Stay updated with the latest research and technology news
arXiv:2503.04641v3 Announce Type: replace Abstract: Understanding and replicating the real world is a critical challenge in Artificial General Intelligence (AGI) research. To achieve this, many...
arXiv:2503.08796v2 Announce Type: replace Abstract: We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human...
arXiv:2503.09027v2 Announce Type: replace Abstract: Temporally localizing user-queried events through natural language is a crucial capability for video models. Recent methods predominantly adapt video LLMs...
arXiv:2503.09411v2 Announce Type: replace Abstract: The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid...
arXiv:2503.10522v3 Announce Type: replace Abstract: Audio and music generation based on flexible multimodal control signals is a widely applicable topic, with the following key challenges:...
arXiv:2503.10568v3 Announce Type: replace Abstract: We introduce ARPG, a novel visual autoregressive model that enables randomized parallel generation, addressing the inherent limitations of conventional raster-order...
arXiv:2503.12385v2 Announce Type: replace Abstract: Fine-grained visual categorization (FGVC) is a challenging but significant task in computer vision, which aims to recognize different sub-categories of...
arXiv:2503.13194v3 Announce Type: replace Abstract: The ability of artificial intelligence agents to make optimal decisions and generalise them to different domains and tasks is compromised...
arXiv:2504.06193v3 Announce Type: replace Abstract: Link prediction is a crucial graph-learning task with applications including citation prediction and product recommendation. Distilling Graph Neural Networks (GNNs)...
arXiv:2504.07667v2 Announce Type: replace Abstract: The generalization of learning-based high dynamic range (HDR) fusion is often limited by the availability of training data, as collecting...
arXiv:2504.09733v3 Announce Type: replace Abstract: Accurately estimating decision boundaries in black box systems is critical when ensuring safety, quality, and feasibility in real-world applications. However,...
arXiv:2504.13335v2 Announce Type: replace Abstract: Harmonic generation plays a crucial role in contrast-enhanced ultrasound, both for imaging and therapeutic applications. However, accurately capturing these nonlinear...
arXiv:2504.14326v2 Announce Type: replace Abstract: Mobile metaverses are envisioned as a transformative digital ecosystem that delivers immersive, intelligent, and ubiquitous services through mobile devices. Driven...
arXiv:2504.20426v3 Announce Type: replace Abstract: The advancement of reasoning capabilities in Large Language Models (LLMs) requires substantial amounts of high-quality reasoning data, particularly in mathematics....
arXiv:2504.20532v2 Announce Type: replace Abstract: Diffusion-based speech generation has achieved remarkable fidelity, increasing the risk of misuse and unauthorized redistribution. However, most existing generative speech...
arXiv:2504.20903v3 Announce Type: replace Abstract: We formalize AI-human collaboration through an agent-based simulation that distinguishes optimization-based AI search from satisficing-based human adaptation. Using an NK...
arXiv:2504.21205v3 Announce Type: replace Abstract: This paper introduces SecRepoBench, a benchmark to evaluate code agents on secure code completion in real-world repositories. SecRepoBench has 318...
arXiv:2505.00527v2 Announce Type: replace Abstract: Generalizing language-conditioned multi-task imitation learning (IL) models to novel long-horizon 3D manipulation tasks is challenging. To address this, we propose...
arXiv:2505.04338v2 Announce Type: replace Abstract: We propose Riemannian Denoising Diffusion Probabilistic Models (RDDPMs) for learning distributions on submanifolds of Euclidean space that are level sets...
arXiv:2505.04866v3 Announce Type: replace Abstract: We develop a fully discrete, semi-implicit mixed finite element method for approximating solutions to a class of fourth-order stochastic partial...
arXiv:2505.06795v5 Announce Type: replace Abstract: Amortized variational inference in latent-variable forecasters creates a deployment gap: the test-time encoder approximates a training-time optimization-refined latent, but without...
arXiv:2505.07671v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) has emerged as a powerful framework for enhancing large language models (LLMs) with external knowledge, particularly in...
arXiv:2505.07755v2 Announce Type: replace Abstract: Edge computing has emerged as a pivotal technology, offering significant advantages such as low latency, enhanced data security, and reduced...
arXiv:2505.07861v3 Announce Type: replace Abstract: Due to long generations, large language model (LLM) math reasoning demands significant computational resources and time. While many existing efficient...