arXiv:2605.26293v1 Announce Type: cross Abstract: Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves downstream preference tuning in English. We extend this method to multiple languages and evaluate two models across a total of 14 high and low-resource languages on a diverse set of tasks. Our […]
RAGEAR: Retrieval-Augmented Graph-Enhanced Academic Recommender
arXiv:2605.26819v1 Announce Type: cross Abstract: We present RAGEAR (Retrieval-Augmented Graph-Enhanced Academic Recommender), a neurosymbolic recommender system for academic course recommendation. RAGEAR combines dense retrieval over full lecture transcripts with a symbolic Knowledge Graph modelling courses, lessons, transcript chunks, credits, study plans, and curricular information. The Knowledge Graph supports symbolic filtering and contextualisation based on structured […]
StreamSplit: Continuous Audio Representation Learning via Uncertainty-Guided Adaptive Splitting
arXiv:2605.26523v1 Announce Type: cross Abstract: Large-batch Contrastive Learning (CL), the foundation of modern representation learning, is fundamentally incompatible with the volatile resource constraints of edge devices. This conflict creates a dilemma: small on-device batches degrade model fidelity, while offloading to the cloud incurs unacceptable latency and bandwidth costs. Existing solutions often resort to static model […]
Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
arXiv:2605.26600v1 Announce Type: cross Abstract: Standard Self-Supervised Learning (SSL) for Automatic Modulation Recognition (AMR) struggles with ineffective isotropic augmentations, spectral instability, and semantic drift. To address these challenges, we propose Dynamic-Consistency Contrastive Learning (DyCo-CL), a geometry-aware framework that couples Virtual Adversarial Augmentation (VAA) with a semantic consistency loss. We provide a theoretical analysis indicating that […]
Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective
arXiv:2605.26441v1 Announce Type: cross Abstract: This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposal selection framework that utilizes contrastive learning and reconstruction paradigm for scoring the pre-defined moment proposals. Although they have achieved significant progress, we argue that their current frameworks have overlooked two […]
Comparative Study of Vision-Based Metric Measurement for Large-Scale Planar Scenes
arXiv:2605.26475v1 Announce Type: cross Abstract: Vision-based metric distance and area measurement remains challenging in large-scale outdoor environments due to long-range sensing, camera zoom, and unstable imaging conditions. This work studies planar metric measurement in a real-world reservoir monitoring scenario using PTZ cameras and compares three representative approaches: geometry-based monocular ranging, image stitching with birds-eye-view transformation, […]
Linear and Neural Dueling Bandits with Delayed Feedback
arXiv:2605.26554v1 Announce Type: cross Abstract: Contextual dueling bandits form a cornerstone of preference-based decision-making, with critical applications in recommender systems and large language model alignment. However, standard algorithms rely on the idealized assumption of immediate feedback, a condition frequently violated in real-world scenarios such as prompt optimization. This setting introduces a unique theoretical challenge: unlike […]
The Labyrinth and the Thread: Rethinking Regularizations in Sequential Knowledge Editing for Large Language Models
arXiv:2605.26670v1 Announce Type: cross Abstract: Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rely on complex regularization or constraint mechanisms whose necessity remains unclear. In this work, we systematically investigate the mechanisms underlying effective and stable sequential editing. Specifically, we first analyze the empirical […]
Generative artificial intelligence and the marginalization of minoritized knowledges in higher education: the case of disability
arXiv:2605.26769v1 Announce Type: cross Abstract: Generative artificial intelligence redefines higher education by restructuring the processes through which scientific knowledge is produced and validated. These systems are not neutral; they actively contribute to the marginalization of non-hegemonic epistemologies. This research draws upon educational sciences, critical technology studies, and disability studies to demonstrate that training datasets, which […]
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
arXiv:2605.26895v1 Announce Type: cross Abstract: Normalization layers in modern large language models (LLMs) consist of a deterministic normalization operation and a learnable scale vector. While the normalization operation has been extensively studied, the scale vector remains poorly understood despite its ubiquitous use. In this work, we present a systematic study of scale vectors in LLMs […]
Semigroup Consistency as a Diagnostic for Learned Physics Simulators
arXiv:2605.26324v1 Announce Type: cross Abstract: Learned physics simulators are often evaluated by one-step or short-horizon prediction error, but these metrics can miss failures in temporal composition and long-horizon rollout. For autonomous, state-complete systems, exact solution maps satisfy a semigroup law: direct evolution over $s+t$ should agree with evolution over $s$ followed by $t$. We propose […]
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
arXiv:2605.26385v1 Announce Type: cross Abstract: Large-scale search, recommendation, and retrieval-augmented generation (RAG) systems typically employ a two-stage architecture: an early-stage ranker (ESR) generates a candidate set, which is subsequently re-ranked by a late-stage ranker (LSR). While there are many reinforcement learning (RL) methods for training the LSR, end-to-end training of the ESR has proven challenging. […]