Ddx3x deficiency in mice impairs corticofugal motor circuits and causes motor deficits that are attenuated by early-life exercise
PNASProceedings of the National Academy of Sciences, Volume 123, Issue 44, November 2026.
SignificanceAcquisition of motor skills during infancy is critical for a child’s ability to interact with the physical and social environment and motor impairments are frequent in individuals with neurodevelopmental disorders. Here, we studied the neural ...
SignificanceAcquisition of motor skills during infancy is critical for a child’s ability to interact with the physical and social environment and motor impairments are frequent in individuals with neurodevelopmental disorders. Here, we studied the neural ...
The efficiency of information gain by natural selection
PNASProceedings of the National Academy of Sciences, Volume 123, Issue 44, November 2026.
SignificanceNatural selection changes the genetic makeup of a population in ways that provide information about its environmental history. In the 1960s, Motoo Kimura noted that a lineage that acquires information through selection has suboptimal fitness ...
SignificanceNatural selection changes the genetic makeup of a population in ways that provide information about its environmental history. In the 1960s, Motoo Kimura noted that a lineage that acquires information through selection has suboptimal fitness ...
Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution
arXiv cs.AIarXiv:2609.04820v3 Announce Type: replace-cross
Abstract: Sandbox execution and memory forensics are among the most resources intensive stages of malware triage. Static analysis can scale to millions of files while dynamic and memory analysis require minutes per sample. Because multimodal ransomware detectors often apply every modality to every sample, costs and latency rise even when static evidence suffice.We proposea cost aware Hierarchical Multi Agent System (HMAS) that frames evidence acquisition as a budgeted sequential decision problem enabling timely ransomware detection. Specialist agents generate schema validated risk signals for each modality while domain controllers aggregate evidence and coordinate analysis. The orchestrator starts with static evidence and escalates only if confidence is low or signals disagree. A locally hosted language model provides a limited, accoutable review without replacing the deterministic pipeline. Experiments on 16 ransomware families show 94.12% binary accuracy (F1 0.9376, ROC-AUC 0.9989). For multi class family attribution, it achieves 98.90% accuracy (macro-F1 0.9748). The system resolves 57.95% of the samples using static analysis alone whhile only 6.21% require the full pipeline. Compared with exhaustive cost of 12.0 units,the proposed system reduces te average cost to 6.724 units, representing approximately 44% saving. Zero day experiments further examine generalization to unseen ransomware families. Additional evaluations examine cost sensitivity and component level contribution. LLM-assisted review provides only marginal improvement in F1 while introducing additional computational overhead. Overall, the results show the potential of adaptive hierarchical multi agent orchestration to balance ransomware detection performance, family attribution analysis cost and decision latency.
Cost-efficient Active Learning for Referring Image Segmentation and Grounding
arXiv cs.AIarXiv:2608.30621v3 Announce Type: replace-cross
Abstract: Collecting natural-language referring expressions along with region annotations, such as masks or boxes, is a major bottleneck in visual grounding (VG), as annotators must write descriptions that distinguish target regions from visually similar ones. We tackle this by formulating active learning (AL) for VG under the realistic setting where only raw images are available without accompanying text. Since ground-truth text is unavailable, sample selection must estimate which images contain ambiguous regions that would require discriminative referring expressions. To address this, we generate auxiliary region-text pairs using foundation models, and introduce Referred Region Ambiguity, a new acquisition function that measures whether the model's confidence collapses onto a single region or disperses across multiple candidates. It allows our method to prioritize images with strong cross-region competition, which are more informative due to their visual ambiguity. We also design a referring-expression annotation interface that helps annotators quickly focus on writing discriminative language with a few clicks. Experiments on RIS and REC benchmarks show that our AL framework consistently outperforms several AL baselines, while a user study shows up to 1.6X faster description labeling of ours.
