We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty o…
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 how actions change scene geometry can provide complementary supervision for goal-directed manipulation.We intro…
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
Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bo…
为什么值得关注：属于技术进展，可能扩散到其他领域
Very-high-resolution Earth-observation satellites acquire more data than they can store and downlink, while in maritime…
为什么值得关注：属于技术进展，可能扩散到其他领域
Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensiv…
为什么值得关注：属于技术进展，可能扩散到其他领域
Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, wit…
为什么值得关注：提供了新的研究结果
In text-guided image editing, describing the desired change is often straightforward, but identifying the intended objec…
为什么值得关注：属于技术进展，可能扩散到其他领域
Text prompting is an indirect interface for poster generation, requiring users to encode inherently two-dimensional comp…
为什么值得关注：属于技术进展，可能扩散到其他领域
Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move fr…
为什么值得关注：属于技术进展，可能扩散到其他领域
RNA function arises from the coupling of nucleotide sequence and three-dimensional structure, motivating their joint des…
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
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
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
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
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
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
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
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
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
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