Stay updated with the latest research and technology news
arXiv:2601.21803v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems combine dense retrievers and language models to ground LLM outputs in retrieved documents. However, the opacity...
arXiv:2601.21804v1 Announce Type: new Abstract: Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on...
arXiv:2601.21805v1 Announce Type: new Abstract: Cross-domain recommendation (CDR) offers an effective strategy for improving recommendation quality in a target domain by leveraging auxiliary signals from...
arXiv:2601.21814v1 Announce Type: new Abstract: We explore the concept of folklore within software engineering, drawing from folklore studies to define and characterize narratives, myths, rituals,...
arXiv:2601.21815v1 Announce Type: new Abstract: Understanding how media rhetoric shapes audience engagement is crucial in the attention economy. This study examines how moral emotional framing...
arXiv:2601.21816v1 Announce Type: new Abstract: Evaluating the performance of large language models (LLMs) from human preference data is crucial for obtaining LLM leaderboards. However, many...
arXiv:2601.21821v1 Announce Type: new Abstract: Recent advances in Vision Language Models (VLMs) have driven significant progress in visual reasoning. However, open-source VLMs still lag behind...
arXiv:2601.21822v1 Announce Type: new Abstract: Rapid advancements in sixth-generation (6G) networks and large language models (LLMs) have paved the way for ubiquitous intelligence, wherein seamless...
arXiv:2601.21823v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) are highly energy-efficient due to event-driven, sparse computation, but their training is challenged by spike non-differentiability...
arXiv:2601.21824v1 Announce Type: new Abstract: Determinism is indispensable for reproducibility in large language model (LLM) training, yet it often exacts a steep performance cost. In...
arXiv:2601.21826v1 Announce Type: new Abstract: As large language models (LLMs) are applied to increasingly longer and more complex tasks, there is a growing need for...
arXiv:2601.21829v1 Announce Type: new Abstract: This article describes GAZELOAD, a multimodal dataset for mental workload estimation in industrial human-robot collaboration. The data were collected in...
arXiv:2601.21830v1 Announce Type: new Abstract: The electrocardiogram (ECG) is a cost-effective, highly accessible and widely employed diagnostic tool. With the advent of Foundation Models (FMs),...
arXiv:2601.21832v1 Announce Type: new Abstract: Machine learning models are widely regarded as a way forward to tackle multi-query challenges that arise once expensive black-box simulations...
arXiv:2601.21835v1 Announce Type: new Abstract: We introduce a scalable method to approximate the kernel of the Linearized Laplace Approximation (LLA). For this, we use a...
arXiv:2601.21837v1 Announce Type: new Abstract: In recent years, trustworthiness has garnered increasing attention and exploration in the field of intelligent education, due to the inherent...
arXiv:2601.21839v1 Announce Type: new Abstract: Test-time compute has emerged as a promising strategy to enhance the reasoning abilities of large language models (LLMs). However, this...
arXiv:2601.21841v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges...
arXiv:2601.21842v1 Announce Type: new Abstract: Software Pipelining is a classic and important loop-optimization for VLIW processors. It improves instruction-level parallelism by overlapping multiple iterations of...
arXiv:2601.21844v1 Announce Type: new Abstract: Efficient management of spare parts inventory is crucial in the automotive aftermarket, where demand is highly intermittent and uncertainty drives...
arXiv:2601.21845v1 Announce Type: new Abstract: Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train...
arXiv:2601.21846v1 Announce Type: new Abstract: As energy demands surge across ICT infrastructures, service providers must engage users in sustainable practices while maintaining the Quality of...
arXiv:2601.21847v1 Announce Type: new Abstract: Meta-Black-Box Optimization (MetaBBO) is an emerging avenue within Optimization community, where algorithm design policy could be meta-learned by reinforcement learning...
arXiv:2601.21851v1 Announce Type: new Abstract: Foundation models, despite their robust zero-shot capabilities, remain vulnerable to spurious correlations and 'Clever Hans' strategies. Existing mitigation methods often...