Functional compatibility as a determinant of persistent neural learning
arXiv cs.AIarXiv:2608.22462v4 Announce Type: replace-cross
Abstract: Neural networks can acquire new capabilities while damaging existing ones, but what determines whether new learning persists remains unclear. We identify functional compatibility, the extent to which incoming learning can coexist with behaviour that must be preserved, as an experimentally manipulable causal determinant of persistence. From identical neural states, we vary compatibility while matching unrestricted learning opportunity and imposing a common retention requirement. Persistent learning increases with compatibility across independent directions, convolutional and transformer architectures, vision and text, and a ten-seed replication. Learning rules and retention constraints determine how much compatible opportunity is retained, whereas nonlinear geometry limits the matched intervention at larger update norms. Functional compatibility therefore reframes stability-plasticity from preventing forgetting to determining which new learning can coexist with existing function and persist.
EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment
arXiv cs.AIarXiv:2608.14011v2 Announce Type: replace-cross
Abstract: Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the shared token space. Recent attempts have introduced Multi-Token Prediction (MTP) into this field, yet they primarily inherit its efficiency merit, leaving its potential as dense supervision unexplored. Unlocking this potential hinges on whether future behaviors qualify as informative supervision. Our analysis reveals that future behaviors carry a semantic echo of the current one far above that of random pairs, which nevertheless decays along horizons under intent transitions, making them informative yet order-dependent signals. Motivated by this, we propose EchoRec, which empowers MTP with cycle-consistent holistic preference alignment across multi-horizon for generative recommendation. It comprises two synergistic modules. Horizon-aware Preference Generation (HPG) sequentially chains lightweight auxiliary branches upon the base recommender, where each branch conditions on its predecessor to respect preference evolution. Verifiable Holistic-Preference Alignment (VHA) further consolidates them into the holistic preference and echoes it back through cycle-consistent projectors to suppress spurious alignment, with a theoretical guarantee that excludes the rank-collapse form of spurious alignment under an invertible round trip, enabling the holistic preference to be retained in the decoding representation. All auxiliary components serve as disposable scaffolding discarded at inference, introducing negligible online serving overhead. Extensive experiments on four datasets demonstrate the superiority of our EchoRec, together with its naturally acquired multi-item generation ability. Our code and datasets will be available upon acceptance.
Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and Generation
arXiv cs.AIarXiv:2606.30266v2 Announce Type: replace-cross
Abstract: Motion-language agents must possess the bidirectional capability to both understand human movement (motion-to-text, M2T) and generate it from natural language (text-to-motion, T2M). While foundational models have achieved strong performance in static settings, autonomous agents operating in dynamic environments must continuously incorporate new motion concepts -- such as novel athletic styles or specialized gestures -- without catastrophic forgetting of previously acquired skills. We investigate the stability-plasticity trade-off in bidirectional motion-language learning under sequential task exposure. Building on a frozen large language model backbone, we introduce low-rank adaptation (LoRA) variants designed to mitigate inter-task interference. We specifically propose mixture-of-experts architectures that utilize an autoencoder-based router to select task-specific experts at inference time, so that no task-label is needed. To evaluate these methods, we establish a reproducible five-task benchmark derived from HumanML3D through semantic clustering of motion descriptions. Our experimental results demonstrate near-zero forgetting across both M2T and T2M directions while maintaining high generation and captioning quality. Furthermore, we show that hard expert selection via routing significantly outperforms soft expert blending in quality metrics, indicating that preserving expert isolation is critical for maintaining performance in our continual learning setting. Finally, we observe that a divergence between token-level accuracy and downstream generation quality may occur, highlighting the need for more comprehensive evaluation protocols in future research on lifelong motion-language agents.
Selective Linkage Precision for Released Medical Vision-Language Models
arXiv cs.AIarXiv:2606.02276v2 Announce Type: replace-cross
Abstract: Hospitals may release de-identified chest radiographs while restricting access to their reports. An attacker who already has reports from the same population and their metadata can use a vision-language model (VLM) to match images to reports. We introduce selective linkage precision, which measures correct matches among the highest-confidence queries after filtering candidates by the available attributes. Across 8 public VLMs and 3 chest radiograph datasets, the maximum whole-pool Recall@1 is 0.40%. However, this metric averages over every query without attribute filtering. On ReXGradient-160K, MedSigLIP-448 reaches 67.68% precision at a budget of 100 after filtering by sex, age band, and projection, with a median of 327 candidate reports. On the same eligible query set, an attribute-only policy reaches 24.99% and the model alone reaches 1.98%. Adding acquisition year, available in only 1 of the 3 datasets, yields 99.05% precision and a median of 24 candidates. Uniform guessing on the observed selected queries has an expected precision of 19.91%. Expanding the primary-setting collection to all 123,100 ReXGradient studies lowers precision to 37.23%. On BioViL-T, the tested head finetuning procedures do not lower linkage below the public checkpoint. Selective linkage precision requires inference without retraining and could help hospitals evaluate which attributes to publish.
