Stay updated with the latest research and technology news
arXiv:2601.21979v1 Announce Type: new Abstract: Feature embeddings acquired from pretrained models are widely used in medical applications of deep learning to assess the characteristics of...
arXiv:2601.21981v1 Announce Type: new Abstract: Event stream data is a critical resource for fine-grained analysis across various domains, including financial transactions, system operations, and sports....
arXiv:2601.21983v1 Announce Type: new Abstract: Bayesian inference allows us to define a posterior distribution over the weights of a generic neural network (NN). Exact posteriors...
arXiv:2601.21984v1 Announce Type: new Abstract: Discovering superior circuit topologies requires navigating an exponentially large design space-a challenge traditionally reserved for human experts. Existing AI methods...
arXiv:2601.21985v1 Announce Type: new Abstract: Generative models for 3D molecular conformations must respect Euclidean symmetries and concentrate probability mass on thermodynamically favorable, mechanically stable structures....
arXiv:2601.21986v1 Announce Type: new Abstract: Traditional sequential recommendation (SR) models learn low-dimensional item ID embeddings from user-item interactions, often overlooking textual information such as item...
arXiv:2601.21988v1 Announce Type: new Abstract: An agent operating in an unknown dynamical system must learn its dynamics from observations. Active information gathering accelerates this learning,...
arXiv:2601.21989v1 Announce Type: new Abstract: We study algorithms in the resettable streaming model, where the value of each key can either be increased or reset...
arXiv:2601.21991v1 Announce Type: new Abstract: Real-world reinforcement learning is often \emph{nonstationary}: rewards and dynamics drift, accelerate, oscillate, and trigger abrupt switches in the optimal action....
arXiv:2601.21993v1 Announce Type: new Abstract: Contemporary software architectures struggle to support autonomous agents whose reasoning is adaptive, probabilistic, and context-dependent, while system integration remains dominated...
arXiv:2601.21996v1 Announce Type: new Abstract: While Mechanistic Interpretability has identified interpretable circuits in LLMs, their causal origins in training data remain elusive. We introduce Mechanistic...
arXiv:2601.21998v1 Announce Type: new Abstract: This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively,...
arXiv:2601.21999v1 Announce Type: new Abstract: Imbalanced Domain Generalization (IDG) focuses on mitigating both domain and label shifts, both of which fundamentally shape the model's decision...
arXiv:2601.22001v1 Announce Type: new Abstract: AI agent inference is driving an inference heavy datacenter future and exposes bottlenecks beyond compute - especially memory capacity, memory...
arXiv:2601.22002v1 Announce Type: new Abstract: Transformers achieve superior performance on many tasks, but impose heavy compute and memory requirements during inference. This inference can be...
arXiv:2601.22008v1 Announce Type: new Abstract: Unlike short-form retrieval-augmented generation (RAG), such as factoid question answering, long-form RAG requires retrieval to provide documents covering a wide...
arXiv:2601.22010v1 Announce Type: new Abstract: Language models often default to a narrow set of high-probability outputs, leaving their generation paths homogeneous and prone to mode...
arXiv:2601.22012v1 Announce Type: new Abstract: Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying mechanisms. We...
arXiv:2601.22013v1 Announce Type: new Abstract: Video storytelling is often constrained by available material, limiting creative expression and leaving undesired narrative gaps. Generative video offers a...
arXiv:2601.22016v1 Announce Type: new Abstract: The quality of machine learning models depends heavily on their training data. Selecting high-quality, diverse training sets for large language...
arXiv:2601.22018v1 Announce Type: new Abstract: Recently, 3D vision-based diffusion policies have shown strong capability in learning complex robotic manipulation skills. However, a common architectural mismatch...
arXiv:2601.22020v1 Announce Type: new Abstract: Unlearning in Multimodal Large Language Models (MLLMs) prevents the model from revealing private information when queried about target images. Existing...
arXiv:2601.22024v1 Announce Type: new Abstract: The operation of future 6th-generation (6G) mobile networks will increasingly rely on the ability of deep reinforcement learning (DRL) to...
arXiv:2601.22025v1 Announce Type: new Abstract: Evaluating Large Language Model (LLM) applications differs from traditional software testing because outputs are stochastic, high-dimensional, and sensitive to prompt...