problem users intend to solve. In practice, limited user knowledge and vague expressions can obscure that problem, creating semantic uncertainty in the descriptions used for modeling. This uncertainty can lead to mathematical models that depart from users' intentions. We study semantic alignment to identify and correct errors or omissions in these descriptions before mathematical modeling. Methodology/results: We develop AMAO, an ambiguity-aware multi-agent framework for automated OR under semantic uncertainty. Its two-stage alignment process first uses semantic cues and contextual information to identify and correct potential semantic errors, then obtains additional information via human–AI interaction for further revision when the available context is insufficient. Specifically, AMAO integrates OR-guided mixture-of-experts (MoE) tuning and trajectory-based harness evolution to enhance semantic alignment capabilities. In addition, an ambiguity-aware benchmark and its matched multi-turn dialogue extension are proposed. Extensive experiments support that AMAO can recover the intended operational problem from ambiguous descriptions and recognize when available information is insufficient. Managerial implications: AMAO provides managers with an integrated workflow for translating ambiguous operational descriptions into mathematical models and optimization solutions. By combining semantic alignment with targeted user interaction, it supports recovery of the intended problem and improves downstream solution accuracy.

For four finite discrete random variables, we prove that the negative of the Ingleton expression, divided by the joint entropy, is at most $19/124 \approx 0.15323$, improving the previously reported upper bound $3/19$ by $11/2356$. The proof uses a copy program with four copy steps and six auxiliary variables, certified by exact rational linear-programming certificates. We also show that two published information inequalities, due to Dougherty-Freiling-Zeger and Csirmaz, imply the bound $5/32$ by an explicit nonnegative combination with Shannon inequalities, and that $5/32$ is the exact optimum both of the union of the three published inequality catalogues considered here and of the full copy-lemma extensions of all 213 distinct copy programs occurring in them. The new program is not among these programs, and the bound $19/124$ remains optimal when all of them and all catalogue inequalities are added. Ancillary files provide the parsed catalogues, exact primal and dual certificates, exact extension certificates, and verifiers that use only the Python standard library.

Inspired by cognitive science, we present CREATIVEFLOW, an analogical generation framework that explicitly models analogical divergent thinking to mitigate creative homogenization in text-to-3D pipelines. Our method derives a series of meaningful yet relationally similar source-target asset pairs, each featuring distinct geometric configurations. Expert evaluations demonstrate that our framework substantially enhances creative novelty and visual fascination. This workflow and its resulting assets establish a foundational dataset and benchmark for future relation-aware 3D model training.

A safe action is not necessarily a viable one. A frozen vision-language-action (VLA) policy can favor a locally admissible move that leaves no policy-supported route to safe task completion. We call this the feasibility-likelihood gap: likelihood ranks the next move, while feasibility depends on the futures it leaves open. To bring those futures into the decision, we derive the exact next-block marginal of the history-conditioned policy-environment trajectory law restricted to safe task completion. The derivation reveals a candidate-dependent feasible-future mass: its support records whether safe completion remains possible under the frozen continuation process, while its magnitude measures how much weighted safe-completion mass remains. Since exact evaluation is impractical online, we develop a selective finite-candidate approximation and establish conditions for recovering the best retained viable candidate. Our alarm-triggered, training-free reranker VICS-G lowers mean cumulative safety cost by 1.9%-57.5% across six Safety-CHORES settings while remaining within 2.5 percentage points of policy sampling in success and 0.82 steps in mean episode length. Our approach offers a promising and practical path toward safer task completion, grounded in an exact policy-relative target yet requiring neither policy retraining nor online rollouts.