A Multi-Instance LLM Framework for Rating the Quality of Surgical Feedback
arXiv cs.AIarXiv:2605.25440v2 Announce Type: replace-cross
Abstract: Verbal feedback delivered by attending surgeons in the operating room plays a critical formative role in resident trainee skill acquisition. Yet, assessing the quality of trainer feedback and its effectiveness in influencing trainee behavior during live surgery remains a challenge. Prior studies assessed feedback content relying on extensive manual annotation by expert human raters and focused on developing broad taxonomies that overlook the qualitative aspects of feedback delivery such as clarity or urgency. Limited existing automated methods, including keyword analysis and topic modeling, also fail to capture these nuanced aspects. We introduce a two-stage LLM-based framework that discovers interpretable feedback quality criteria grounded in the context of surgical training. Our method uses multi-instance prompting via repeated independent sampling of candidate criteria followed by consolidation, and surgical domain knowledge injection to discover a small set of human interpretable scoring criteria (e.g., Encouragement, Urgency, Clarity). These criteria are then used to automatically score live surgical feedback via an LLM-as-a-judge approach. Evaluation on 4.2k trainer feedback instances demonstrates that our AI-discovered criteria outperform prior content-based frameworks in predicting feedback effectiveness, including observed trainee behavioral adjustments and trainer approval. This work advances scalable, human-aligned assessment of communication quality in the operating room and provides a foundation for improving surgical teaching practices.
InTAct: Interval-based Task Activation Consolidation for Continual Learning
arXiv cs.AIarXiv:2511.17439v3 Announce Type: replace-cross
Abstract: Continual learning seeks to acquire new knowledge while preserving previously learned representations. Despite the success of prompt-based methods, they remain fragile in domain-incremental learning scenarios, where shifts in the input distribution cause representation drift in shared layers and lead to forgetting. We introduce InTAct, a method that preserves functional behavior in shared representations without freezing parameters or retaining past data. InTAct constrains updates within activation regions associated with prior domains, while allowing flexible adaptation elsewhere, thereby stabilizing neuron functionality rather than directly restricting parameter values. The approach is architecture-agnostic, integrates seamlessly with existing prompt-based frameworks, and matches or outperforms state-of-the-art methods on domain-incremental benchmarks.
Tactile MNIST: Benchmarking Active Tactile Perception
arXiv cs.AIarXiv:2506.06361v3 Announce Type: replace-cross
Abstract: Tactile perception has the potential to significantly enhance dexterous robotic manipulation by providing rich local information that can complement or substitute for other sensory modalities such as vision. However, tactile sensing is an inherently local sensor modality, providing information only at the points of contact. This strict locality necessitates the use of active perception techniques to acquire useful, task-relevant information from manipulated objects or the environment in general. Hence, the agent must actively guide sensors toward regions with more informative or significant features and integrate this information over time to understand a scene or complete a task. While active perception and tactile sensing methods have received significant attention recently, both fields lack standardized benchmarks. To bridge this gap, we introduce the Tactile MNIST Benchmark Suite, an open-source, Gymnasium-compatible benchmark specifically designed for active tactile perception tasks, including classification, localization, pose estimation, and volume estimation. Our benchmark suite offers diverse simulation scenarios, from simple toy environments to complex tactile perception tasks using vision-based tactile sensors. Furthermore, we offer a comprehensive dataset comprising 13,580 synthetic 3D MNIST digit models and 153,600 real-world tactile samples collected from 600 3D-printed digits. Using this dataset, we train a CycleGAN for realistic tactile simulation rendering. By providing standardized protocols and reproducible evaluation frameworks, our benchmark suite facilitates systematic progress in tactile sensing and active perception more broadly.
