arXiv:2605.12226v4 Announce Type: replace
Abstract: Recent advances in large language models (LLMs) pose new challenges for ontology matching (OM). While OM systems built on LLMs have shown remarkable capabilities in discovering more matching candidates, traditional OM validation that relies on domain experts has become overwhelming. In this study, we explore the use of crowdsourcing for OM validation and introduce a novel crowdsourcing system. We propose three domain-specific mechanisms, namely differential trustworthiness, coherence pre-filling, and time-dependent opinion, to ensure the quality of crowdsourcing for OM validation. We demonstrate that our crowdsourcing system can be integrated with existing OM systems to enable human-in-the-loop validation. The evaluation of the system shows its effectiveness in handling diverse user groups and different annotation settings. We discuss two real-world use cases of the system and current limitations for improvement.
Science Journals
arXiv:2606.04131v1 Announce Type: new
Abstract: We are interested in the so-called multiple-node immunization problem for complex networks under attack by a viral agent. It consists in identifying and removing a set of nodes of size $k$ in a graph to maximize the impeding of virus spread. A few approaches have been proposed in the literature based on numerical and theoretical insights on how classical models for virus spread evolve on graphs. Based on the analysis of these models, the maximal eigenvalue of the adjacency matrix of the graph has become a classical measure of how resilient the network is. Thus, a clear, well-explored approach for multiple-node immunization consists of identifying a set of $k$ nodes in such a way that the reduced network, obtained by removing these nodes, has a minimal largest eigenvalue. This spectral optimization problem turns out to be a computationally hard problem for which only greedy algorithms offer good solutions at efficient computational time. Among those, the so-called Netshield algorithm represents one of the reference choices. The latter is, in fact, a clearly defined algorithm aiming at optimizing a certain sub-modular functional, called shield-value, which approximates the original optimization problem. We propose here a novel procedure, based on random walk kernels and related random spanning forests, to build a new algorithm, referred to as K-shield, which enhances Netshield searching performance at the same computational complexity. We give theoretical insights behind this novel method, which could also be used for other optimization problems, and then test it via numerical showcase experiments on various benchmarks.
arXiv:2601.04493v3 Announce Type: replace
Abstract: Continuum robots are flexible, slender manipulators well suited for confined surgical environments. In these settings, unknown interaction forces and model uncertainty significantly affect robot shape, motivating state estimation from external observations. Existing estimation methods either neglect actuation modeling or rely on simplified deterministic actuation models. In contrast, we jointly estimate robot shape, external loads, and actuation inputs using mechanically principled actuation priors. To achieve this, we present a discrete Cosserat rod formulation with piecewise-linear strain integration that provides high numerical accuracy while inducing a sparse factor graph structure for efficient nonlinear optimization. We extend the framework to tendon-driven and parallel robots in simulation and validate it experimentally on a surgical concentric tube robot. Overall, our approach enables principled real-time estimation across multiple robot architectures while providing direct access to manipulator Jacobians through the linearized factor graph.
arXiv:2606.04923v1 Announce Type: new
Abstract: Rubric-based reinforcement learning (RL) uses an LLM-as-a-Judge (LaaJ) to score model outputs according to rubrics as rewards. However, policy models may exploit latent biases in the judge, leading to reward hacking and ineffective or unsafe training outcomes. In real-world rubric-based RL, such hacking behaviors are often subtle and entangled with multiple judge biases, making them difficult to analyze, detect, and mitigate. In this paper, we introduce CHERRL, a controllable hacking environment for rubric-based RL. By injecting known biases into LaaJ, CHERRL enables stable reproduction of reward hacking, explicit observation of reward divergence, and precise identification of hacking onset. This provides a clean experimental testbed for studying the mechanisms and mitigations of reward hacking in rubric-based RL. To demonstrate its utility, we analyze different judge biases from the perspectives of discoverability and exploitability, and explore an agent-based system for automatically detecting reward hacking onset from training logs. The code and environment are publicly available at https://github.com/THUAIS-Lab/CHERRL.
