arXiv:2603.14267v2 Announce Type: replace-cross Abstract: Video dubbing has broad applications in filmmaking, multimedia creation, and assistive speech technology. Existing approaches either train directly on limited dubbing datasets or adopt a two-stage pipeline that adapts pre-trained text-to-speech (TTS) models, which often struggle to produce expressive prosody, rich acoustic characteristics, and precise synchronization. To address these issues, […]
Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction
arXiv:2603.16281v1 Announce Type: cross Abstract: Electroencephalography (EEG) is a widely used tool for studying brain function, with applications in clinical neuroscience, diagnosis, and brain-computer interfaces (BCIs). Recent EEG foundation models trained on large unlabeled corpora aim to learn transferable representations, but their effectiveness remains unclear; reported improvements over smaller task-specific models are often modest, sensitive […]
NextMem: Towards Latent Factual Memory for LLM-based Agents
arXiv:2603.15634v1 Announce Type: new Abstract: Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations. Textual methods impose heavy context and indexing burdens, while parametric methods suffer from catastrophic forgetting and high costs. To […]
FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-calibration for Cattle Mounting Pose Estimation
arXiv:2603.16596v1 Announce Type: cross Abstract: Mounting posture is an important visual indicator of estrus in dairy cattle. However, achieving reliable mounting pose estimation in real-world environments remains challenging due to cluttered backgrounds and frequent inter-animal occlusion. We present FSMC-Pose, a top-down framework that integrates a lightweight frequency-spatial fusion backbone, CattleMountNet, and a multiscale self-calibration head, […]
An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
arXiv:2603.16428v1 Announce Type: cross Abstract: Fine-tuning Large Language Models (LLMs) has become essential for domain adaptation, but its memory-intensive property exceeds the capabilities of most GPUs. To address this challenge and democratize LLM fine-tuning, we present SlideFormer, a novel system designed for single-GPU environments. Our innovations are: (1) A lightweight asynchronous engine that treats the […]
Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations
arXiv:2603.14894v2 Announce Type: replace-cross Abstract: Trust and ethical concerns due to the widespread deployment of opaque machine learning (ML) models motivating the need for reliable model explanations. Post-hoc model-agnostic explanation methods addresses this challenge by learning a surrogate model that approximates the behavior of the deployed black-box ML model in the locality of a sample […]
FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data
arXiv:2603.16513v1 Announce Type: cross Abstract: Structured data is foundational to healthcare, finance, e-commerce, and scientific data management. Large structured-data models (LDMs) extend the foundation model paradigm to unify heterogeneous datasets for tasks such as classification, regression, and decision support. However, existing LDMs face major limitations. First, most rely on sample-wise self-attention, whose O(N^2) complexity limits […]
CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection
arXiv:2603.16439v1 Announce Type: cross Abstract: Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene conditions, pose significant challenges to the generalization ability of existing models. To address this, we propose Cross-Domain […]
Malicious Or Not: Adding Repository Context to Agent Skill Classification
arXiv:2603.16572v1 Announce Type: cross Abstract: Agent skills extend local AI agents, such as Claude Code or Open Claw, with additional functionality, and their popularity has led to the emergence of dedicated skill marketplaces, similar to app stores for mobile applications. Simultaneously, automated skill scanners were introduced, analyzing the skill description available in SKILL.md, to verify […]
Spatial correlations in SIS processes on random regular graphs
arXiv:2509.25386v2 Announce Type: replace-cross Abstract: In network-based SIS models of infectious disease transmission, infection can only occur between directly connected individuals. This constraint naturally gives rise to spatial correlations between the states of neighboring nodes, as the infection status of connected individuals becomes interdependent. Although mean-field approximations and the standard pairwise model are commonly used […]
When Openclaw Agents Learn from Each Other: Insights from Emergent AI Agent Communities for Human-AI Partnership in Education
arXiv:2603.16663v1 Announce Type: cross Abstract: The AIED community envisions AI evolving “from tools to teammates,” yet our understanding of AI teammates remains limited to dyadic human-AI interactions. We offer a different vantage point: a rapidly growing ecosystem of AI agent platforms where over 167,000 agents participate, interact as peers, and develop learning behaviors without researcher […]
Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models
arXiv:2601.22629v2 Announce Type: replace-cross Abstract: Diffusion language models (Diffusion-LMs) introduce an explicit temporal dimension into text generation, yet how this structure can be leveraged to control generation diversity for exploring multiple valid semantic or reasoning paths remains underexplored. In this paper, we show that Diffusion-LMs, like diffusion models in image generation, exhibit a temporal division […]