Stay updated with the latest research and technology news
arXiv:2601.22341v1 Announce Type: new Abstract: We study the discrete constrained saddle dynamics and their momentum variants for locating saddle points on manifolds. Under the assumption...
arXiv:2601.22344v1 Announce Type: new Abstract: The low-rank approximation properties of Randomly Pivoted LU (RPLU), a variant of Gaussian elimination where pivots are sampled proportional to...
arXiv:2601.22345v1 Announce Type: new Abstract: We evaluate language models on their ability to explore interactive environments under a limited interaction budget. We introduce three parametric...
arXiv:2601.22346v1 Announce Type: new Abstract: We propose a deep neural network-based solution to the problem of allocating indivisible goods under additive subjective valuations without monetary...
arXiv:2601.22347v1 Announce Type: new Abstract: Recent post-training quantization (PTQ) methods have adopted block rotations to diffuse outliers prior to rounding. While this reduces the overhead...
arXiv:2601.22349v1 Announce Type: new Abstract: Many practical samplers rely on time-dependent drifts -- often induced by annealing or tempering schedules -- to improve exploration and...
arXiv:2601.22350v1 Announce Type: new Abstract: Given a Markov decision process (MDP), we seek to learn representations for a range of policies to facilitate behavior steering...
arXiv:2601.22352v1 Announce Type: new Abstract: Language model agents often appear capable of self-recovery after failing tool call executions, yet this behavior lacks a formal explanation....
arXiv:2601.22355v1 Announce Type: new Abstract: We study the problem of quantifying how far an empirical distribution deviates from Gaussianity under the framework of optimal transport....
arXiv:2601.22356v1 Announce Type: new Abstract: Safe learning is essential for deploying learningbased controllers in safety-critical robotic systems, yet existing approaches often enforce multiple safety constraints...
arXiv:2601.22357v1 Announce Type: new Abstract: Being polite is free - or is it? In this paper, we quantify the energy cost of seemingly innocuous messages...
arXiv:2601.22358v1 Announce Type: new Abstract: Movable signals have emerged as a third approach to enable smart radio environments (SREs), complementing reconfigurable intelligent surfaces (RISs) and...
arXiv:2601.22359v1 Announce Type: new Abstract: Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data....
arXiv:2601.22361v1 Announce Type: new Abstract: Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial progress in...
arXiv:2601.22362v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in production, contributing towards shifting the burden in terms of computational resources and...
arXiv:2601.22364v1 Announce Type: new Abstract: Large Language Models (LLMs) have been shown to organize the representations of input sequences into straighter neural trajectories in their...
arXiv:2601.22365v1 Announce Type: new Abstract: The Gilbert-Pollak Conjecture \citep{gilbert1968steiner}, also known as the Steiner Ratio Conjecture, states that for any finite point set in the...
arXiv:2601.22369v1 Announce Type: new Abstract: Provably correct distributed protocols, which are a critical component of modern distributed systems, are highly challenging to design and have...
arXiv:2601.22371v1 Announce Type: new Abstract: Multi-fidelity (MF) regression often operates in regimes of extreme data imbalance, where the commonly-used Gaussian-process (GP) surrogates struggle with cubic...
arXiv:2601.22373v1 Announce Type: new Abstract: Large language models used for clinical abstraction are sensitive to prompt wording, yet most work treats prompts as fixed and...
arXiv:2601.22376v1 Announce Type: new Abstract: High-definition (HD) maps provide essential semantic information of road structures for autonomous driving systems, yet current HD map construction methods...
arXiv:2601.22379v1 Announce Type: new Abstract: Block-wise sparse attention offers significant efficiency gains for long-context modeling, yet existing methods often suffer from low selection fidelity and...
arXiv:2601.22381v1 Announce Type: new Abstract: Robotic objects are simple actuated systems that subtly blend into human environments. We design and introduce Lantern, a minimalist robotic...
arXiv:2601.22382v1 Announce Type: new Abstract: Many key challenges in biological design-such as small-molecule drug discovery, antimicrobial peptide development, and protein engineering-can be framed as black-box...