arXiv:2601.04051v3 Announce Type: replace
Abstract: Symbolic regression aims to find symbolic expressions that describe datasets. Due to its inherent interpretability, symbolic regression (SR) is a powerful paradigm for scientific discovery. Recent advances have expanded SR to describe related phenomena using a single expression with varying sets of parameters, thereby introducing a single categorical variable. To illustrate, this enables the search for a single expression describing temperaturedependent viscosity across multiple fluids, while simultaneously identifying a distinct set of fluid-specific parameters. We expand upon prior efforts by considering multiple categorical variables and introducing intermediate levels of parameter sharing. Rather than parameters being either entirely universal or entirely unique, some parameters can also be shared across specific categories while remaining distinct for others. This allows for separating universal effects (shared parameters), category-specific trends (partially-shared parameters), and category interactions (non-shared parameters). We test the limits of this setup in terms of reducing data requirements and transfer learning using a synthetic, fitting-only example. Furthermore, we apply the method to an astrophysics dataset also used in a previous single-category study. In comparison, we achieve similar fit quality with significantly fewer parameters while extracting additional information about the problem.
arXiv:2601.03569v3 Announce Type: replace
Abstract: Local Intrinsic Dimensionality (LID) has shown strong potential for anomaly detection in high-dimensional data, including landslide failure detection in granular media, where early and accurate identification of failure zones is crucial for effective geohazard mitigation. However, this task is still challenging due to the spatial correlations and temporal dynamics that are inherently present in surface displacement data. To address this gap, we propose a novel unsupervised framework called spatiotemporal LID (st-LID) that generalizes the LID for robust failure detection in landslide monitoring networks. Our approach introduces three key innovations: (1) Kinematic enhancement, incorporating velocity into the LID computation to capture instantaneous deformation rates and short-term temporal dynamics; (2) Bayesian spatial fusion, which aggregates LID values across spatial neighborhoods via Bayesian estimation, to embed spatial correlations and account for localized noise; and (3) Temporal modeling (t-LID), a new variant that characterizes long-term dynamics of displacement data, providing a robust temporal representation of displacement behavior. By unifying these components, st-LID identifies complex, multi-stage failure zones often overlooked by existing methods. Extensive experiments show that st-LID consistently outperforms state-of-the-art unsupervised baselines in detection precision and lead-time, providing a robust foundation for landslide early warning systems and targeted risk intervention to enhance community resilience and preparedness strategies.
arXiv:2606.04388v1 Announce Type: new
Abstract: Federated Learning (FL) has emerged as an effective paradigm for collaborative intelligence while preserving data privacy. However, data heterogeneity arising from non-IID distributions and decentralized security threats remain significant challenges, particularly in resource-constrained enterprise environments. This paper presents TITAN-FedAnil+, a Trust-Based Adaptive Network for blockchain-enabled federated learning in intelligent enterprises. The proposed framework introduces affinity propagation-based adaptive clustered aggregation to identify and filter malicious updates without requiring prior knowledge of the number of attackers. In addition, GPU-accelerated vectorization is employed to improve computational efficiency, while a signed state jump mechanism enables lightweight blockchain resynchronization. Experimental results demonstrate substantial reductions in memory overhead, achieving up to 81% savings across 50 communication rounds on constrained 8 GB edge devices compared with the baseline framework. The results indicate that TITAN-FedAnil+ effectively improves robustness, scalability, and resource efficiency for secure federated learning deployments in intelligent enterprise environments.
arXiv:2606.04924v1 Announce Type: new
Abstract: The widespread use of Large Language Models (LLMs) as writing tools challenges the validity of crowdsourced data, as crowdworkers may outsource tasks to models. To better understand how this is addressed, we surveyed 155 researchers in NLP and related disciplines about their experiences and opinions on collecting free-text responses via crowdsourcing. This paper provides an overview of practitioners' challenges, mitigation strategies, and the foreseen implications on data quality. 44% of respondents reported observing LLM usage in their crowdsourced data. While 93% of them had anticipated this, half were unsure what precautions to take. The most prevalent detection strategies are distinctive textual style patterns and unusually fast completion times. Overall, survey responses show that the research community is aware of the problem and taking measures, but existing efforts remain insufficient to fully address it. Finally, we derive a set of considerations to guide future crowdsourced free-text data collection in the era of LLMs.
arXiv:2606.04925v1 Announce Type: new
Abstract: Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task setting of unsupervised VPS, omitting any human supervision. Existing unsupervised scene understanding works mainly focused on image segmentation tasks; the video domain remains underexplored. We propose VideoCUPS, the first unsupervised VPS approach. VideoCUPS generates temporally consistent panoptic video pseudo-labels from scene-centric videos by exploiting unsupervised depth, motion, and visual cues. Training on these pseudo-labels using a novel Video DropLoss yields an accurate, unsupervised VPS model. To benchmark progress, we introduce a comprehensive evaluation protocol and four competitive baselines, extending state-of-the-art unsupervised panoptic image and instance video segmentation models to VPS. VideoCUPS outperforms all baselines and demonstrates strong label-efficient learning. With VideoCUPS, our evaluation protocol, and baselines, we provide a strong foundation for future research on unsupervised VPS.
