arXiv:2602.18700v2 Announce Type: replace-cross
Abstract: LLM agents rely heavily on high-quality trajectory data to guide their problem-solving behaviors, yet producing such data requires substantial task design, high-capacity model generation, and m…
arXiv:2602.22480v2 Announce Type: replace
Abstract: An important emerging application of coding agents is agent optimization: the iterative improvement of a target agent through edit-execute-evaluate cycles. Despite its relevance, the community lacks …
arXiv:2605.01382v1 Announce Type: cross
Abstract: Analyzing human vasculature and vessel-like, tubular structures, such as airways, is crucial for disease diagnosis and treatment. Current methods often rely on small sub-regions or simplified tree-like…
arXiv:2605.01391v1 Announce Type: new
Abstract: Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity types, failing to captur…
arXiv:2605.01591v1 Announce Type: cross
Abstract: Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surrogate models, limitin…
arXiv:2411.03926v3 Announce Type: replace
Abstract: Federated learning (FL) is widely used in Internet-of-Things (IoT) systems, but its distributed training process also exposes it to backdoor attacks. Existing studies mainly consider single-target or…
arXiv:2604.16506v2 Announce Type: replace-cross
Abstract: Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple images rather than interpreting a single view. …
arXiv:2605.01450v1 Announce Type: new
Abstract: Recent frameworks like ToFu and TEMPEH provide an automated alternative to classical registration pipelines by predicting 3D meshes in dense semantic correspondence directly from calibrated multi-view im…
arXiv:2605.02037v1 Announce Type: cross
Abstract: We present VILAS, a fully low-cost, modular robotic manipulation platform designed to support end-to-end vision-language-action (VLA) policy learning and deployment on accessible hardware. The system i…
arXiv:2605.01365v1 Announce Type: cross
Abstract: Open-vocabulary 3D affordance detection requires localizing interaction regions on point clouds given novel affordance descriptions. Recent methods extend multimodal large language models (MLLMs) with …