Map Users and Mapmakers: The Scope of Cognitive Attribution from Acquired Representations
arXiv cs.AIarXiv:2609.13879v2 Announce Type: replace
Abstract: An acquired representation can enlarge a system's cognitive repertoire without transferring the capacities exercised in producing that representation. This paper develops a framework for specifying that enlargement and its limits. Its central contribution is a five-part attribution table distinguishing effective tracking, application of acquired structures, acquisition from explicit specifications, acquisition from identifying observations, and retention and reuse. Each entry identifies a positive capacity commitment and a further claim requiring additional support. The argument deliberately grants meaningful content, causal efficacy, and productive inference, so that its conclusion does not depend on treating representations as inert encodings. Map and category examples show why even complete application competence leaves acquisition capacity undetermined, and why acquiring a criterion from its description differs from finding it in examples. Short formal proofs appear in an appendix. The framework is applied to Andrew Ng's world-model interpretation of Othello-GPT and to the specific indicators discussed in contemporary accounts of machine concepts. It preserves demonstrated recognition, classification, inference, and qualified acquisition while specifying what remains unestablished about criterion discovery and accumulation. The result concerns the scope of cognitive attribution rather than the constitutive conditions of concept possession: cognitive achievements deserve credit for the capacities they establish, without silently importing a broader repertoire through the labels attached to them.
Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection
arXiv cs.AIarXiv:2606.19168v2 Announce Type: replace
Abstract: To achieve deeper safety alignment for large language models (LLMs), recent efforts have studied how to push safety interventions earlier into the pretraining stage, primarily by filtering unsafe data or rewriting it into safer forms. We argue that pretraining-stage alignment should go beyond making the data safe: LLMs may generalize unsafe behaviors from seemingly benign pretraining data. To this end, we propose Safety Reflection Pretraining, a pretraining-stage alignment method which regularly inserts short safety reflections between sentences in pretraining corpora. This integrates self-monitoring directly into language modeling, establishing a foundational capability that is subsequently reinforced by compatible post-training. Our experiments with 1.7B models pretrained on FineWeb-Edu show that Safety Reflection Pretraining improves safety classification accuracy and substantially reduces the success rates of inference-stage and fine-tuning attacks. Complementary to our real-world experiments, we also introduce a fully controlled synthetic environment, MedSafetyWorld, with a clear definition of safety and a reasoning structure under which we find that models can easily generalize unsafe behaviors from safe data. Ablations in MedSafetyWorld further demonstrate a clear advantage of Safety Reflection Pretraining over data filtering and rewriting in preventing models from acting on unsafe behaviors. Taken together, our findings suggest that pretraining alignment should not only make the training data safe, but also shape the behaviors that models are likely to acquire from safe data.
When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
arXiv cs.AIarXiv:2605.24202v3 Announce Type: replace
Abstract: Outcome-reward RL can train every role of a multi-agent LLM workflow. Its benefit is hard to predict because the reward assigns no credit to individual roles and a shared policy trades pooled data against specialization. We ask when this training improves a workflow over its base model and single-agent RL, and what each role learns. We train three workflows (Eval-Opt, Voting, Orch-Workers) with GRPO on math and code at three Qwen3 scales, with one policy for all roles (Shared-Policy, SP) or one per role type (Isolated-Policy, IP). Every workflow gains by adapting to its structure; this does not make a role better than training it alone. Single-agent RL in the same structure matches or beats trained Voting and Orch-Workers, and within the grid only Eval-Opt under IP exceeds it. Eval-Opt's evaluator learns when to retry and its generator learns to complete the retried attempts, a joint strategy that a single policy trained alone does not acquire. Under SP, per-output token averaging sets each role's gradient share, a hidden hyperparameter absent from single-agent RL, and the solving roles learn slowly; reweighting it gives SP the speed and peak of IP, and its decline. Under IP, a parallel role, whose instances share one adapter, takes one optimizer step per instance per training step and can drift after the peak as its entropy rises and accuracy declines. Merging those steps delays the decline.