arXiv:2606.04928v1 Announce Type: new
Abstract: Large Language Models (LLMs) are increasingly deployed across diverse applications, raising critical questions for governance, accountability, and data provenance. Understanding which training data most influenced a model's output remains a fundamental open problem. We address this challenge through training data attribution (TDA) for auto-regressive LLMs by expanding upon the inverse formulation: How would training data be affected if the model had seen the generated output during training? Our method perturbs the base model using bidirectional gradient optimization (gradient ascent and descent) on a generated text sample and measures the resulting change in loss across training samples. Our framework supports attribution at arbitrary data granularity, enabling both factual and stylistic attribution. We evaluate our method against baselines on pretrained models with known datasets, and show that it outperforms previous work on influence metrics, thereby enhancing model interpretability, an essential requirement for accountable AI systems.
arXiv:2512.24698v2 Announce Type: replace
Abstract: Generating dynamic motions for legged robots remains a challenging problem. While reinforcement learning has achieved notable success in various legged locomotion tasks, producing highly dynamic behaviors often requires extensive reward tuning or high-quality demonstrations. Leveraging reduced-order models can help mitigate these challenges. However, the model discrepancy poses a significant challenge when transferring policies to full-body dynamics environments. In this work, we introduce a continuation-based learning framework that combines simplified model pretraining and model-homotopy-inspired transfer to efficiently generate and refine complex dynamic behaviors. First, we pretrain the policy using a single rigid body model to capture core motion patterns in a simplified environment. Next, we employ a continuation strategy to progressively transfer the policy to the full-body environment, minimizing performance loss. To define the continuation path, we introduce a parametric transition path from the single rigid body model to the full-body model by gradually redistributing mass and inertia between the trunk and legs. The proposed method achieves faster convergence and demonstrates superior stability during the transfer process compared to baseline methods. Our framework is validated on a range of dynamic tasks, including flips and wall-assisted maneuvers, and is successfully deployed on a real quadrupedal robot.
arXiv:2512.23965v2 Announce Type: replace
Abstract: Generating samples from complex and high-dimensional distributions is ubiquitous in various scientific fields of statistical physics, Bayesian inference, scientific computing and machine learning. Very recently, Huang et al. (IEEE Trans. Inform. Theory, 2025) proposed new Schr\"odinger-F\"ollmer samplers (SFS), based on the Euler discretization of the Schr\"odinger-F\"ollmer diffusion evolving on the unit interval $[0, 1]$. There, a convergence rate of order $\mathcal{O}(\sqrt{h})$ in the $L^2$-Wasserstein distance was obtained for the Euler discretization with a uniform time step-size $h>0$. By introducing a temperature parameter, different samplers are proposed in this paper, based on the Euler discretization of the Schr\"odinger-F\"ollmer process with temperatures. As revealed by numerical experiments, high temperatures are vital, particularly in sampling from multimodal distributions. Further, a novel approach of error analysis is developed for the time discretization and an enhanced convergence rate of order $\mathcal{O}(h)$ is obtained in the $L^2$-Wasserstein distance, under certain smoothness conditions on the drift. This significantly improves the existing order-half convergence in the aforementioned paper. Unlike Langevin samplers, SFS is gradient-free, works in a unit interval $[0, 1]$ and does not require any ergodicity. Numerical experiments confirm the convergence rate and show that, the SFS substantially outperforms vanilla Langevin samplers, particularly in sampling from multimodal distributions.
