Supervised fine-tuning (SFT) adapts pretrained large language models (LLMs) to downstream tasks, but the required concep…
为什么值得关注：属于技术进展，可能扩散到其他领域
Adversarial games have driven advances from heuristic search to reinforcement learning, yet learning and adapting strate…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Anatomical continuity provides complementary information for medical image restoration, but its use requires accounting…
为什么值得关注：提供了新的研究结果
Accurate simulation of rigid-body interactions is essential for predictive physical world models.Despite recent progress…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Randomized controlled trials (RCTs) identify treatment effects without confounding but are often small, whereas observat…
为什么值得关注：属于技术进展，可能扩散到其他领域
Do LLM scientific agents rely only on their initial task context, or do they adapt their decisions in response to experi…
为什么值得关注：提供了新的研究结果
Large language model compliance systems are deployed on the assumption that a verdict depends on the regulatory rule it…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Learning and problem solving depend critically on the structure of internal representations.While many modern data-drive…
为什么值得关注：属于技术进展，可能扩散到其他领域
Understanding large language model (LLM) reasoning requires looking beyond behavioral performance to examine how reasoni…
为什么值得关注：属于技术进展，可能扩散到其他领域
Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosym…
为什么值得关注：属于技术进展，可能扩散到其他领域
Egocentric world models predict first-person observations conditioned on an agent's actions, but most focus on a single…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Machine learning (ML) in high-energy nuclear physics (HENP) is entering a new stage in which physical knowledge is incor…
为什么值得关注：为行业报告，可提供结构化数据
A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short wr…
为什么值得关注：属于技术进展，可能扩散到其他领域
Over 90% of disease-associated variants from genome-wide association studies fall in noncoding regulatory regions, yet t…
为什么值得关注：属于技术进展，可能扩散到其他领域
Multimodal large language models have made remarkable progress in bridging vision and language, facilitating various per…
为什么值得关注：属于技术进展，可能扩散到其他领域
Omnimodal embeddings naturally involve both shared representations and modality-specific features across heterogeneous i…
为什么值得关注：属于政府/政策信息，对教育或研究方向可能产生影响
Pretrained audio encoders are reused for downstream tasks that are often unknown when the encoder is trained, so their u…
为什么值得关注：属于技术进展，可能扩散到其他领域
We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning a…
为什么值得关注：提供了新的研究结果
Topological Deep Learning extends graph-based learning to higher-order domains, such as hypergraphs, cellular, and simpl…
为什么值得关注：属于技术进展，可能扩散到其他领域
Time-series foundation models (TSFMs) have achieved strong forecasting performance across domains.However, most adaptati…
为什么值得关注：属于技术进展，可能扩散到其他领域