Found 24 document(s)
Page 1 of 2
-
Since the foundation of the People's Republic of China in 1949, supplementary education has been shaped by three very different paradigms. At the outset were Communist traditions in which China learned from the Soviet Un...
-
Computational metrics are widely used to prioritize enzyme designs for experimental testing, yet their ability to capture catalytic function remains poorly established. Here, we systematically evaluate 33 in-silico metri...
-
Vision-and-language navigation (VLN) relies on retaining and using relevant observations. Yet growing histories introduce redundancy, and retained information may remain underused. We introduce ReInsBench, a diagnostic b...
-
Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard PlanningAdapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly through text, losing its characters and art style, or ...
-
Energy-efficient deployment of large language models requires understanding how model architecture, hardware, and serving settings shape energy per generated token. We introduce the Token-Energy Law, a compact, interpret...
-
In this report, we introduce Sage-A1.5, a 35B Mixture-of-Experts agentic model that builds on A1 to advance long-horizon problem solving through adaptive capability composition. Compared with A1, Sage-A1.5 learns not onl...
-
Depth pruning removes entire transformer layers to make large language models faster, and recent methods recover quality by replacing the removed layers with a training-free linear map. Which layers to remove, however, i...
-
Recent advances in foundation-model agents have enabled increasingly capable embodied systems for long-horizon planning and interaction. However, embodied agents require fast, closed-loop decisions as they continuously p...
-
We present IQuest-Q1, a sparse Mixture-of-Experts (MoE) agentic foundation model with 320B total parameters (15B activated). IQuest-Q1 is developed through a three-stage process: (1) stable and efficient pre-training, co...
-
Frontend coding agents are usually graded on one question: did the requested target get built. Real engineering changes carry a second obligation, because the rest of the site has to keep working. We call that second obl...
-
4D scene reconstruction requires robust handling of dynamic objects, yet existing streaming methods commonly assume static scenes, leading to pose drift and ghosting artifacts over long sequences. We introduce Stream4D, ...
-
Generative recommendation with semantic IDs (SIDs) represents each item as a sequence of discrete tokens and autoregressively predicts the next item's SID. Despite strong recommendation performance, repeated decoding ove...
-
Vision Transformer (ViT) classifiers commonly rely on a global classification (CLS) token for image-level prediction, which is poorly aligned with local interpretability requirements in medical imaging. We propose SAP-Vi...