Stay updated with the latest research and technology news
arXiv:2602.17625v1 Announce Type: new Abstract: Modern big-data systems generate massive, heterogeneous, and geographically dispersed streams that are large-scale and privacy-sensitive, making centralization challenging. While federated...
arXiv:2602.17632v1 Announce Type: new Abstract: Modern offline Reinforcement Learning (RL) methods find performant actor-critics, however, fine-tuning these actor-critics online with value-based RL algorithms typically causes...
arXiv:2602.17633v1 Announce Type: new Abstract: Reasoning with LLMs increasingly unfolds inside a broader verification loop. Internally, systems use cheap checks, such as self-consistency or proxy...
arXiv:2602.17634v1 Announce Type: new Abstract: Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse...
arXiv:2602.17636v1 Announce Type: new Abstract: Existing methods for Virtual Try-On (VTON) often struggle to preserve fine garment details, especially in unpaired settings where accurate person-garment...
arXiv:2602.17639v1 Announce Type: new Abstract: Retrieving user-specified objects from complex scenes remains a challenging task, especially when queries are ambiguous or involve multiple similar objects....
arXiv:2602.17641v1 Announce Type: new Abstract: Feature engineering remains a critical yet challenging bottleneck in machine learning, particularly for tabular data, as identifying optimal features from...
arXiv:2602.17642v1 Announce Type: new Abstract: Traditional electronic recycling processes suffer from significant resource loss due to inadequate material separation and identification capabilities, limiting material recovery....
arXiv:2602.17645v1 Announce Type: new Abstract: Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing gradients and complex multimodal boundaries. While prior...
arXiv:2602.17646v1 Announce Type: new Abstract: As humans increasingly rely on multiround conversational AI for high stakes decisions, principled frameworks are needed to ensure such interactions...
arXiv:2602.17649v1 Announce Type: new Abstract: This study investigates the effectiveness of a Virtual Reality (VR)-based training program in improving body awareness among children with Attention...
arXiv:2602.17650v1 Announce Type: new Abstract: Humans can infer the three-dimensional structure of objects from two-dimensional visual inputs. Modeling this ability has been a longstanding goal...
arXiv:2602.17651v1 Announce Type: new Abstract: A recent breakthrough [Hirahara and Nanashima, STOC'2024] established that if $\mathsf{NP} \not \subseteq \mathsf{ioP/poly}$, the existence of zero-knowledge with negligible...
arXiv:2602.17653v1 Announce Type: new Abstract: Recent work has shown that language models (LMs) trained on synthetic corpora can exhibit typological preferences that resemble cross-linguistic regularities...
arXiv:2602.17654v1 Announce Type: new Abstract: We propose a two-stage "Mine and Refine" contrastive training framework for semantic text embeddings to enhance multi-category e-commerce search retrieval....
arXiv:2602.17655v1 Announce Type: new Abstract: Language Identification (LID) is an important component of many multilingual natural language processing pipelines, where it facilitates corpus curation, training...
arXiv:2602.17658v1 Announce Type: new Abstract: Reward modeling is a core component of modern alignment pipelines including RLHF and RLAIF, underpinning policy optimization methods including PPO...
arXiv:2602.17659v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to faithfully follow language....
arXiv:2602.17663v1 Announce Type: new Abstract: HIPE-2026 is a CLEF evaluation lab dedicated to person-place relation extraction from noisy, multilingual historical texts. Building on the HIPE-2020...
arXiv:2602.17664v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) incur high inference cost due to iterative denoising, motivating efficient pruning. Existing pruning heuristics largely inherited...
arXiv:2602.17665v1 Announce Type: new Abstract: Recent progress in multimodal reasoning has enabled agents that can interpret imagery, connect it with language, and perform structured analytical...
arXiv:2501.14380v3 Announce Type: cross Abstract: Quantum computers have advanced rapidly in qubit count and gate fidelity. However, large-scale fault-tolerant quantum computing still relies on quantum...
arXiv:2510.21549v1 Announce Type: cross Abstract: The distributed coloring problem is arguably one of the key problems studied in the area of distributed graph algorithms. The...
arXiv:2602.16737v1 Announce Type: cross Abstract: Accurate and timely identification of hospital outbreak clusters is crucial for preventing the spread of infections that have epidemic potential....