arXiv:2512.22105v2 Announce Type: replace
Abstract: Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection methods, which are computationally efficient but rely on handcrafted association heuristics, and end-to-end approaches, which learn association from data at the cost of higher computational complexity. We propose Track-Detection Link Prediction (TDLP), a tracking-by-detection method that performs per-frame association via link prediction between tracks and detections, i.e., by predicting the correct continuation of each track at every frame. TDLP is architecturally designed primarily for geometric features such as bounding boxes, while optionally incorporating additional cues, including pose and appearance. Unlike heuristic-based methods, TDLP learns association directly from data without handcrafted rules, while remaining modular and computationally efficient compared to end-to-end trackers. Extensive experiments on multiple benchmarks demonstrate that TDLP consistently surpasses state-of-the-art performance across both tracking-by-detection and end-to-end methods. Finally, we provide a detailed analysis comparing link prediction with metric learning-based association and show that link prediction is more effective, particularly when handling heterogeneous features such as detection bounding boxes. Our code is available at \href{https://github.com/Robotmurlock/TDLP}{https://github.com/Robotmurlock/TDLP}.
arXiv:2606.04846v1 Announce Type: new
Abstract: As Large Language Models (LLMs) become increasingly popular in educational settings, they raise important questions about the ethical implications of their use. Publicly available online chatbots are quickly improving in capability and accuracy leading to more widespread use, including among students looking for help with their homework. This makes it crucial to consider whether these models are aligned with educational standards. Because curriculum standards in the United States are set at the state level, they differ significantly in required content, emphasis, and narrative focus. In this work, we develop an LLM-based pipeline to identify variations in U.S. History curricula across states and evaluate the extent to which different LLMs reflect these state-specific curricular differences. In addition, we conduct controlled experiments that vary user personas by stating user attributes such as geographic location, grade level, gender and race to evaluate the sensitivity of LLM responses to user characteristics. We find that while models are able to adjust their presentation of historical topics, these shifts may come from the perceived political leanings of states and do not necessarily reflect actual curriculum content. Additionally, models successfully adapt to a student's grade level while showing minimal sensitivity to race or gender, suggesting they are capable of useful adaptation to student personas with limited demographic bias. Together, these findings highlight potential risks that open access to LLM chatbots may cause to student learning outcomes stemming from misalignment with state curriculum standards and highlight the need for more robust alignment techniques.
arXiv:2605.00182v3 Announce Type: replace
Abstract: Proteins are shaped by gradual evolution under biophysical and functional constraints. Protein language models learn rich evolutionary constraints from large-scale sequences, and discrete diffusion-based protein language models~(\eg, DPLMs) are promising for both understanding and generation. However, existing DPLMs typically rely on masked diffusion that contradicts a simple biological intuition: proteins evolve through accumulated edits, not by emerging from masks. Consequently, these frameworks lack explicit pretraining objectives for substitution and insertion/deletion (indel) operations, limiting both optimization-style post-editing and flexible guided generation. To address these limitations, we present DPLM-Evo, an evolutionary discrete diffusion framework that explicitly predicts substitution, insertion, and deletion operations during denoising. DPLM-Evo decouples an upsampled-length latent alignment space from the variable-length observed sequence space, which makes indel-aware generation tractable. To better align substitutions with real evolution, we further introduce a contextualized evolutionary noising kernel that produces biologically informed, context-dependent mutation patterns. Across tasks, DPLM-Evo improves sequence understanding and achieves state-of-the-art mutation effect prediction performance on ProteinGym in the single-sequence setting. It also enables variable-length simulated evolution, and post-editing/optimization of existing proteins via explicit edit trajectories.
arXiv:2606.04946v1 Announce Type: new
Abstract: Consistency is an important property in dynamic submodular maximization and entails maintaining a near-optimal solution at all times, making only a small number of adjustments to the solution in each step. Prior work has explored this question for the insertion-only case, where the algorithm faces a stream of $n$ insertions, and has established lower and upper bounds for the cardinality-constrained version of the problem. We consider this question in the fully dynamic setting, where the stream of operations may contain both insertions and deletions.
We develop a general framework for designing algorithms for this setting, and instantiate it to obtain the first constant-factor approximations with sublinear consistency. For cardinality constraints, we propose a $\frac 12 - O(\varepsilon)$ approximation that is $O\left(\frac{1}{\varepsilon^2}\right)$ consistent. For rank-$k$ matroid constraints, we construct a $\frac 14 - O(\varepsilon)$ approximation to the dynamic optimum that is $O\left(\frac{\log k}{\varepsilon^2}\right)$ consistent.
