arXiv:2604.00070v2 Announce Type: replace-cross Abstract: Complete and high-quality multi-modal Magnetic Resonance Imaging (MRI) is essential for accurate neuro-oncological assessment, as each contrast provides complementary anatomical and pathological information. However, acquiring all modalities (e.g., T1c, T1n, T2w, T2f) for every patient is often impractical due to prolonged scan times, cost, and patient discomfort, potentially limiting comprehensive […]
Debate-Enhanced Pseudo Labeling and Frequency-Aware Progressive Debiasing for Weakly-Supervised Camouflaged Object Detection with Scribble Annotations
arXiv:2512.20260v5 Announce Type: replace-cross Abstract: Weakly-Supervised Camouflaged Object Detection (WSCOD) aims to locate and segment objects that are visually concealed within their surrounding scenes, relying solely on sparse supervision such as scribble annotations. Despite recent progress, existing WSCOD methods still lag far behind fully supervised ones due to two major limitations: (1) the pseudo masks […]
Reasoning-Intensive Regression
arXiv:2508.21762v3 Announce Type: replace-cross Abstract: AI researchers and practitioners increasingly apply large language models (LLMs) to what we call reasoning-intensive regression (RiR), i.e., deducing subtle numerical scores from text. Unlike standard language regression tasks such as sentiment or similarity analysis, RiR often appears instead in ad-hoc applications such as rubric-based scoring, modeling dense rewards in […]
Representation in large language models
arXiv:2501.00885v2 Announce Type: replace-cross Abstract: The extraordinary success of recent Large Language Models (LLMs) on a diverse array of tasks has led to an explosion of scientific and philosophical theorizing aimed at explaining how they do what they do. Unfortunately, disagreement over fundamental theoretical issues has led to stalemate, with entrenched camps of LLM optimists […]
The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning
arXiv:2602.13595v2 Announce Type: replace Abstract: Neural scaling laws provide a predictable recipe for AI advancement: reducing numerical precision should linearly improve computational efficiency and energy profile ($E propto mathrmbits$). In this paper, we demonstrate that this scaling law breaks in the context of multi-hop reasoning. We reveal a ‘quantization trap’ where reducing precision from 16-bit […]
CASE: An Agentic AI Framework for Enhancing Scam Intelligence in Digital Payments
arXiv:2508.19932v2 Announce Type: replace Abstract: The proliferation of digital payment platforms has transformed commerce, offering unmatched convenience and accessibility globally. However, this growth has also attracted malicious actors, leading to a corresponding increase in sophisticated social engineering scams. These scams are often initiated and orchestrated on multiple surfaces outside the payment platform, making user and […]
Autonomous Systems Dependability in the era of AI: Design Challenges in Safety, Security, Reliability and Certification
arXiv:2604.27807v2 Announce Type: replace Abstract: The design of embedded safety-critical systems such as those used in next-generation automotive and autonomous platforms, is increasingly challenged by escalating system complexity, hardware-software heterogeneity, and the integration of intelligent, data-driven components. Ensuring dependability in such systems requires a holistic approach that spans multiple abstraction layers and encompasses both design- […]
VGR: Visual Grounded Reasoning
arXiv:2506.11991v3 Announce Type: replace-cross Abstract: In the field of multimodal chain-of-thought (CoT) reasoning, existing approaches predominantly rely on reasoning on pure language space, which inherently suffers from language bias and is largely confined to math or science domains. This narrow focus limits their ability to handle complex visual reasoning tasks that demand comprehensive understanding of […]
MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
arXiv:2510.17281v5 Announce Type: replace-cross Abstract: Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are almost reached due to the gradual depletion of high-quality data and marginal gains obtained from larger computational resource consumption. Inspired by the abilities of human and traditional AI […]
WildfireVLM: AI-powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery
arXiv:2602.13305v2 Announce Type: replace-cross Abstract: Wildfires are a growing threat to ecosystems, human lives, and infrastructure, with their frequency and intensity rising due to climate change and human activities. Early detection is critical, yet satellite-based monitoring remains challenging due to faint smoke signals, dynamic weather conditions, and the need for real-time analysis over large areas. […]
Removing Sandbagging in LLMs by Training with Weak Supervision
arXiv:2604.22082v2 Announce Type: replace-cross Abstract: As AI systems begin to automate complex tasks, supervision increasingly relies on weaker models or limited human oversight that cannot fully verify output quality. A model more capable than its supervisors could exploit this gap through sandbagging, producing work that appears acceptable but falls short of its true abilities. Can […]
Augmented Lagrangian Multiplier Network for State-wise Safety in Reinforcement Learning
arXiv:2605.00667v1 Announce Type: cross Abstract: Safety is a primary challenge in real-world reinforcement learning (RL). Formulating safety requirements as state-wise constraints has become a prominent paradigm. Handling state-wise constraints with the Lagrangian method requires a distinct multiplier for every state, necessitating neural networks to approximate them as a multiplier network. However, applying standard dual gradient […]