research note
This paper addresses a core limitation in current large language model (LLM) agents augmented with external tools, namely the step-wise atomic tool call paradigm
research note
This paper addresses the challenge of effectively guiding robotic generalist policies—specifically flow matching vision-language-action models—toward semantically meaningful behaviors on novel or d…
research note
Influcoder addresses the computational inefficiencies of influence function-based Data Attribution (DA) methods for large language models (LLMs)
research note
This paper addresses the challenge of improving complex reasoning tasks in large language models by teaching them to reason by analogy rather than relying solely on parametric knowledge
research note
This paper addresses a foundational problem in end-to-end speech-to-speech translation (S2ST) — large-scale mined paired speech corpora, while abundant, are noisy and misaligned, degrading model qua…
research note
This paper addresses the challenge of mechanically characterizing soft hydrogels under extremely high strain rates induced by inertial cavitation events, where standard constant-parameter constitut…
research note
This paper addresses the challenging problem of dexterous manipulation of articulated tools with multi-fingered robotic hands
research note
This paper addresses the problem of secure multi-user integrated sensing and communication (ISAC) networks where untrusted sensing users (SUs) may eavesdrop on confidential information intended for…
research note
This paper investigates the conditions under which the curvature of planar d-webs on (\mathbb{C}^2,0) remains holomorphic along an invariant irreducible curve C
research note
This paper addresses a critical but understudied risk in search-augmented large language model (LLM) recommenders — susceptibility to polluted web content
research note
This paper addresses the challenge of detecting reasoning failures of large language models (LLMs) at inference time without relying on ground-truth labels
research note
This paper introduces operads, well-studied mathematical structures from algebraic topology and category theory, as a rigorous framework for modeling question decomposition in large language models…
