arXiv:2403.18602v2 Announce Type: replace-cross Abstract: Motivation: In recent years, the availability of multi-omics data has increased substantially. Multi-omics data integration methods mainly aim to leverage different molecular layers to gain a complete molecular description of biological processes. An attractive integration approach is the reconstruction of multi-omics networks. However, the development of effective multi-omics network reconstruction […]
There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models
arXiv:2410.23530v5 Announce Type: replace-cross Abstract: Diffusion Models achieve state-of-the-art performance in generating new samples but lack a low-dimensional latent space that encodes the data into editable features. Inversion-based methods address this by reversing the denoising trajectory, transferring images to their approximated starting noise. In this work, we thoroughly analyze this procedure and focus on the […]
Noradrenergic-inspired gain modulation attenuates the stability gap in joint training
arXiv:2507.14056v2 Announce Type: replace-cross Abstract: Recent work in continual learning has highlighted the stability gap — a temporary performance drop on previously learned tasks when new ones are introduced. This phenomenon reflects a mismatch between rapid adaptation and strong retention at task boundaries, underscoring the need for optimization mechanisms that balance plasticity and stability over […]
Improving Value-based Process Verifier via Structural Prior Injection
arXiv:2502.17498v2 Announce Type: replace-cross Abstract: In the Large Language Model(LLM) reasoning scenario, people often estimate state value via Monte Carlo sampling. Though Monte Carlo estimation is an elegant method with less inductive bias, noise and errors are inevitably introduced due to the limited sampling. To handle the problem, we inject the structural prior into the […]
LingoQ: Bridging the Gap between EFL Learning and Work through AI-Generated Work-Related Quizzes
arXiv:2509.17477v2 Announce Type: replace-cross Abstract: Non-native English speakers performing English-related tasks at work struggle to sustain EFL learning, despite their motivation. Often, study materials are disconnected from their work context. Our formative study revealed that reviewing work-related English becomes burdensome with current systems, especially after work. Although workers rely on LLM-based assistants to address their […]
Geometric Dynamics of Agentic Loops in Large Language Models
arXiv:2512.10350v4 Announce Type: replace-cross Abstract: Iterative LLM systems(self-refinement, chain-of-thought, autonomous agents) are increasingly deployed, yet their temporal dynamics remain uncharacterized. Prior work evaluates task performance at convergence but ignores the trajectory: how does semantic content evolve across iterations? Does it stabilize, drift, or oscillate? Without answering these questions, we cannot predict system behavior, guarantee stability, […]
Descriptive and risk analysis of vehicle movements linked to porcine reproductive and respiratory syndrome and porcine epidemic diarrhea transmission in US commercial swine farms
arXiv:2601.18819v1 Announce Type: new Abstract: Vehicle movements, including vehicle cabs and trailers, play a role in disseminating disease in swine production. However, there are many information gaps about vehicle movements patterns that increase the probability of disease transmission, which is crucial in developing better preventive strategies. In this study we described the movement pattern of […]
Decoding Cortical Microcircuits: A Generative Model for Latent Space Exploration and Controlled Synthesis
arXiv:2506.11062v2 Announce Type: replace Abstract: A central idea in understanding brains and building artificial intelligence is that structure determines function. Yet, how the brain’s complex structure arises from a limited set of genetic instructions remains a key question. The ultra high-dimensional detail of neural connections vastly exceeds the information storage capacity of genes, suggesting a […]
MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption
arXiv:2510.05580v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA, a unified, backbone-agnostic post-training framework for efficient and scalable alignment. MetaVLA introduces Context-Aware Meta Co-Training, which consolidates diverse target […]
The LLM Data Auditor: A Metric-oriented Survey on Quality and Trustworthiness in Evaluating Synthetic Data
arXiv:2601.17717v2 Announce Type: replace Abstract: Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LLMs mitigate the bottlenecks imposed by the acquisition costs of real-world data for model training, evaluation, and system iteration. However, ensuring the high quality […]
Creating a Causally Grounded Rating Method for Assessing the Robustness of AI Models for Time-Series Forecasting
arXiv:2502.12226v3 Announce Type: replace-cross Abstract: AI models, including both time-series-specific and general-purpose Foundation Models (FMs), have demonstrated strong potential in time-series forecasting across sectors like finance. However, these models are highly sensitive to input perturbations, which can lead to prediction errors and undermine trust among stakeholders, including investors and analysts. To address this challenge, we […]
MLVTG: Mamba-Based Feature Alignment and LLM-Driven Purification for Multi-Modal Video Temporal Grounding
arXiv:2506.08512v2 Announce Type: replace-cross Abstract: Video Temporal Grounding (VTG), which aims to localize video clips corresponding to natural language queries, is a fundamental yet challenging task in video understanding. Existing Transformer-based methods often suffer from redundant attention and suboptimal multi-modal alignment. To address these limitations, we propose MLVTG, a novel framework that integrates two key […]