Stay updated with the latest research and technology news
arXiv:2603.04972v1 Announce Type: new Abstract: Weight-space merging aims to combine multiple fine-tuned LLMs into a single model without retraining, yet most existing approaches remain fundamentally...
arXiv:2603.04974v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning...
arXiv:2603.04975v1 Announce Type: new Abstract: Event cameras, with their high dynamic range, show great promise for Low-light Image Enhancement (LLIE). Existing works primarily focus on...
arXiv:2603.04976v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of...
arXiv:2603.04977v1 Announce Type: new Abstract: Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based...
arXiv:2603.04979v1 Announce Type: new Abstract: Compared to the first generation of deep neural networks, dominated by regular, compute-intensive kernels such as matrix multiplications (MatMuls) and...
arXiv:2603.04980v1 Announce Type: new Abstract: In this work, we introduce Wallaroo, a simple autoregressive baseline that leverages next-token prediction to unify multi-modal understanding, image generation,...
arXiv:2603.04981v1 Announce Type: new Abstract: Dynamic data selection accelerates training by sampling a changing subset of the dataset while preserving accuracy. We rethink two core...
arXiv:2603.04982v1 Announce Type: new Abstract: Can targeted user training unlock the productive potential of generative artificial intelligence (GenAI) in professional settings? We investigate this question...
arXiv:2603.04985v1 Announce Type: new Abstract: Personas are a valuable tool for discussing accessibility requirements in software design and development practices. However, the use of personas...
arXiv:2603.04986v1 Announce Type: new Abstract: Sequential Recommendation (SR) predicts users next interactions by modeling the temporal order of their historical behaviors. Existing approaches, including traditional...
arXiv:2603.04988v1 Announce Type: new Abstract: Multi-degree-of-freedom (DOF) robotic manipulators exhibit strongly nonlinear, high-dimensional, and coupled dynamics, posing significant challenges for controller design. To address these...
arXiv:2603.04989v1 Announce Type: new Abstract: Tracking any point (TAP) is a fundamental yet challenging task in computer vision, requiring high precision and long-term motion reasoning....
arXiv:2603.04991v1 Announce Type: new Abstract: Belief propagation (BP) decoding of quantum low density parity check (QLDPC) codes is often implemented using overcomplete stabilizer (OS) representations,...
arXiv:2603.04992v1 Announce Type: new Abstract: The safety evaluation of large language models (LLMs) remains largely centered on English, leaving non-English languages and culturally grounded risks...
arXiv:2603.04993v1 Announce Type: new Abstract: Monocular 3D clothed human reconstruction aims to generate a complete and realistic textured 3D avatar from a single image. Existing...
arXiv:2603.04996v1 Announce Type: new Abstract: Large language models perform well in short text generation but still struggle with long text generation, particularly under complex constraints....
arXiv:2603.04998v1 Announce Type: new Abstract: Non-Intrusive Load Monitoring (NILM) aims to estimate appliance-level consumption from aggregate electrical signals recorded at a single measurement point. In...
arXiv:2603.04999v1 Announce Type: new Abstract: Mobile photography is often limited by complex, lens-specific optical aberrations. While recent deep learning methods approach this as an end-to-end...
arXiv:2603.05000v1 Announce Type: new Abstract: Autonomous Mobility-on-Demand (AMoD) systems promise to revolutionize urban transportation by providing affordable on-demand services to meet growing travel demand. However,...
arXiv:2603.05002v1 Announce Type: new Abstract: The Edge of Stability (EoS) is a phenomenon where the sharpness (largest eigenvalue) of the Hessian converges to $2/\eta$ during...
arXiv:2603.05004v1 Announce Type: new Abstract: Graph Neural Networks (GNNs) have achieved remarkable results in various tasks. Recent studies reveal that graph backdoor attacks can poison...
arXiv:2603.05005v1 Announce Type: new Abstract: Traditional financial institutions face inefficiencies that can be addressed by distributed ledger technology. However, a primary barrier to adoption is...
arXiv:2603.05007v1 Announce Type: new Abstract: We introduce a general framework for positional games in which players score points by claiming a prescribed portion of each...