arXiv:2606.04952v1 Announce Type: new
Abstract: CARE-link is an open-source, web-based clinical support platform designed to improve the management of gestational diabetes by linking clinicians and patients through an LLM-mediated workflow. The system aggregates patient-generated data outside the hospital, summarizes relevant clinical information, and delivers context-aware decision support to clinicians. For patients, CARE-link provides clear explanations of management plans and delivers timely lifestyle guidance through a WhatsApp interface. The integrated dual-facing design aims to promote continuous monitoring, support individualized care, and reduce the burden of in-clinic follow-ups. Built with a modular architecture, the platform can be adapted to other chronic conditions requiring longitudinal tracking and behavioral support. CARE-link has the potential to enhance clinical oversight, promote patient compliance, and strengthen continuity of care particularly in resource-constrained settings.
arXiv:2606.04957v1 Announce Type: new
Abstract: System-generated logs underpin security monitoring, yet their rigid template-based format hinders both automated analysis and human comprehension. We present NLLog (Natural-Language Log), a lightweight pipeline that deterministically rewrites parsed templates into WHO-WHAT-SEVERITY sentences, pools them with term-frequency-inverse-document-frequency weighting, classifies sessions with tree ensembles, and back-projects evidence with TreeSHAP for analyst review. On Hadoop Distributed File System (HDFS) and Blue Gene/L (BGL) corpora, NLLog exceeds two reproduced matched-protocol baselines; across HDFS, BGL, and the AIT Alert Data Set, it sustains low false-positive rates with commodity-hardware latency suitable for security operations center triage. Coverage, sparse-versus-dense, faithfulness, and adversarial ablations show that fallback sufficiency is corpus-dependent, that an enrollment-time coverage check can surface refinement requirements before deployment, and that an auditable deterministic rewrite combined with lightweight dense encoding provides a measurable representation layer for log-anomaly detection and triage.
arXiv:2512.21917v3 Announce Type: replace
Abstract: Policy alignment to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., Bradley-Terry model / logistic link). Misspecification of this link can bias inferred rewards and misalign learned policies. We study policy alignment under an unknown and unrestricted link function. We formulate an $f$-divergence-constrained reward maximization problem and show that realizability in a policy class induces a semiparametric single-index binary choice model, where a scalar policy-induced index captures all dependence on demonstrations and the remaining preference distribution is unrestricted. Rather than impose identifiability of structural parameters of such a model and estimate them, as in econometrics, we develop methods that directly learn policies, with the reward function implicit, analyzing error to the optimal policy and allowing for unidentifiable and nonparametric indices. We prove link-agnostic convergence guarantees in terms of generic function complexity measures and validate the methods and theory empirically. Code is available at https://github.com/causalml/spo/.
arXiv:2606.04389v1 Announce Type: new
Abstract: Large Language Models (LLMs) show promise in psychological counseling, yet existing benchmarks rely heavily on highly cooperative simulated clients. We observe a critical counselor-following phenomenon: these clients often rapidly shift from resistance to compliance after only a few turns, creating an illusion of therapeutic progress and inflating scores under current evaluation protocols through superficial empathy. To address this evaluation mismatch, we propose a Cognitive Behavioral Therapy (CBT)-grounded resistance-aware framework. We introduce CARS, a client simulator that explicitly models dynamic resistance via Cognitive Conceptualization Diagrams (CCDs). We present STREAMS, a dual-module framework that decouples strategic reasoning (Thinker) from response generation (Presenter) and optimizes it via reinforcement learning. We further propose EWTS-MI, an entropy-weighted metric for evaluating responsiveness under high-friction interactions. Experiments across resistant and non-resistant counseling settings validate our findings on evaluation mismatch and demonstrate the effectiveness of resistance-aware training for improving strategic robustness under challenging counseling interactions.
arXiv:2512.21094v3 Announce Type: replace
Abstract: Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language, yet its evaluation remains fragmented, often relying on unimodal metrics or narrowly scoped benchmarks that fail to capture cross-modal alignment, instruction following, and perceptual realism under complex prompts. To address this limitation, we present T2AV-Compass, a unified benchmark for comprehensive evaluation of T2AV systems, consisting of 500 diverse and complex prompts constructed via a taxonomy-driven pipeline to ensure semantic richness and physical plausibility. Besides, T2AV-Compass introduces a dual-level evaluation framework that integrates objective signal-level metrics for video quality, audio quality, and cross-modal alignment with a subjective MLLM-as-a-Judge protocol for instruction following and realism assessment. Extensive evaluation of 11 representative T2AVsystems reveals that even the strongest models fall substantially short of human-level realism and cross-modal consistency, with persistent failures in audio realism, fine-grained synchronization, instruction following, etc. These results indicate significant improvement room for future models and highlight the value of T2AV-Compass as a challenging and diagnostic testbed for advancing text-to-audio-video generation.
