arXiv:2601.20375v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can be fine-tuned on domain-specific data to enhance their performance in specialized fields. However, such data often contains numerous low-quality samples, necessitating effective data processing (DP). In practice, DP strategies are typically developed through iterative manual analysis and trial-and-error adjustment. These processes inevitably incur high labor […]
Parity, Sensitivity, and Transformers
arXiv:2602.05896v2 Announce Type: replace-cross Abstract: Understanding what neural architectures can and cannot compute is a central challenge in the theory of AI. One of the fundamental problems in this context is the PARITY task, which asks whether the number of 1s in a binary input sequence is even or odd. PARITY is one of the […]
TinyBayes: Closed-Form Bayesian Inference via Jacobi Prior for Real-Time Image Classification on Edge Devices
arXiv:2605.06333v1 Announce Type: cross Abstract: Cocoa (Theobroma cacao) is a critical cash crop for millions of smallholder farmers in West Africa, where Cocoa Swollen Shoot Virus Disease (CSSVD) and anthracnose cause devastating yield losses. Automated disease detection from leaf images is essential for early intervention, yet deploying such systems in resource-constrained settings demands models that […]
PulseLM: A Foundation Dataset and Benchmark for PPG-Text Learning
arXiv:2603.03331v2 Announce Type: replace-cross Abstract: Photoplethysmography (PPG) is a widely used non-invasive sensing modality for continuous cardiovascular and physiological monitoring across clinical, laboratory, and wearable settings. While existing PPG datasets support a broad range of downstream tasks, they typically provide supervision in the form of numerical measurements or task-specific labels, limiting their compatibility with language-based […]
Intelligent CCTV for Urban Design: AI-Based Analysis of Soft Infrastructure at Intersections
arXiv:2605.05402v1 Announce Type: new Abstract: Artificial intelligence (AI) and computer vision are transforming transportation data collection. This study introduces an AI-enabled analytics framework leveraging existing CCTV infrastructure to evaluate the impact of soft interventions, such as temporary pedestrian refuges and curb extensions, on vehicle speed and safety. Using deep learning and perspective-based speed estimation, we […]
P^2O: Joint Policy and Prompt Optimization
arXiv:2603.21877v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) enhances Large Language Model (LLM) reasoning but suffers from advantage collapse on “hard samples” where all rollouts fail. This lack of variance eliminates crucial learning signals. For these intractable samples, simply scaling up rollout budgets offers limited gains. We introduce Joint Policy and Prompt […]
When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models
arXiv:2605.05403v1 Announce Type: new Abstract: This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user beliefs, position reversals, or deviation from an objective standard of correctness. These formulations capture only overt forms of […]
FIT to Forget: Robust Continual Unlearning for Large Language Models
arXiv:2601.21682v2 Announce Type: replace-cross Abstract: While large language models (LLMs) exhibit remarkable capabilities, they increasingly face demands to unlearn memorized privacy-sensitive, copyrighted, or harmful content. Existing unlearning methods primarily focus on emphsingle-shot scenarios, whereas real-world deletion requests arrive emphcontinually. Na”ively applying these methods to sequential requests leads to severe utility degradation and catastrophic forgetting. To […]
Multivariate Standardized Residuals for Conformal Prediction
arXiv:2507.20941v4 Announce Type: replace-cross Abstract: While split conformal prediction guarantees marginal coverage, approaching the stronger property of conditional coverage is essential for reliable uncertainty quantification. Naive conformal scores, however, suffer from poor conditional coverage in heteroskedastic settings. In univariate regression, this is commonly addressed by normalizing non-conformity scores using an estimated local score variance. In […]
AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
arXiv:2605.00425v2 Announce Type: replace Abstract: Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards provide limited guidance for assigning credit to individual steps within long interaction trajectories. Existing approaches often introduce dense intermediate […]
A model for mosquito-borne epidemic outbreaks with information-dependent protective behaviour
arXiv:2511.16802v2 Announce Type: replace Abstract: We investigate a model for a mosquito-borne epidemic in which human hosts may adopt protective behaviour against vector bites in response to information on both past and current disease prevalence. Assuming that mosquitoes can also feed on non-competent hosts (i.e. hosts that do not contribute to disease transmission), we first […]
DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
arXiv:2605.06592v1 Announce Type: cross Abstract: Contrastive language-image pretraining (CLIP) suffers from two structural weaknesses: the symmetric InfoNCE loss discards the relative ordering among unmatched in-batch pairs, and global pooling collapses the visual representation into a semantic bottleneck that is poorly sensitive to fine-grained local structure. RANKCLIP partially addresses the first issue with a list-wise Plackett-Luce […]