arXiv:2603.25633v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used in math education not only as problem solvers but also as assessors of learners’ reasoning. However, it remains unclear whether stronger math problem-solving ability is associated with stronger step-level assessment performance. This study examines that relationship using the GSM8K and MATH subsets of […]
Working Paper: Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots
arXiv:2410.20894v3 Announce Type: replace Abstract: Artificial General Intelligence (AGI) Agents and Robots must be able to cope with everchanging environments and tasks. They must be able to actively construct new internal causal models of their interactions with the environment when new structural changes take place in the environment. Thus, we claim that active causal structure […]
A Bayesian Gamma-power-mixture survival regression model: predicting the recurrence of prostate cancer post-prostatectomy
arXiv:2603.25455v1 Announce Type: cross Abstract: In a dataset of 423 patients who had had radical prostatectomy for localised prostate cancer we estimated the apparent Shannon information (ASI) about time to biochemical recurrence in various subsets of the available pre-op variables using a Bayesian Gamma-power-mixture survival regression model. In all the subsets examined the ASI was […]
Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models
arXiv:2603.23783v2 Announce Type: replace-cross Abstract: Adapting large-scale foundation models to new domains with limited supervision remains a fundamental challenge due to latent distribution mismatch, unstable optimization dynamics, and miscalibrated uncertainty propagation. This paper introduces an uncertainty-aware probabilistic latent transport framework that formulates domain adaptation as a stochastic geometric alignment problem in representation space. A Bayesian […]
CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wild
arXiv:2603.25524v1 Announce Type: cross Abstract: Long-term behavioral monitoring of individual animals is crucial for studying behavioral changes that occur over different time scales, especially for conservation and evolutionary biology. Computer vision methods have proven to benefit biodiversity monitoring, but automated behavior monitoring in wild populations remains challenging. This stems from the lack of datasets that […]
Improving Fine-Grained Rice Leaf Disease Detection via Angular-Compactness Dual Loss Learning
arXiv:2603.25006v1 Announce Type: cross Abstract: Early detection of rice leaf diseases is critical, as rice is a staple crop supporting a substantial share of the world’s population. Timely identification of these diseases enables more effective intervention and significantly reduces the risk of large-scale crop losses. However, traditional deep learning models primarily rely on cross entropy […]
Pixelis: Reasoning in Pixels, from Seeing to Acting
arXiv:2603.25091v1 Announce Type: cross Abstract: Most vision-language systems are static observers: they describe pixels, do not act, and cannot safely improve under shift. This passivity limits generalizable, physically grounded visual intelligence. Learning through action, not static description, is essential beyond curated data. We present Pixelis, a pixel-space agent that operates directly on images and videos […]
AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
arXiv:2603.24857v1 Announce Type: cross Abstract: As machine learning (ML) systems expand in both scale and functionality, the security landscape has become increasingly complex, with a proliferation of attacks and defenses. However, existing studies largely treat these threats in isolation, lacking a coherent framework to expose their shared principles and interdependencies. This fragmented view hinders systematic […]
TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Driven Optimization
arXiv:2603.24936v1 Announce Type: cross Abstract: Human trajectory forecasting is important for intelligent multimedia systems operating in visually complex environments, such as autonomous driving and crowd surveillance. Although Conditional Flow Matching (CFM) has shown strong ability in modeling trajectory distributions from spatio-temporal observations, existing approaches still focus primarily on supervised fitting, which may leave social norms […]
Grokking as a Falsifiable Finite-Size Transition
arXiv:2603.24746v1 Announce Type: cross Abstract: Grokking — the delayed onset of generalization after early memorization — is often described with phase-transition language, but that claim has lacked falsifiable finite-size inputs. Here we supply those inputs by treating the group order $p$ of $mathbbZ_p$ as an admissible extensive variable and a held-out spectral head-tail contrast as […]
GoldiCLIP: The Goldilocks Approach for Balancing Explicit Supervision for Language-Image Pretraining
arXiv:2603.24804v1 Announce Type: cross Abstract: Until recently, the success of large-scale vision-language models (VLMs) has primarily relied on billion-sample datasets, posing a significant barrier to progress. Latest works have begun to close this gap by improving supervision quality, but each addresses only a subset of the weaknesses in contrastive pretraining. We present GoldiCLIP, a framework […]
Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models
arXiv:2603.25250v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection aims to identify samples that deviate from in-distribution (ID). One popular pipeline addresses this by introducing negative labels distant from ID classes and detecting OOD based on their distance to these labels. However, such labels may present poor activation on OOD samples, failing to capture the OOD […]