Found 39 document(s)
Page 1 of 3
-
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...
-
As software agents increasingly generate and modify code, evaluating their ability to review changes and discover defects becomes important. Such evaluation needs executable project environments for investigation and rel...
-
Verifiable rewards have advanced reinforcement learning in mathematics and code. However, many valuable open-ended tasks share three properties: no automatic verifier of overall quality, multiple requirements to satisfy ...
-
Layer-level pruning is attractive for large language model (LLM) deployment as it reduces the model size while preserving a dense architecture that can be efficiently executed on standard hardware. Current methods typica...
-
Curriculum learning, which organizes training samples according to their learning priority, has been widely adopted in reinforcement learning to improve training efficiency. However, existing methods commonly construct c...
-
Dynamic object manipulation requires robots to anticipate target motion while replanning fast enough to avoid executing outdated actions. Existing approaches either rely on fast reactive control without an explicit futur...
-
Robotic manipulation is not merely observation-to-action generation, but the realization of task-specified state changes in the physical world. Existing vision-language-action (VLA) methods directly learn observation-to-...
-
Automated Gleason grading of prostate whole slide images (WSIs) enables faster and more consistent cancer risk stratification. However, it remains a challenging task due to the subtle morphological differences between gr...
-
Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spatial question answering offers limited evidence of...
-
The Reinforcement Learning (RL) paradigm has achieved remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). However, when applied to long-horizon tasks, it faces severe challenges: i...
-
World models help agents assess the consequences of their actions before acting. Many real systems, however, involve multiple actors who make their own decisions, can evolve even when the agent takes no action, and are o...
-
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...
-
Large language models (LLMs) can translate natural-language optimization problems into solver programs, but reliably producing correct formulations and implementations remains challenging. Existing approaches improve opt...
-
The performance of medical image segmentation depends on a large amount of annotated data, and most segmentation models experience a significant drop in performance in low-sample-size scenarios. Existing semi-supervised ...
-
Large language models serve applications with diverse inference budgets, but training and maintaining separate models for each budget incurs substantial costs. Recent Looped Transformers enable flexible inference computa...