Computer Science
Temporal graph questions require reliable handling of time, identifiers, and arithmetic. Large language model (LLM) agents often fail on these tasks, especially when a graph records both ordinary evolution and later corrections. We present…
Bilevel optimization underpins many machine learning applications, including hyperparameter optimization, meta-learning, neural architecture search, and reinforcement learning. While hypergradient-based methods have advanced significantly,…
This paper presents gradient-enhanced non-dominated sorting genetic algorithm II (G-NSGA-II) to address the challenges of local optima and solution non-uniqueness in the complex permittivity extraction problem for the first time. This…
Customer churn is a major challenge for telecommunication companies, directly eroding revenue and long term customer relationships. Traditional retention programs rely on generic, not personalized incentives and lack the precision to…
Formal verification of highly optimized arithmetic circuits at the gate-level remains a significant challenge due to the state space explosion problem. Although Symbolic Computer Algebra (SCA) offers a scalable theoretical foundation by…
This paper investigates how language similarity can improve cross-lingual transfer for automatic speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australian Aboriginal language, has very limited transcribed speech…
Min-wise hashing and its (k)-min-wise variant are standard tools in similarity estimation, sampling, sketching, and streaming. A (k)-min-wise family requires every prescribed (r)-subset of a fixed set, for (r\le k), to appear as the (r)…
Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model…
As large language models (LLMs) are increasingly used in decision support, it is important to understand whether their choices under uncertainty exhibit stable and interpretable behavioural regularities. Human decision-making combines…
Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a…
Despite advances in Emotional Intelligence (EI), Large Language Models (LLMs) still significantly underperform humans in complex emotional reasoning. This gap originates partly from the limited incorporation of individual differences,…
State Space Models (SSMs) have emerged as a powerful paradigm for efficient long-sequence modeling, offering parallel training and fast linear-time recurrent inference. However, like other recurrent architectures, SSMs must compress an…
At the limit of handling, a stabilizing MPC depends on the yaw-rate reference it tracks and the stable-handling envelope it enforces, both operating-point-dependent and unknown a priori, so fixed or worst-case settings are either too…
Short-answer VQA benchmarks conflate two distinct quantities: whether a model's answer is semantically correct, and whether that answer matches the surface form expected by the automatic evaluator. We study this conflation across six…
Apple Music serves listeners across 150+ storefronts in dozens of languages, with a catalog that grows by hundreds of thousands of new tracks daily. At this scale, search recall on misspelled, transliterated, and cross-lingual queries…
Video emotion analysis is typically framed as a static classification problem, treating each clip as an independent labeled unit. However, such a formulation overlooks a key psychological fact: emotions change as a result of cumulative…
Open-vocabulary 3D scene understanding is commonly achieved by embedding 2D vision-language features such as CLIP into a 3D Gaussian Splatting scene, turning it into a text-queryable semantic field. However, attaching a high-dimensional…
We explore a torus polynomial approximation based approach towards a long-standing question: whether $AND$ can be computed by $CC^0$ circuits - the class of constant-depth polynomial size circuits containing $MOD_m$ gates for some $m$.…
Previous work in group recommender systems has demonstrated a sensitivity to the distribution of preferences within a group. Specifically, the selection of the preference aggregation strategy benefits from considering such group…
Melody skeleton extraction aims to derive a shorter melody that preserves structural notes while removing ornaments. Prior methods rely on hand-crafted reduction rules or note-wise salience classifiers trained with heuristically or…