We prove a geometric hierarchy of Fourier layer energies for the weakly nonlinear cubic Schrodinger equation on $\mathbb T_\pi\times\mathbb T_1$, retaining its nontrivial resonant dynamics. For initial Fourier support in a rectangle, form nested rectangles with half-widths $(2j+1)$ times the initial ones; layers are the differences between consecutive rectangles. On $0\le t\le T\delta^{-1}$, the energy in layer $j$, measured by its squared $H^1$ norm, is at most $C_N\delta^{2j}$ for $1\le j\le N$; the energy outside the $N$th rectangle is at most $C_N\delta^{2N+2}$. These bounds hold at every fixed depth $N$ under a uniform $H^s$ bound, $s>2$, with constants depending on $N$. The Sobolev bound holds for every fixed $T$ in the defocusing case. We also obtain layer estimates for support bounded in one coordinate and for geometrically decaying initial Fourier tails. The proof uses a filtered Poincare-Dulac normal form: input layers select which nonresonant interactions are removed, while the same layer weights control the interactions left in the equation. Finite coordinate changes and stability estimates transfer this hierarchy to the exact solution.

We study two-step recurrences with positive step sizes and nonnegative momentum coefficients whose terminal residual is the Chebyshev minimax polynomial on a prescribed spectral interval $[\mu,L]$. These recurrences have the same terminal error on a fixed quadratic, but their first-order responses to stepwise Hessian perturbations can differ. We prove that the sine-Jacobi recurrence of Part I is asymptotically optimal for this response norm within a factor of $1.000004$, uniformly over $0<\mu<L$. Every terminal-exact recurrence satisfies $A_N\ge(2\sqrt{c_{cert}}-o(1))N^{3/2}\epsilon_N^\star/(L-\mu)$ with $c_{cert}>1.14268353624$, whereas the sine-Jacobi recurrence attains the constant $2\sqrt{c_{\sin}}$ with $c_{\sin}<1.14269218$. The proof reduces the gain to the diagonal energy of a Jacobi Green matrix. A centering lift represents this matrix by an exponential kernel; packing its diagonal into a density on the line preserves the energy and controls the change in the Birman-Schwinger spectrum. A calibrated identity gives a lower bound using the ground parameter and one Fredholm determinant. Two further determinants and a trace observation improve the bound through a pointwise inequality on an explicit compact state region. One rational certificate verifies this inequality by interval arithmetic. A second certificate constructs a density satisfying the selected observations and both normalizations with energy below the sine value. Finally, no $C^1$ function of finitely many observations of the specified kinds gives a locally sharp lower bound at the sine density.

Long-horizon agents consume external content, invoke tools, and modify persistent state. Indirect prompt injection can exploit task-specific context, propagate across causally connected stages, and alter a consequential action while the workflow continues; we term this staged prompt injection. We build an automated, feedback-guided attack generation pipeline and apply it to Claude Code and Codex in their native runtimes. The confirmed attacks span eight workflow scenarios, seven attack goals, and six injection surfaces, showing that production agents are vulnerable to context-aware, multi-step injection over long horizons. Stopping such attacks requires a decision before each consequential action: input screening and completed-run evaluation cannot locate the intervention point, and existing pre-action methods use incompatible units and labels. We therefore formulate boundary action auditing: given initial context, a trajectory prefix, and a fully specified pending message or tool call, an auditor predicts Pass or Block before its effect occurs. Pairing attacked and benign executions yields a 479-pair, 3,112-unit benchmark. We further propose Path-Aligned Attribution (PAA), a training-free auditor that decomposes pending actions into operative elements and traces what supplied each value and guided each decision. PAA blocks only when the model attributes an unwarranted, material effect on an element to an attacker-reachable source that either provides unqualified steering or conflicts with visible evidence. Under full-benchmark fail-open scoring with Claude Sonnet 5, PAA reaches 86% Block recall at a 6-8% false-block rate (FBR), whereas ARGUS reaches 44-47% recall at 16-33% FBR. Under the same backend, on the tool calls that all three auditors natively support, PAA has higher recall and lower FBR than VIGIL and ARGUS; all paired 95% confidence intervals exclude zero.

Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence. Existing mitigation methods assume that memory-induced sycophancy originates from biased or incorrect memories and attempt to reduce this risk by filtering such memories at different stages of the memory pipeline. However, in the real world, objective and correct memories can still induce sycophancy, and the same memory can warrant different influence across different contexts. To this end, we propose MemAdapter, a novel framework that adaptively integrates retrieved memories to support objective and reliable reasoning. Specifically, MemAdapter consists of three components: (i) Counterfactual Induction, which leverages counterfactual reasoning to uncover the potential risk of retrieved memories; (ii) Context-Aware Reflection, which calibrates the inferential influence of each retrieved memory in light of the current task via self-reflection; and (iii) Evidence-Based Reasoning, which grounds the final response in appropriate evidence while preserving the legitimate influence of memory. Extensive experiments on three benchmarks demonstrate that MemAdapter consistently improves memory reliability across diverse scenarios. Our code is available at https://github.com/DEEP-JLU/MemAdapter.

Instruction following typically enforces discrete, response-level requirements, whereas an expert-authored skill prescribes procedural requirements spanning multiple phases and environment interactions. Given such a skill, we train the executor to execute all required phases instead of focusing solely on the final answer. We therefore introduce Grounded Skill-Following, which requires an agent to execute a fixed, expert-authored skill across its required phases by grounding decisions in environment observations. To achieve verifiable procedural execution, we formulate each skill as a skill contract combining visible skill instructions with an explicit contract runtime. The runtime specifies required phases, admissible actions, permitted transitions, and accepted termination. This structure provides a dense, verifiable training signal throughout execution. We leverage this by introducing Verified Progress Credit, which assigns rewards upon the initial completion of contract milestones and aggregates them into the trajectory return to guide policy optimization. During rollout, the contract runtime continuously tracks state transitions to provide Contract-State Feedback, which indicates whether the latest action is accepted and guides the agent toward valid next actions. To measure procedural compliance, we introduce the Protocol Completion Rate (PCR), defined as reaching accepted termination through all required phases, and decouple it from the final Task Outcome. Jointly trained with our framework, Qwen3.5-4B achieves Protocol Completion Rates of 99.27% on Math and 99.96% on Search, while slightly outperforming original baselines in Task Outcome (82.95% and 46.61%, respectively). Controlled studies examine how skill instructions, training signals, and contract-state feedback affect both metrics, while withholding interventions evaluate behavioral dependence on observation content.

Understanding how magnetic excitations and exchange interactions evolve with doping is crucial for deciphering the physics that shapes the phase diagram of high-temperature cuprate superconductors. Here, we clearly determine the behavior of the paramagnon dispersion in the oxychloride cuprate Na$_{x}$Ca$_{2-x}$CuO$_2$Cl$_2$ up to the highest doping level. We find that the paramagnon bandwidth, defined by the energy at the $X$ zone boundary $(0.5,0,0)$, remains unchanged within experimental uncertainty, even though it exhibits significant broadening. In contrast, along the nodal direction $\Gamma-M$ (i.e., from $(0,0,0)$ to $(0.5,0.5,0)$), the paramagnon energy shows a marked softening with doping, with a shift of up to $\Delta E\sim150$ meV at the midpoint of the zone for the highest doping, which is about half of its initial value in the antiferromagnetic phase. Calculations of the dynamical spin structure factor for a one-band Hubbard model, including hopping terms up to the third-nearest neighbor ($t^{\prime\prime}$), explain this behavior and accurately reproduce the observed wave vector dependence and directional variation in the Brillouin zone.

Conventional large-language-model chat interfaces typically follow user-initiated turns: each request elicits a response, after which the system waits for further input. Human asynchronous communication instead unfolds over time through message bursts, delays, silence, resumed topics, and self-initiated contact. Proactive dialogue therefore requires not only deciding when to speak, but also managing pending conversational actions and allowing them to be revised as context evolves. We introduce Proactive AI, a framework for proactive dialogue built around replannable temporal message queues. The framework treats interaction as a continuous event timeline and unsent conversational actions as revisable state. A user event, dialogue-pacemaker event, or scheduled decision may yield silence, one or more immediate messages, or future conversational actions. The system may also observe a user message without an immediate visible response and defer the response decision. Before delivery, every planned message must be reconsidered against the current context; reaching a scheduled time does not itself authorize delivery. We provide a formal semantics that characterizes when future conversational actions may be revised, withdrawn, or executed as context evolves. The framework extends AI participation beyond responses to current requests, enabling self-initiated exchanges without new requests, sustained follow-up over time, and revisions of subsequent actions as context evolves. It provides an executable basis for long-term human-AI interaction in tutoring, scientific collaboration, and everyday companionship.

