Stay updated with the latest research and technology news
arXiv:2503.17736v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) have made significant strides in the field of video understanding in recent times. Nevertheless, existing video...
arXiv:2503.19859v3 Announce Type: replace Abstract: The substantial computational demands of modern large-scale deep learning present significant challenges for efficient training and deployment. Recent research has...
arXiv:2503.22782v2 Announce Type: replace Abstract: Uncovering the opacity of diffusion-based generative models is urgently needed, as their applications continue to expand while their underlying procedures...
arXiv:2504.02443v3 Announce Type: replace Abstract: Performance-critical industrial applications, including large-scale program, network, and distributed system analyses, rely on fixed-point computations. The introduction of recursive common...
arXiv:2504.02546v4 Announce Type: replace Abstract: Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT)....
arXiv:2504.03622v2 Announce Type: replace Abstract: Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization...
arXiv:2504.16299v3 Announce Type: replace Abstract: Hoeffding's formulation and solution to the universal hypothesis testing (UHT) problem had a profound impact on many subsequent works dealing...
arXiv:2504.17878v2 Announce Type: replace Abstract: The imminent realization of fault-tolerant quantum computing precipitates a systemic collapse of classical public-key infrastructure and necessitates an urgent transition...
arXiv:2504.20106v2 Announce Type: replace Abstract: Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can...
arXiv:2505.04638v4 Announce Type: replace Abstract: Large language models (LLMs) and large multimodal models (LMMs) promise to accelerate biomedical discovery, yet their reliability remains unclear. We...
arXiv:2505.12311v3 Announce Type: replace Abstract: Despite over a decade of development, autonomous driving trajectory planning in complex urban environments continues to encounter significant challenges. These...
arXiv:2505.12387v4 Announce Type: replace Abstract: With the rapid discovery of emergent phenomena in deep learning and large language models, understanding their cause has become an...
arXiv:2505.12728v3 Announce Type: replace Abstract: Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a...
arXiv:2505.12940v2 Announce Type: replace Abstract: Operator learning is a rapidly growing field that aims to approximate nonlinear operators related to partial differential equations (PDEs) using...
arXiv:2505.13102v3 Announce Type: replace Abstract: Unlike conventional "black-box" transformers with classical self-attention mechanism, we build a lightweight and interpretable transformer-like neural net by unrolling a...
arXiv:2505.13197v3 Announce Type: replace Abstract: Time-resolved single-cell omics data offers high-throughput, genome-wide measurements of cellular states, which are instrumental to reverse-engineer the processes underpinning cell...
arXiv:2505.13696v2 Announce Type: replace Abstract: Many animals possess a remarkable capacity to rapidly construct flexible cognitive maps of their environments. These maps are crucial for...
arXiv:2505.14103v3 Announce Type: replace Abstract: Jailbreak attacks to Large audio-language models (LALMs) are studied recently, but they exclusively focused on the attack scenario where the...
arXiv:2505.14661v3 Announce Type: replace Abstract: LLMs enable an exciting new class of data processing applications over large collections of unstructured documents. Several new programming frameworks...
arXiv:2505.16936v4 Announce Type: replace Abstract: We present SPAR, a framework for self-supervised placement-aware representation learning in distributed sensing. Distributed sensing spans applications where multiple spatially...
arXiv:2505.16964v2 Announce Type: replace Abstract: Real-world clinical practice demands multi-image comparative reasoning, yet current medical benchmarks remain limited to single-frame interpretation. We present MedFrameQA, the...
arXiv:2505.17001v2 Announce Type: replace Abstract: This paper studies the task of SatStreet-view synthesis, which aims to render photorealistic street-view panorama images and videos given any...
arXiv:2505.17730v2 Announce Type: replace Abstract: Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their...
arXiv:2505.17782v2 Announce Type: replace Abstract: Monitoring volcanic activity is of paramount importance to safeguarding lives, infrastructure, and ecosystems. However, only a small fraction of known...