arXiv:2511.00379v1 Announce Type: new Abstract: Ensuring that Large Language Models (LLMs) align with the diverse and evolving human values across different regions and cultures remains a critical challenge in AI ethics. Current alignment approaches often yield superficial conformity rather than genuine ethical understanding, failing to address the complex, context-dependent nature of human values. In this […]
Continual Learning, Not Training: Online Adaptation For Agents
arXiv:2511.01093v1 Announce Type: cross Abstract: Continual Learning (CL) methods have traditionally focused on mitigating catastrophic forgetting through gradient-based retraining, an approach ill-suited for deployed agents that must adapt in real time. We introduce our Adaptive Teaching and Learning System (ATLAS), a dual-agent architecture that decouples reasoning (Teacher) from execution (Student) and incorporates a persistent learning […]
GroupSHAP-Guided Integration of Financial News Keywords and Technical Indicators for Stock Price Prediction
arXiv:2510.23112v3 Announce Type: replace-cross Abstract: Recent advances in finance-specific language models such as FinBERT have enabled the quantification of public sentiment into index-based measures, yet compressing diverse linguistic signals into single metrics overlooks contextual nuances and limits interpretability. To address this limitation, explainable AI techniques, particularly SHAP (SHapley Additive Explanations), have been employed to identify […]
Self-Harmony: Learning to Harmonize Self-Supervision and Self-Play in Test-Time Reinforcement Learning
arXiv:2511.01191v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) offers a label-free paradigm for adapting models using only synthetic signals at inference, but its success hinges on constructing reliable learning signals. Standard approaches such as majority voting often collapse to spurious yet popular answers. We introduce Self-Harmony, a framework built on a simple intuition: the […]
Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
arXiv:2511.00382v1 Announce Type: new Abstract: Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence indicates that they can also degrade a model’s safety or fairness. Since different fine-tuning techniques may exert distinct effects on these […]
Speech-DRAME: A Framework for Human-Aligned Benchmarks in Speech Role-Play
arXiv:2511.01261v1 Announce Type: cross Abstract: Role-play has become a key testbed for generative models, expanding from text-only dialogue to multimodal interaction. Extending role-play to speech captures prosody, emotion, and delivery, but also poses new evaluation challenges. Current pipelines often use audio large language models (ALLMs) as zero-shot judges, which miss paralinguistic cues, collapse multiple aspects […]
Efficiently Training A Flat Neural Network Before It has been Quantizated
arXiv:2511.01462v1 Announce Type: cross Abstract: Post-training quantization (PTQ) for vision transformers (ViTs) has garnered significant attention due to its efficiency in compressing models. However, existing methods typically overlook the relationship between a well-trained NN and the quantized model, leading to considerable quantization error for PTQ. However, it is unclear how to efficiently train a model-agnostic […]
Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
arXiv:2511.01307v1 Announce Type: cross Abstract: Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks, as personalization techniques can be misused by malicious users to generate unauthorized content. Although several studies have attempted to […]
A Multimodal Framework for Depression Detection during Covid-19 via Harvesting Social Media: A Novel Dataset and Method
arXiv:2511.00424v1 Announce Type: new Abstract: The recent coronavirus disease (Covid-19) has become a pandemic and has affected the entire globe. During the pandemic, we have observed a spike in cases related to mental health, such as anxiety, stress, and depression. Depression significantly influences most diseases worldwide, making it difficult to detect mental health conditions in […]
Using machine learning methods to predict cognitive age from psychophysiological tests
arXiv:2511.00013v1 Announce Type: new Abstract: This study introduces a novel method for predicting cognitive age using psychophysiological tests. To determine cognitive age, subjects were asked to complete a series of psychological tests measuring various cognitive functions, including reaction time and cognitive conflict, short-term memory, verbal functions, and color and spatial perception. Based on the tests […]