arXiv:2604.28173v3 Announce Type: replace
Abstract: Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that capture the atomic joint movements and Action Motifs that are formed by their temporal compositions and encode similar body movements found across different overall human actions. We derive A4Mer, a nested latent Transformer to learn this hierarchical representation from human pose data in a fully self-supervised manner. A4Mer splits a 3D pose sequence into variable-length segments and represents each segment as a single latent token (Action Atoms). Through bottom-up representation learning, temporal patterns composed of these Action Atoms, which capture meaningful temporal spans of reusable, semantic segments of body movements, naturally emerge (Action Motifs). A4Mer achieves this with a unified pretext task of masked token prediction in their respective latent spaces. We also introduce Action Motif Dataset (AMD), a large-scale dataset of multi-view human behavior videos with full SMPL annotations. We introduce a novel use of cameras by mounting them on the feet to achieve their frame-wise annotations despite frequent and heavy body occlusions. Experimental results demonstrate the effectiveness of A4Mer for extracting meaningful Action Motifs, which significantly benefit human behavior modeling tasks including action recognition, motion prediction, and motion interpolation.
arXiv:2512.19968v3 Announce Type: replace
Abstract: Permissionless blockchains achieve consensus while allowing unknown nodes to join and leave the system at any time. They typically come in two flavors: proof of work (PoW) and proof of stake (PoS), and both are vulnerable to attacks. PoS protocols suffer from long-range attacks, wherein attackers alter execution history at little cost, and PoW protocols are vulnerable to attackers with enough computational power to subvert execution history. PoS protocols respond by relying on external mechanisms like social consensus; PoW protocols either fall back to probabilistic guarantees, or are slow.
We present Sieve-MMR, the first fully-permissionless protocol with deterministic security and constant expected latency that does not rely on external mechanisms. We obtain Sieve-MMR by porting a PoS protocol (MMR) to the PoW setting. From MMR we inherit constant expected latency and deterministic security, and proof-of-work gives us resilience against long-range attacks. The main challenge to porting MMR to the PoW setting is what we call time-travel attacks, where attackers use PoWs generated in the distant past to increase their perceived PoW power in the present. We respond by proposing Sieve, a novel algorithm that implements a new broadcast primitive we dub time-travel-resilient broadcast (TTRB). Sieve relies on a black-box, deterministic PoW primitive to implement TTRB, which we use as the messaging layer for MMR.
arXiv:2606.04107v1 Announce Type: new
Abstract: Single-image reflection separation is highly challenging under extreme conditions like glare or weak reflections. Existing methods often struggle to recover both layers in glare or weak-reflection scenarios because of insufficient information. This paper presents a diffusion model explicitly fine-tuned for this task, leveraging generative diffusion priors for robust separation. Our method simultaneously generates transmission and reflection layers through a unified diffusion model, incorporating a novel cross-layer self-attention mechanism for better feature disentanglement. We further introduce a disjoint sampling strategy to iteratively reduce interference between the layers during diffusion and a latent optimization step with a learned composition function for improved results in complex real-world scenarios. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods on multiple real-world benchmarks. Project page: https://brian90709.github.io/diff-reflection-separation/
arXiv:2512.17678v2 Announce Type: replace
Abstract: Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling. However, most existing feature selection approaches either operate as multi-stage pipelines or rely on post hoc feature attribution, making selection and prediction weakly coupled. In this work, we present YOTO (you only train once), an end-to-end framework that jointly identifies discrete gene subsets and performs prediction within a single differentiable architecture. In our model, the prediction task directly guides which genes are selected, while the learned subsets, in turn, shape the predictive representation. This closed feedback loop enables the model to iteratively refine both what it selects and how it predicts during training. Unlike existing approaches, YOTO enforces sparsity so that only the selected genes contribute to inference, eliminating the need to train additional downstream classifiers. Through a multi-task learning design, the model learns shared representations across related objectives, allowing partially labeled datasets to inform one another, and discovering gene subsets that generalize across tasks without additional training steps. We evaluate YOTO on two representative single-cell RNA-seq datasets, showing that it consistently outperforms state-of-the-art baselines. These results demonstrate that sparse, end-to-end, multi-task gene subset selection improves predictive performance and yields compact and meaningful gene subsets, advancing biomarker discovery and single-cell analysis.