Found 3,529 document(s)
Page 3 of 236
-
Generative AI workflows execute user tasks by composing sequences of LLM calls, where each call performs a sub-task (e.g., summarization or translation), forming a workflow. Executing such workflows requires decisions ov...
-
We present Stable Signer V3, an interactive high-resolution sign language avatar system built on 4D Deformable Primitive Splatting. It addresses three limitations of existing avatars: restricted facial expression, inaccu...
-
Safely overseeing AI is increasingly challenging for the humans doing it, as they must evaluate longer and more complex outputs with every new model generation. To mitigate this challenge, we could leverage complementari...
-
An AI agent can reproduce the distribution of its messages and of the receiver's task outcomes while disclosing private information that the task never required. We ask what a passive audit can certify when the auditor k...
-
Skill-augmented agentic RL has emerged as an effective approach to improving LLM agents on long-horizon tasks. Despite this progress, individual skills may follow distinct trajectories as the policy evolves, with some be...
-
Catastrophic forgetting in sequential deep learning arises from a fixed-capacity architectural constraint: parameter updates encoding new tasks perturb weight subspaces supporting prior representations. We introduce the ...
-
Pore-water pressure changes the effective stress and deformation of saturated geomaterials, while skeleton deformation generates pressure and drives drainage. Resolving this feedback together with hydraulic boundary cond...
-
Answering natural language questions over knowledge graph data is challenging due to the vast number of facts, which can be difficult to process and navigate. One potential solution for this issue is to use mined subgrap...
-
Multi-head attention is a central component of the transformer architecture, yet how its expressivity depends on the number of heads remains poorly understood. We study a one-layer, attention-only transformer with additi...
-
Reinforcement learning (RL) is increasingly proposed as a fast solver for unit commitment (UC), but standalone agents remain far more expensive than mixed-integer linear programming (MILP). In the first study of RL on th...
-
System One models, introduced with TypeSafe's Jev, answer typed questions about a state with calibrated probabilities instead of generated text: choosing among options described in natural language (Choice), placing the ...
-
We present a simulation framework for Euclid galaxy clustering measurements that reproduces the essential behaviour of the spectroscopic reduction chain, bypassing the computation required by full pixel-level simulations...
-
The (111) orientation of SrTiO$_3$ (STO)-based heterostructures has emerged as a versatile platform for two-dimensional electron gases (2DEGs), yet the influence of STO's polar ferroelastic domain-wall (DW) network on ch...
-
Building capable language models for India requires scalable multilingual data and robust evaluation. We introduce Nemotron-Pretraining-Indic-v1, a synthetic pretraining corpus of approximately 2.83 trillion tokens cover...
-
Single-photon avalanche diode (SPAD) arrays offer photon-level sensitivity for sensing in optical integrated sensing and communication (O-ISAC). However, after each detection, a SPAD is blind for a dead time, which satur...