Stay updated with the latest research and technology news
arXiv:2601.17467v1 Announce Type: new Abstract: Large reasoning models (LRMs) often generate long, seemingly coherent reasoning traces yet still produce incorrect answers, making hallucination detection challenging....
arXiv:2601.17468v1 Announce Type: new Abstract: Single Image Reflection Separation (SIRS) disentangles mixed images into transmission and reflection layers. Existing methods suffer from transmission-reflection confusion under...
arXiv:2601.17469v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have shown remarkable capabilities in learning from graph-structured data with various applications such as social analysis...
arXiv:2601.17470v1 Announce Type: new Abstract: Shadow removal under diverse lighting conditions requires disentangling illumination from intrinsic reflectance, a challenge compounded when physical priors are not...
arXiv:2601.17471v1 Announce Type: new Abstract: Continuous fuzzing platforms such as OSS-Fuzz uncover large numbers of vulnerabilities, yet the subsequent repair process remains largely manual. Unfortunately,...
arXiv:2601.17472v1 Announce Type: new Abstract: Cross-domain recommendation (CDR) has been increasingly explored to address data sparsity and cold-start issues. However, recent approaches typically disentangle domain-invariant...
arXiv:2601.17473v1 Announce Type: new Abstract: This paper considers the development of an AI-based provably-correct mathematical proof tutor. While Large Language Models (LLMs) allow seamless communication...
arXiv:2601.17476v1 Announce Type: new Abstract: Peer review determines which scholarship is legitimized; however, review biases often disadvantage scholarship that diverges from the norm. Human-Computer Interaction...
arXiv:2601.17480v1 Announce Type: new Abstract: Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable...
arXiv:2601.17481v1 Announce Type: new Abstract: Conversational AI systems require guardrails to prevent harmful outputs, yet existing approaches use static rules that cannot adapt to new...
arXiv:2601.17482v1 Announce Type: new Abstract: The prevailing "parse-then-compress" paradigm in log compression fundamentally limits effectiveness by treating log parsing and compression as isolated objectives. While...
arXiv:2601.17483v1 Announce Type: new Abstract: Training modern neural networks is increasingly fragile, with rare but severe destabilizing updates often causing irreversible divergence or silent performance...
arXiv:2601.17486v1 Announce Type: new Abstract: Visual imitation learning with 3D point clouds has advanced robotic manipulation by providing geometry-aware, appearance-invariant observations. However, point cloud-based policies...
arXiv:2601.17489v1 Announce Type: new Abstract: Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant...
arXiv:2601.17492v1 Announce Type: new Abstract: Large Language Models (LLMs) have revolutionized Recommender Systems (RS) through advanced generative user modeling. However, LLM-based RS (LLM-RS) often inadvertently...
arXiv:2601.17495v1 Announce Type: new Abstract: In many deployed systems, new text inputs are handled by retrieving similar past cases, for example when routing and responding...
arXiv:2601.17497v1 Announce Type: new Abstract: Functional encryption is a powerful cryptographic primitive that enables fine-grained access to encrypted data and underlies numerous applications. Although the...
arXiv:2601.17500v1 Announce Type: new Abstract: Learned Sparse Retrieval (LSR) methods construct sparse lexical representations of queries and documents that can be efficiently searched using inverted...
arXiv:2601.17502v1 Announce Type: new Abstract: PyTerrier provides a declarative framework for building and experimenting with Information Retrieval (IR) pipelines. In this demonstration, we highlight several...
arXiv:2601.17504v1 Announce Type: new Abstract: Accurate brain tumor segmentation from multi-modal magnetic resonance imaging (MRI) is a prerequisite for precise radiotherapy planning and surgical navigation....
arXiv:2601.17507v1 Announce Type: new Abstract: Humanoid robot loco-manipulation remains constrained by the semantic-physical gap. Current methods face three limitations: Low sample efficiency in reinforcement learning,...
arXiv:2601.17508v1 Announce Type: new Abstract: We consider the permanent of a square matrix with non-negative entries. A tractable approximation is given by the so-called Bethe...
arXiv:2601.17512v1 Announce Type: new Abstract: Federated Learning (FL) that extracts data knowledge while protecting the privacy of multiple clients has achieved remarkable results in distributed...
arXiv:2601.17513v1 Announce Type: new Abstract: This paper presents an automated antenna design and optimization framework employing multi-objective genetic algorithms (MOGAs) to investigate various evolutionary optimization...