We establish the log Sarkisov Program for strongly $\mathbb{Q}$-factorial compact Kähler threefolds.

Gastric Adenocarcinoma is a leading cause of cancer mortality. Although "Inflamed/Non-Inflamed" subtypes have been proposed to predict immunotherapy response, their identification relies on a costly 10-gene RNA signature. We propose a Cross-modal Contrastive Multiple Instance Learning (CCMIL) framework for cross-modal retrieval, imputing these molecular signatures directly from standard Hematoxylin & Eosin (H&E) slides. By leveraging a supervised contrastive objective, CCMIL aligns visual morphological patterns with molecular phenotypes into a shared latent space. This establishes an interpretable search-by-case retrieval engine, enabling pathologists to query a whole slide image to surface transcriptomically coherent neighbors and approximate RNA signatures without genomic sequencing at inference. Our results demonstrate that this retrieval-first approach captures the continuous phenotypic spectrum of tumor inflammation and yields clinically interpretable attention heatmaps. Furthermore, the learned representation also supports competitive downstream classification, providing a practical molecular pre-screening strategy.

This paper introduces a novel Support Vector Regression (SVR) model that incorporates Ordered Weighted Average (OWA) operators to differently penalize deviations of observations from the {\epsilon}-strip. The penalty is determined based on the position of each deviation in the ordered vector of all deviations. A key contribution of this work is the development of two nonlinear formulations: a continuous formulation for non-decreasing monotone weight vectors and a mixed-integer formulation for general weight vectors. By leveraging dual approaches associated with these formulations, the model accommodates nonlinear kernel functions. To enhance computational efficiency, two heuristic approaches are proposed for deriving suitable regression hyperplanes in reduced computation times, as compared to exact methods. Additionally, a third heuristic approach is developed to handle nonlinear kernel functions effectively. Computational experiments conducted on both real and synthetic datasets demonstrate that the exact formulations yield remarkable regression functions with respect to the following standard metrics: mean absolute errors (MAE) and mean squared errors (MSE). The heuristic approaches are shown to be particularly efficient for larger datasets, striking a balance between solution quality and computational effort.

We propose UltraM2M, a weakly-supervised speech enhancement algorithm building upon the recent unsupervised mixture-to-mixture (M2M) algorithm. M2M realizes unsupervised speech enhancement by training deep neural networks on a set of real-recorded noisy-reverberant multi-channel mixture signals to estimate target speech and non-target signals. The two estimated signals are penalized by a so-called mixture-constraint (MC) loss, which constrains them to reconstruct the observed mixture signals. Although shown to be effective, the mixture constraint may be too weak to enable sufficient noise reduction. To deal with this, UltraM2M extends M2M by further leveraging text transcripts of real-recorded mixtures to design an automatic speech recognition (ASR) loss to penalize the estimated speech signal. The ASR loss can be viewed as a form of weak supervision that could help unsupervised enhancement. Evaluation results on the CHiME-4 dataset show the effectiveness of UltraM2M.

Geostationary satellite observations are important for wildfire detection and monitoring. The current study evaluates machine learning models for MTG FCI near-real-time fire detection in 1- and 2-km spatial configurations and compares them with threshold-based algorithms. The models were trained and evaluated using VIIRS fire reference data across diverse ecological regions in Europe, Africa, and the Middle East. The key results are that 1-km models significantly outperform both their 2-km variants and operational threshold products. The constructed 1-km models achieved F1 scores higher by up to 0.36 compared to baseline products. Importantly, the 1-km models detected small fires with higher probability compared to competing models. Finally, the models robustly detected fires up to 260 min earlier than baseline products. To support opensource applications, our trained models are publicly available.