Stay updated with the latest research and technology news
arXiv:2601.22120v1 Announce Type: new Abstract: High renewable penetration increases the frequency and magnitude of net-load ramps, stressing real-time flexibility. Two commonly deployed remedies are look-ahead...
arXiv:2601.22123v1 Announce Type: new Abstract: Simulating the long-time evolution of Hamiltonian systems is limited by the small timesteps required for stable numerical integration. To overcome...
arXiv:2601.22124v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis. To enable their use...
arXiv:2601.22125v1 Announce Type: new Abstract: Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality...
arXiv:2601.22127v1 Announce Type: new Abstract: Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in...
arXiv:2601.22128v1 Announce Type: new Abstract: Large language models (LLMs) trained with next-word-prediction have achieved success as clinical foundation models. Representations from these language backbones yield...
arXiv:2601.22129v1 Announce Type: new Abstract: Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE)...
arXiv:2601.22130v1 Announce Type: new Abstract: Frontier large language models (LLMs) excel as autonomous agents in many domains, yet they remain untested in complex enterprise systems...
arXiv:2601.22131v1 Announce Type: new Abstract: Multi-objective optimization aims to solve problems with competing objectives, often with only black-box access to a problem and a limited...
arXiv:2601.22132v1 Announce Type: new Abstract: Large Language Models (LLMs) deliver state-of-the-art performance on complex reasoning tasks, but their inference costs limit deployment at scale. Small...
arXiv:2601.22135v1 Announce Type: new Abstract: Full-image relighting remains a challenging problem due to the difficulty of collecting large-scale structured paired data, the difficulty of maintaining...
arXiv:2601.22137v1 Announce Type: new Abstract: Matrix functions such as square root, inverse roots, and orthogonalization play a central role in preconditioned gradient methods for neural...
arXiv:2601.22139v1 Announce Type: new Abstract: Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a...
arXiv:2601.22141v1 Announce Type: new Abstract: In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained...
arXiv:2601.22143v1 Announce Type: new Abstract: Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented ability to...
arXiv:2601.22146v1 Announce Type: new Abstract: Due to limited supervised training data, large language models (LLMs) are typically pre-trained via a self-supervised "predict the next word"...
arXiv:2601.22149v1 Announce Type: new Abstract: The development of autonomous web agents, powered by Large Language Models (LLMs) and reinforcement learning (RL), represents a significant step...
arXiv:2601.22150v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when...
arXiv:2601.22151v1 Announce Type: new Abstract: Neural networks have been successfully applied in various resource-constrained edge devices, where usually central processing units (CPUs) instead of graphics...
arXiv:2601.22153v1 Announce Type: new Abstract: Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, struggle in...
arXiv:2601.22154v1 Announce Type: new Abstract: Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However,...
arXiv:2601.22155v1 Announce Type: new Abstract: We introduce UEval, a benchmark to evaluate unified models, i.e., models capable of generating both images and text. UEval comprises...
arXiv:2601.22156v1 Announce Type: new Abstract: Hybrid Transformer architectures, which combine softmax attention blocks and recurrent neural networks (RNNs), have shown a desirable performance-throughput tradeoff for...
arXiv:2601.22157v1 Announce Type: new Abstract: Public repositories host millions of fine-tuned models, yet community usage remains disproportionately concentrated on a small number of foundation checkpoints....