arXiv:2604.18712v1 Announce Type: new
Abstract: Probing has shown that language model representations encode rich linguistic information, but it remains unclear whether they also capture cognitive signals about human processing. In this work, we probe…
arXiv:2604.19342v1 Announce Type: new
Abstract: Generative AI-powered by Large Language Models (LLMs)-is increasingly deployed in industry across healthcare decision support, financial analytics, enterprise retrieval, and conversational automation, wh…
arXiv:2604.19105v1 Announce Type: new
Abstract: Faithfully modeling human behavior in dynamic environments is a foundational challenge for embodied intelligence. While conditional motion synthesis has achieved significant advances, egocentric motion g…
arXiv:2604.19351v1 Announce Type: new
Abstract: The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression me…
arXiv:2511.01233v3 Announce Type: replace
Abstract: We review human evaluation practices in automatic, speech-driven 3D gesture generation and find a lack of standardisation and frequent use of flawed experimental setups. This leads to a situation whe…
arXiv:2604.19262v1 Announce Type: cross
Abstract: Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prioritize generic langua…
arXiv:2604.19394v1 Announce Type: new
Abstract: This paper narrows the performance gap between small, specialized models and significantly larger general-purpose models through domain adaptation via continual pre-training and merging. We address the s…
arXiv:2604.19292v1 Announce Type: cross
Abstract: Multilingual large language models (LLMs) have minimized the fluency gap between languages. This advancement, however, exposes models to the risk of biased behavior, as knowledge and norms may propagat…
arXiv:2604.19133v1 Announce Type: new
Abstract: Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning between air and water. To address this, we introduce …
arXiv:2604.19405v1 Announce Type: new
Abstract: Automatic evaluators such as reward models play a central role in the alignment and evaluation of large vision-language models (LVLMs). Despite their growing importance, these evaluators are almost exclu…