Found 21 document(s)
Page 1 of 2
-
Transformer prefill reuses weights across tokens and is dominated by matrix multiplication and activation data movement; single-token decode has limited reuse and is dominated by weight and KV-cache reads. We present FUT...
-
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience for these capabilities requires coherent requests,...
-
Planning does not by itself imply the ability to recognise errors, but recognising errors can improve planning capacity. In this paper, we study this phenomenon in Transformer planning. To analyze the inner mechanism, we...
-
The magnetic ground states of rare-earth frustrated magnets can be governed by competing energy scales arising from crystal-field anisotropy, exchange interactions, and long-range dipolar interactions. Here we investigat...
-
Analogical reasoning is widely considered a fundamental component of human intelligence. Few benchmarks are designed to explicitly test far analogical reasoning - reasoning between domains that are superficially dissimil...
-
Long-horizon dialogue agents need to keep user memories stable enough for personalization while adapting when the user genuinely changes. Existing memory systems often append every observation or overwrite old entries by...
-
Long-term agent memory is shifting from predefined workflows toward learnable policies for memory construction and retrieval. Existing learning-based methods either optimize construction alone or combine retrieval-side o...
-
Large language model (LLM) agents are increasingly capable of supporting scientific workflows, but their capabilities across diverse research activities remain difficult to assess systematically. Existing benchmarks ofte...
-
Latent communication requires both an effective continuous reasoning process and an interface through which an external model can leverage its intermediate computation. We present J-Comm, a framework comprising two core ...
-
Objective: To develop a unified vision-language model for prompt-conditioned quantitative ultrasound measurement that addresses the mismatch between continuous measurement targets and discrete token-based numerical predi...
-
Existing Ultra-High-Definition (UHD) low-light image enhancement (LLIE) methods typically rely on either spatial- or frequency-domain modeling, or independently process different frequency components for efficient restor...
-
We present a generic actor-critic method that combines a ridge-regularized pathwise least-squares temporal-difference (LSTD) critic with importance-corrected momentum (ICM) actors. The critic solves a ridge-regularized s...
-
While movable antennas (MAs) provide enhanced spatial flexibility through dynamic repositioning, they confront critical challenges in acquiring complete channel state information (CSI) and efficiently optimizing antenna ...
-
Vision-language-action (VLA) policies can select among discrete candidates for pick-and-place manipulation or generate continuous action chunks for motion control. Improving both forms of decision making through a common...