Stay updated with the latest research and technology news
arXiv:2602.05144v1 Announce Type: new Abstract: Machine learning systems are often trained and evaluated for fairness on historical data, yet deployed in environments where conditions have...
arXiv:2602.05145v1 Announce Type: new Abstract: Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads and...
arXiv:2602.05146v1 Announce Type: new Abstract: Machine systems inherently generate signals in which fault conditions and various physical variables are physically coupled. Although many existing fault...
arXiv:2602.05148v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has emerged as a practical paradigm for adapting large language models (LLMs) without updating all parameters. Most...
arXiv:2602.05150v1 Announce Type: new Abstract: Large Language Models (LLMs) are commonly trained on multilingual corpora that include Greek, yet reliable evaluation benchmarks for Greek-particularly those...
arXiv:2602.05152v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems commonly improve robustness via query-time adaptations such as query expansion and iterative retrieval. While effective, these...
arXiv:2602.05156v1 Announce Type: new Abstract: We present the PLATO Hand, a dexterous robotic hand with a hybrid fingertip that embeds a rigid fingernail within a...
arXiv:2602.05157v1 Announce Type: new Abstract: The intersection of Safety of Intended Functionality (SOTIF) and Functional Safety (FuSa) analysis of driving automation features has traditionally excluded...
arXiv:2602.05159v1 Announce Type: new Abstract: Sensing gloves have become important tools for teleoperation and robotic policy learning as they are able to provide rich signals...
arXiv:2602.05162v1 Announce Type: new Abstract: Deep neural networks often inherit social and demographic biases from annotated data during model training, leading to unfair predictions, especially...
arXiv:2602.05163v1 Announce Type: new Abstract: Underwater photography presents significant inherent challenges including reduced contrast, spatial blur, and wavelength-dependent color distortions. These effects can obscure the...
arXiv:2602.05164v1 Announce Type: new Abstract: Foundation models are trained on broad data distributions, yielding generalist capabilities that enable many downstream applications but also expand the...
arXiv:2602.05165v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing the reasoning capabilities of Large Language Models (LLMs). However,...
arXiv:2602.05175v1 Announce Type: new Abstract: Deep neural networks demonstrate impressive performance in visual recognition, but they remain vulnerable to adversarial attacks that is imperceptible to...
arXiv:2602.05176v1 Announce Type: new Abstract: Language models (LMs) are increasingly used in collaboration: multiple LMs trained by different parties collaborate through routing systems, multi-agent debate,...
arXiv:2602.05178v1 Announce Type: new Abstract: Coastal hypoxia, especially in the northern part of Gulf of Mexico, presents a persistent ecological and economic concern. Seasonal models...
arXiv:2602.05181v1 Announce Type: new Abstract: The growing reliance on prediction markets as epistemic infrastructures has positioned platforms like Polymarket as providers of objective, real-time probabilistic...
arXiv:2602.05182v1 Announce Type: new Abstract: Model collaboration -- systems where multiple language models (LMs) collaborate -- combines the strengths of diverse models with cost in...
arXiv:2602.05183v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior...
arXiv:2602.05186v1 Announce Type: new Abstract: Sequence alignment is a cornerstone technique in computational biology for assessing similarities and differences among biological sequences. A key variant,...
arXiv:2602.05187v1 Announce Type: new Abstract: Spectral neural operators, particularly Fourier Neural Operators (FNO), are a powerful framework for learning solution operators of partial differential equations...
arXiv:2602.05189v1 Announce Type: new Abstract: As internet access expands, so does exposure to harmful content, increasing the need for effective moderation. Research has demonstrated that...
arXiv:2602.05190v1 Announce Type: new Abstract: We propose PoseGaussian, a pose-guided Gaussian Splatting framework for high-fidelity human novel view synthesis. Human body pose serves a dual...
arXiv:2602.05191v1 Announce Type: new Abstract: As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding...