Stay updated with the latest research and technology news
arXiv:2602.02104v1 Announce Type: new Abstract: Open-weight LLMs have been released by frontier labs; however, sovereign Large Language Models (for languages other than English) remain low...
arXiv:2602.02107v1 Announce Type: new Abstract: Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss...
arXiv:2602.02108v1 Announce Type: new Abstract: Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The...
arXiv:2602.02110v1 Announce Type: new Abstract: World models learn an internal representation of environment dynamics, enabling agents to simulate and reason about future states within a...
arXiv:2602.02112v1 Announce Type: new Abstract: Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically...
arXiv:2602.02114v1 Announce Type: new Abstract: Continuous Conditional Diffusion Model (CCDM) is a diffusion-based framework designed to generate high-quality images conditioned on continuous regression labels. Although...
arXiv:2602.02117v1 Announce Type: new Abstract: Von Neumann entropy (VNE) is a fundamental quantity in quantum information theory and has recently been adopted in machine learning...
arXiv:2602.02118v1 Announce Type: new Abstract: We study the theoretical convergence of the nonlinear least-squares splitting method for the Monge-Amp\`ere equation in which each iteration decouples...
arXiv:2602.02119v1 Announce Type: new Abstract: Fault injectors are essential tools for evaluating the reliability and resilience of computing systems. They enable the simulation of hardware...
arXiv:2602.02121v1 Announce Type: new Abstract: TriCloudEdge is a scalable three-tier cloud continuum that integrates far-edge devices, intermediate edge nodes, and central cloud services, working in...
arXiv:2602.02123v1 Announce Type: new Abstract: We propose MLV-Edit, a training-free, flow-based framework that address the unique challenges of minute-level video editing. While existing techniques excel...
arXiv:2602.02124v1 Announce Type: new Abstract: Drug-induced toxicity remains a leading cause of failure in preclinical development and early clinical trials. Detecting adverse effects at an...
arXiv:2602.02126v1 Announce Type: new Abstract: Group-wise quantization is an effective strategy for mitigating accuracy degradation in low-bit quantization of large language models (LLMs). Among existing...
arXiv:2602.02128v1 Announce Type: new Abstract: Molecular dynamics (MD) simulations remain the gold standard for studying protein dynamics, but their computational cost limits access to biologically...
arXiv:2602.02130v1 Announce Type: new Abstract: Supervised synthetic CT generation from CBCT requires registered training pairs, yet perfect registration between separately acquired scans remains unattainable. This...
arXiv:2602.02131v1 Announce Type: new Abstract: Stacked intelligent metasurfaces (SIM) provide a cost-effective and scalable solution for large-scale antenna communications.However, efficient channel state information acquisition and...
arXiv:2602.02132v1 Announce Type: new Abstract: Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and...
arXiv:2602.02133v1 Announce Type: new Abstract: Autoregressive language models (ARMs) suffer from the reversal curse: after learning that "$A$ is $B$", they often fail on the...
arXiv:2602.02135v1 Announce Type: new Abstract: A dominating set of a graph G(V, E) is a set of vertices D\subseteq V such that every vertex in...
arXiv:2602.02136v1 Announce Type: new Abstract: Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety...
arXiv:2602.02137v1 Announce Type: new Abstract: Modern data centers (DCs) hosting artificial intelligence (AI)-dedicated devices operate at high power densities with rapidly varying workloads, making minute-level...
arXiv:2602.02138v1 Announce Type: new Abstract: Despite the remarkable success that Multi-Agent Code Generation Systems (MACGS) have achieved, the inherent complexity of multi-agent architectures produces substantial...
arXiv:2602.02139v1 Announce Type: new Abstract: Machine unlearning aims to unlearn specified training data (e.g. sensitive or copyrighted material). A prominent approach is to fine-tune an...
arXiv:2602.02140v1 Announce Type: new Abstract: Recent advances in unified multimodal models (UMM) have demonstrated remarkable progress in both understanding and generation tasks. However, whether these...