arXiv:2508.21058v3 Announce Type: replace-cross Abstract: Long video generation is fundamentally a long context memory problem: models must retain and retrieve salient events across a long range without collapsing or drifting. However, scaling diffusion transformers to generate long-context videos is fundamentally limited by the quadratic cost of self-attention, which makes memory and computation intractable and difficult […]
CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale
arXiv:2512.08826v1 Announce Type: new Abstract: The rapid proliferation of generative components, such as LoRAs, has created a vast but unstructured ecosystem. Existing discovery methods depend on unreliable user descriptions or biased popularity metrics, hindering usability. We present CARLoS, a large-scale framework for characterizing LoRAs without requiring additional metadata. Analyzing over 650 LoRAs, we employ them […]
Sleep effects on brain, cognition, and mental health during adolescence are mediated by the glymphatic system
arXiv:2512.08704v1 Announce Type: new Abstract: Background: Adolescence is a critical period of brain maturation and heightened vulnerability to cognitive and mental health disorders. Sleep plays a vital role in neurodevelopment, yet the mechanisms linking insufficient sleep to adverse brain and behavioral outcomes remain unclear. The glymphatic system (GS), a brain-wide clearance pathway, may provide a […]
Resource and population dynamics in an agent-environment interaction model
arXiv:2512.08762v1 Announce Type: new Abstract: In any ecosystem, the conditions of the environment and the characteristics of the species that inhabit it are entangled, co-evolving in space and time. We introduce a model that couples active agents with a dynamic environment, interpreted as a nutrient source. Agents are persistent random walkers that gather food from […]
A Lightweight Transfer Learning-Based State-of-Health Monitoring with Application to Lithium-ion Batteries in Unmanned Air Vehicles
arXiv:2512.08512v1 Announce Type: new Abstract: Accurate and rapid state-of-health (SOH) monitoring plays an important role in indicating energy information for lithium-ion battery-powered portable mobile devices. To confront their variable working conditions, transfer learning (TL) emerges as a promising technique for leveraging knowledge from data-rich source working conditions, significantly reducing the training data required for SOH […]
Protein Secondary Structure Prediction Using Transformers
arXiv:2512.08613v1 Announce Type: new Abstract: Predicting protein secondary structures such as alpha helices, beta sheets, and coils from amino acid sequences is essential for understanding protein function. This work presents a transformer-based model that applies attention mechanisms to protein sequence data to predict structural motifs. A sliding-window data augmentation technique is used on the CB513 […]
Reflecting with Two Voices: A Co-Adaptive Dual-Strategy Framework for LLM-Based Agent Decision Making
arXiv:2512.08366v1 Announce Type: new Abstract: Large language model (LLM) agents often rely on external demonstrations or retrieval-augmented planning, leading to brittleness, poor generalization, and high computational overhead. Inspired by human problem-solving, we propose DuSAR (Dual-Strategy Agent with Reflecting) – a demonstration-free framework that enables a single frozen LLM to perform co-adaptive reasoning via two complementary […]
From Accuracy to Impact: The Impact-Driven AI Framework (IDAIF) for Aligning Engineering Architecture with Theory of Change
arXiv:2512.08449v1 Announce Type: new Abstract: This paper introduces the Impact-Driven AI Framework (IDAIF), a novel architectural methodology that integrates Theory of Change (ToC) principles with modern artificial intelligence system design. As AI systems increasingly influence high-stakes domains including healthcare, finance, and public policy, the alignment problem–ensuring AI behavior corresponds with human values and intentions–has become […]
A Hybrid Model for Stock Market Forecasting: Integrating News Sentiment and Time Series Data with Graph Neural Networks
arXiv:2512.08567v1 Announce Type: cross Abstract: Stock market prediction is a long-standing challenge in finance, as accurate forecasts support informed investment decisions. Traditional models rely mainly on historical prices, but recent work shows that financial news can provide useful external signals. This paper investigates a multimodal approach that integrates companies’ news articles with their historical stock […]
COINS: SemantiC Ids Enhanced COLd Item RepresentatioN for Click-through Rate Prediction in E-commerce Sarch
arXiv:2510.12604v2 Announce Type: replace-cross Abstract: With the rise of modern search and recommendation platforms, insufficient collaborative information of cold-start items exacerbates the Matthew effect of existing platform items, challenging platform diversity and becoming a longstanding issue. Existing methods align items’ side content with collaborative information to transfer collaborative signals from high-popularity items to cold-start items. […]