Our code is at: https://github.com/XHMY/marl-llm-workflows
What Bayesian Updating Presupposes: Hume's Representational Conditions and Causal Learning
arXiv cs.AIarXiv:2604.03387v2 Announce Type: replace
Abstract: Bayesian causal models explain how expectations change, but they leave a further question open: how does the learner acquire the causal content whose probability changes? I argue that updating alone leaves three conditions of causal judgment unexplained: experiential grounding, general organization, and belief. Hume links these conditions through a felt customary transition, which arises from discriminating resembling cases and supplies the idea of necessary connexion. His arguments against deriving necessity directly from a single interaction or from an act of will support this account of the source. Contemporary causal-theory learning uses perceptual and agency cues to acquire an intervention role. The resulting disagreement is about what that role explains about experienced causal necessity, not about whether the model learns anything. Three elementary constructions distinguish acquisition from assisted execution, lost distinctions from failed access, and posterior agreement from usable deployment. Sampling theories and stable-belief accounts supply further components beyond updating. For models that learn about external events solely through a text corpus and written reports, the evidence is report-mediated rather than firsthand; whether their own transitions are felt is a separate, open question, and the update rule settles neither matter. The paper identifies what a complete explanation must connect: the acquisition of causal content, its availability for general use, and its role in belief. Correct posterior prediction alone establishes none of these connections.
The Presupposition Problem in Representation Genesis
arXiv cs.AIarXiv:2603.21745v3 Announce Type: replace
Abstract: Large language models are the first systems to achieve high cognitive performance without clearly undergoing representation genesis: the transition from a non-representing physical system to one whose states guide behavior in a content-sensitive way. Prior cognitive systems had already made this transition before we could examine it, and philosophy of mind treated genesis as a background condition rather than an explanatory target. LLMs provide a case that does not clearly involve this transition, making the genesis question newly urgent: if genesis did not occur, which cognitive capacities are affected, and why? We currently lack the conceptual resources to answer this. The reason, this paper argues, is structural. Major frameworks in philosophy of mind, including the Language of Thought hypothesis, teleosemantics, predictive processing, enactivism, and genetic phenomenology, share a common feature when applied to the genesis question: at some explanatory step, each deploys concepts whose explanatory purchase depends on the system already being organized as a representer. This pattern, which we call the Representation Presupposition structure, generates systematic explanatory deferral. Attempts to explain the first acquisition of content-manipulable representation within the existing categorical vocabulary import resources from the representational side of the transition itself. We call this the Representation Regress. The paper offers a conceptual diagnosis rather than a new theory, establishing the structure of the problem and deriving two minimum adequacy conditions for any account that avoids this pattern. LLMs make the absence of such a theory consequential rather than merely theoretical.
Representational Acquisition Under Bounded Resources
arXiv cs.AIarXiv:2603.21736v3 Announce Type: replace
Abstract: A learner's obligation to keep acquired content usable imposes a storage-access tradeoff, with exact endpoints that force different physical organizations. For an exact concept-learning task, we determine the storage-read curve within a constant factor. One-read compound queries force answer-specific cells and exponentially costly updates; one-bit, order-independent updates instead force fact-specific cells. At minimum storage capacity, a robust counterpart holds: when update stretch is averaged uniformly over all semantic cube edges, small excess stretch bounds expected distance from a coordinate encoding under the uniform content distribution. It also bounds the information inaccessible to a one-read consumer. Preservation imposes further constraints. On a common invariant ready-state domain, old content preserved by ordinary zero-read overwrites must factor through the unwritten coordinates. Distributed encodings can require reading every cell to choose a preserving update. For conditional Horn reasoning, we obtain a second pair of exact endpoints: maintaining answers makes use local, while minimum storage and one-change named revision force a rule vector whose optimal query-read cost is determined exactly. These results explain how acquired distinctions, subsequent uses, and update constraints jointly determine the costs and organization of a retained resource.
