arXiv:2511.07318v3 Announce Type: replace-cross Abstract: Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet…
arXiv:2510.20486v2 Announce Type: replace-cross Abstract: Imbalanced labels can cause frequent samples to dominate AI-based quantitative remote sensing, degrading rare-event retrieval. In rain-rate retrieval based on satellite infrared brightness…
arXiv:2510.18019v3 Announce Type: replace-cross Abstract: Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they…
arXiv:2510.10932v5 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly vulnerable to behavioral backdoor manipulation…
arXiv:2509.11080v4 Announce Type: replace-cross Abstract: Recommender systems (RecSys) have been widely applied to various applications, including E-commerce, finance, healthcare, social media and have become increasingly influential in shaping…
arXiv:2508.03448v5 Announce Type: replace-cross Abstract: Music recordings often suffer from audio quality issues such as excessive reverberation, distortion, clipping, tonal imbalances, and a narrowed stereo image, especially when created in…
arXiv:2507.01663v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-collocated RL frameworks suffer from significant…
arXiv:2506.19960v2 Announce Type: replace-cross Abstract: Reliable description of bond breaking remains a major challenge for quantum chemistry due to the multireference character of the electronic structure in dissociating species. Multireference…
arXiv:2504.20125v2 Announce Type: replace-cross Abstract: A key factor for lunar mission planning is the ability to assess the local availability of raw materials. However, many potentially relevant measurements are scattered across a variety of…
arXiv:2504.04981v3 Announce Type: replace-cross Abstract: This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledge…
arXiv:2504.04903v3 Announce Type: replace-cross Abstract: We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: image…
arXiv:2503.00785v2 Announce Type: replace-cross Abstract: How to endow aerial robots with the ability to operate in close proximity remains an open problem. The core challenges lie in the propulsion system's dual-task requirement: generating…
arXiv:2502.14043v4 Announce Type: replace-cross Abstract: Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow…
arXiv:2502.07250v3 Announce Type: replace-cross Abstract: Modern machine learning models excel at detecting individual actions, sounds, or scene attributes from short, localized observations. However, many real-world tasks, such as in smart cities…
arXiv:2312.11581v3 Announce Type: replace-cross Abstract: The pandemic in 2020 and 2021 had enormous economic and societal consequences, and studies show that contact tracing algorithms can be key in the early containment of the virus. While large…
arXiv:2609.11498v2 Announce Type: replace Abstract: Practical uncertainty quantification (UQ) for large language models must decide, from a single generation, whether a specific answer should be trusted. Existing methods either sample multiple…
arXiv:2609.11489v2 Announce Type: replace Abstract: Cooperative AI agents are evaluated against other AIs, yet human cooperation relies on implicit conventions -- shared protocols for reading meaning beyond the literal message -- which AI-AI…
arXiv:2609.11318v2 Announce Type: replace Abstract: Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchmarks mainly evaluate medium-horizon…
arXiv:2609.11030v2 Announce Type: replace Abstract: AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare public failures with agent-security evaluations…
arXiv:2609.10992v2 Announce Type: replace Abstract: The integration of Large Language Models into daily tasks relies on context-rich instructions, inevitably exposing sensitive user information. Current privacy-preserving methods typically employ…
arXiv:2609.10629v2 Announce Type: replace Abstract: Quadratic Unconstrained Binary Optimization (QUBO) is a central formulation for combinatorial optimization and has gained increasing attention due to its compatibility with quantum, hybrid…
arXiv:2609.09113v2 Announce Type: replace Abstract: While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autonomous development demands a missing pillar: post-hoc monitoring and auditing…
arXiv:2609.08407v3 Announce Type: replace Abstract: In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qwen3-Embedding and Qwen3-VL-Embedding. We…
arXiv:2609.07627v2 Announce Type: replace Abstract: AI agents sometimes act aligned when they infer they are being tested, and differently when not. We argue this is not an anomaly but what current training regimes are structured to select for…
Pick what should wake you up. We only push stories the AI rates as genuinely urgent.