Stay updated with the latest research and technology news
arXiv:2602.01338v1 Announce Type: new Abstract: We present algorithms for diffusion model sampling which obtain $\delta$-error in $\mathrm{polylog}(1/\delta)$ steps, given access to $\widetilde O(\delta)$-accurate score estimates...
arXiv:2602.01339v1 Announce Type: new Abstract: We provide the first study of the problem of finding differentially private (DP) second-order stationary points (SOSP) in stochastic (non-convex)...
arXiv:2602.01340v1 Announce Type: new Abstract: Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational...
arXiv:2602.01341v1 Announce Type: new Abstract: In traditional access control policies, every access granted and administrative account introduces an additional vulnerability, as a corruption of a...
arXiv:2602.01342v1 Announce Type: new Abstract: Powerful quantum computers in the future may be able to break the security used for communication between vehicles and other...
arXiv:2602.01345v1 Announce Type: new Abstract: Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for...
arXiv:2602.01346v1 Announce Type: new Abstract: While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging....
arXiv:2602.01348v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is widely used to ground Large Language Models (LLMs) for multi-hop question answering. Recent work mainly focused...
arXiv:2602.01350v1 Announce Type: new Abstract: Set partitions are arrangements of distinct objects into groups. The problem of listing all set partitions arises in a variety...
arXiv:2602.01351v1 Announce Type: new Abstract: The problem of Profit Maximization asks to choose a limited number of influential users from a given social network such...
arXiv:2602.01352v1 Announce Type: new Abstract: Text-to-motion generation, which converts motion language descriptions into coherent 3D human motion sequences, has attracted increasing attention in fields, such...
arXiv:2602.01355v1 Announce Type: new Abstract: Aggregation query over free text is a long-standing yet underexplored problem. Unlike ordinary question answering, aggregate queries require exhaustive evidence...
arXiv:2602.01356v1 Announce Type: new Abstract: This paper introduces bucket calculus, a novel mathematical framework that fundamentally transforms the computational complexity landscape of parallel machine scheduling...
arXiv:2602.01357v1 Announce Type: new Abstract: Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model...
arXiv:2602.01359v1 Announce Type: new Abstract: Although recent studies on time-series anomaly detection have increasingly adopted ever-larger neural network architectures such as transformers and foundation models,...
arXiv:2602.01362v1 Announce Type: new Abstract: In discrete generative modeling, two dominant paradigms demonstrate divergent capabilities: Masked Diffusion Language Models (MDLM) excel at semantic understanding and...
arXiv:2602.01363v1 Announce Type: new Abstract: Self-supervised speaker embeddings are widely used in speaker verification systems, but prior work has shown that they often encode sensitive...
arXiv:2602.01365v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a key technique for improving reasoning abilities in large language models, yet its...
arXiv:2602.01367v1 Announce Type: new Abstract: Survival analysis is essential for clinical decision-making, as it allows practitioners to estimate time-to-event outcomes, stratify patient risk profiles, and...
arXiv:2602.01368v1 Announce Type: new Abstract: As Artificial Intelligence (AI) becomes increasingly embedded in financial decision-making, the opacity of complex models presents significant challenges for professionals...
arXiv:2602.01369v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has demonstrated strong performance in video understanding tasks, yet its adversarial robustness remains underexplored. Existing attack methods often...
arXiv:2602.01370v1 Announce Type: new Abstract: Synthetic data offers a scalable solution for vision-language pre-training, yet current state-of-the-art methods typically rely on scaling up a single...
arXiv:2602.01378v1 Announce Type: new Abstract: Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and...
arXiv:2602.01381v1 Announce Type: new Abstract: Inference-time scaling has recently emerged as a powerful paradigm for improving the reasoning capability of large language models. Among various...