Bi-directional digital twin prototype anchoring with multi-periodicity learning for few-shot fault diagnosis
arXiv cs.AIarXiv:2603.07054v2 Announce Type: replace
Abstract: Intelligent fault diagnosis (IFD) typically requires abundant labeled data, which are difficult to obtain from physical assets in practical industrial applications. Digital twins (DTs) provide a promising alternative by generating labeled simulation data, while most existing DT-assisted diagnosis methods rely on domain adaptation and still require considerable unlabeled target-domain data. To enable diagnostic knowledge transfer when only a few labeled target samples are available, this paper proposes a bi-directional DT prototype anchoring framework with multi-periodicity learning for few-shot fault diagnosis. The model is first meta-trained in the DT virtual space to acquire transferable diagnostic knowledge and is then adapted to the physical asset through test-time adaptation. To improve cross-domain adaptation under extremely limited target data, a bidirectional twin-domain prototype anchoring strategy is developed to mutually constrain the source- and target-domain class representations, while covariance-guided augmentation is introduced to improve the robustness of target prototype estimation. In addition, a multi-periodicity feature learning module is designed to capture the intrinsic periodic characteristics of motor current signals. A finite-element-based DT of an asynchronous motor is constructed for experimental validation under three rotational speeds and multiple few-shot settings. The experimental results show that the proposed method outperforms representative comparison methods, while the ablation studies verify the effectiveness of the components. These results demonstrate the potential of the proposed framework for DT-to-asset diagnostic knowledge transfer under severely limited target-domain data.
Balancing Representations by Identifying and Generating Under-represented Data
arXiv cs.AIarXiv:2611.02952v1 Announce Type: cross
Abstract: Self-supervised learning inherits the coverage of its source data. When an unlabeled corpus is long-tailed, the representation becomes dense around frequent modes and thin where coverage is weak. Objectives for long-tailed SSL reweight the images already in the corpus and add no new ones. We introduce BRIDGE (Balancing Representations by Identifying and Generating Under-represented Data), a label-free feedback loop around the source set. The current encoder scores every source image by its mean kNN distance, and a budgeted acquisition rule selects images from a band of that score distribution where support is thin and the generator still produces faithful variants. A frozen image-to-image diffusion model then adds local variants of the selected anchors, and pretraining continues on the enlarged source set. We formulate acquisition as recoverability-weighted allocation of local support and derive when a finite budget should favor a sparse band that excludes the extreme tail and when reallocation after each repair is optimal under a fixed objective. Across five long-tailed, web-scraped and synthetic source regimes, BRIDGE has the highest seven-task linear-probe and kNN average of the compared methods, and paired experiments extend the gain to ViT-S under contrastive and self-distillation objectives, to low-label fine-tuning and to semantic segmentation. The linear-probe gain is smaller under masked reconstruction. Generated repair matches an oracle that restores the withheld real images, and under a frozen encoder the inserted images shrink the neighborhoods of the selected anchors about twice as much as those of matched unselected images. BRIDGE needs no labels and leaves the pretraining objective unchanged, so it can be added to pretraining on uncurated web data, where the encoder decides which images to generate.
MultiMental-IAS: A Multimodal Driver Mental State Analysis Dataset for Context-Aware Non-IID Evaluation
arXiv cs.AIarXiv:2611.02790v1 Announce Type: cross
Abstract: Robust driver-state modelling requires synchronized physiological, behavioural, and contextual signals, yet existing open resources typically target a single cognitive state, omit continuous vehicle context, or do not define evaluation protocols that expose inter-subject heterogeneity. We present Multimental-IAS, a multimodal driver mental-state dataset collected in a cockpit-in-the-loop simulation built on CARLA. It contains vehicle telemetry with scenario-context channels, four-channel EEG and three-channel PPG from a Muse 2 headband, and cabin-facing video from 23 participants, recorded in 148 trials (11.6 hours) under six induced states: Normal, Distracted, Alerted, Stressed, Relaxed, and Drowsy. We document the acquisition pipeline in detail and provide a benchmark with one protocol for all models: chronological within-subject splits, participant-disjoint cross-subject folds, validation-based model selection, and ablations over modalities, scenario-context channels, and signal normalization. Multimodal fusion reaches a macro-F1 of 0.94 for drivers seen during training. For unseen drivers, fusing driving dynamics with per-window normalized EEG/PPG raises macro-F1 from 0.408 (telemetry alone) to 0.485, consistently across all five folds, while the gap between the two protocols quantifies the inter-driver heterogeneity that personalized models must address. Multimental-IAS thus provides a concrete testbed for non-IID generalization, personalization, and federated learning in driver monitoring.
继续滚动加载更多…