Stay updated with the latest research and technology news
arXiv:2602.14028v1 Announce Type: new Abstract: While Group Relative Policy Optimization (GRPO) offers a powerful framework for LLM post-training, its effectiveness in open-ended domains like Machine...
arXiv:2602.14030v1 Announce Type: new Abstract: Large language models now produce text indistinguishable from human writing, which increases the need for reliable provenance tracing. Multi-bit watermarking...
arXiv:2602.14032v1 Announce Type: new Abstract: Enhancing the generalization capability of robotic learning to enable robots to operate effectively in diverse, unseen scenes is a fundamental...
arXiv:2602.14033v1 Announce Type: new Abstract: Future sixth-generation (6G) mobile networks will demand artificial intelligence (AI) agents that are not only autonomous and efficient, but also...
arXiv:2602.14035v1 Announce Type: new Abstract: Flowchart-oriented dialogue (FOD) systems aim to guide users through multi-turn decision-making or operational procedures by following a domain-specific flowchart to...
arXiv:2602.14037v1 Announce Type: new Abstract: We study the decision problem Affine Rank Minimization, denoted ARM(k). The input consists of rational matrices A_1,...,A_q in Q^{m x...
arXiv:2602.14038v1 Announce Type: new Abstract: Memory is critical for enabling large language model (LLM) based agents to maintain coherent behavior over long-horizon interactions. However, existing...
arXiv:2602.14039v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) embedding models combine expert outputs using weighted linear summation, implicitly assuming a linear subspace structure in the embedding...
arXiv:2602.14040v1 Announce Type: new Abstract: Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for...
arXiv:2602.14041v1 Announce Type: new Abstract: We present BitDance, a scalable autoregressive (AR) image generator that predicts binary visual tokens instead of codebook indices. With high-entropy...
arXiv:2602.14042v1 Announce Type: new Abstract: In real-world scenarios, the performance of semantic segmentation often deteriorates when processing low-quality (LQ) images, which may lack clear semantic...
arXiv:2602.14043v1 Announce Type: new Abstract: Social simulation is critical for mining complex social dynamics and supporting data-driven decision making. LLM-based methods have emerged as powerful...
arXiv:2602.14044v1 Announce Type: new Abstract: Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While...
arXiv:2602.14045v1 Announce Type: new Abstract: The popularization of social media has led to increasing consumption of narrative content in byte-sized formats. Such micro-dramas contain fast-pace...
arXiv:2602.14046v1 Announce Type: new Abstract: Maintenance is a critical stage in the software lifecycle, ensuring that post-release systems remain reliable, efficient, and adaptable. However, manual...
arXiv:2602.14048v1 Announce Type: new Abstract: Embodied social agents have recently advanced in generating synchronized speech and gestures. However, most interactive systems remain fundamentally reactive, responding...
arXiv:2602.14049v1 Announce Type: new Abstract: Spatio-temporal traffic forecasting is a core component of intelligent transportation systems, supporting various downstream tasks such as signal control and...
arXiv:2602.14050v1 Announce Type: new Abstract: Length generalization is the ability of language models to maintain performance on inputs longer than those seen during pretraining. In...
arXiv:2602.14051v1 Announce Type: new Abstract: Decentralized federated learning (DFL) enables edge devices to collaboratively train models through local training and fully decentralized device-to-device (D2D) model...
arXiv:2602.14054v1 Announce Type: new Abstract: Code generation remains a challenging task that requires precise and structured reasoning. Existing Test Time Scaling (TTS) methods, including structured...
arXiv:2602.14055v1 Announce Type: new Abstract: The widespread adoption of TLS 1.3 and QUIC has rendered payload content invisible, shifting traffic analysis toward side-channel features. However,...
arXiv:2602.14060v1 Announce Type: new Abstract: We introduce LM-Lexicon, an innovative definition modeling approach that incorporates data clustering, semantic expert learning, and model merging using a...
arXiv:2602.14062v1 Announce Type: new Abstract: Large, openly licensed speech datasets are essential for building automatic speech recognition (ASR) systems, yet many widely spoken languages remain...
arXiv:2602.14065v1 Announce Type: new Abstract: Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval. However,...