Computer Science
The rapid growth of social media has created vast amounts of political discourse, which provides valuable opportunities to analyze public opinions and identify different political perspectives. Sentiment Analysis (SA) is a core task in…
While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains comparatively less explored. We introduce V-FiLLM, a framework that generates financial…
ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals. Starting…
Hierarchical Text Classification (HTC), as a critical text mining task, faces challenges such as complex label hierarchies and class imbalance. Existing methods based on large language models (LLMs) struggle to be efficiently applied to…
We study the graphic $s$-$t$ path TSP on subcubic graphs (maximum degree 3): given two vertices $s,t$, find a shortest walk from $s$ to $t$ that visits every vertex. Our main result is that the optimal $5/4$ coefficient is attained for…
AI-assisted facial phenotyping supports rare genetic disorder prioritization by retrieving visually similar diagnosed cases from facial image reference databases such as the GestaltMatcher Database (GMDB). Existing GestaltMatcher-based…
Although Whisper models benefit from large-scale multilingual pre-training, their performance on Burmese medical speech remains limited. This work presents a Burmese medical speech recognition framework built on a high-quality 28-hour…
In LLM pre-training, synchronization propagates rank-local stalls, slowdowns, and numerical errors into job-wide symptoms, obscuring their origin. Existing diagnosis often relies on in-process monitors that cannot report after the trainer…
Feature-attribution methods such as SHAP provide useful evidence about individual model predictions, but their numerical outputs are rarely sufficient for audiences with different expertise, goals, and risks of misinterpretation. In medical…
Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex structure of patent documents, dense technical terminology, and multi-modal information,…
Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations. We characterize the output behavior of 32 models from six families using their…
Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired…
Attribute hallucination---where vision-language models (VLMs) correctly identify an object but mischaracterize its properties---is prevalent yet mechanistically poorly understood. The dominant explanation, language-prior dominance, has…
Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their context, parameters, limitations, and intended use. However, these practices remain focused…
We systematically investigate finite-difference (FD) derivative computation in Physics-Informed Neural Networks (PINNs) as an alternative to automatic differentiation (AD). On three benchmark PDEs we show that, with a properly calibrated…
Modeling spatiotemporal dynamical systems governed by partial differential equations (PDEs) poses two major challenges: it either requires expensive physics-based simulators that entail iterative numerical solving at high computational…
Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and…
We introduce Sona, a single-model generative recommender for Yandex Music. In an online A/B test, Sona replaced the entire production cascade, comprising more than 15 candidate generators followed by pre-ranking and ranking models that…
Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, leading to a cross-modal gap between the training (text-only) and the inference…
Political stance detection in LLMs has long been dominated by closed-ended, multiple-choice political survey questions---originally designed for humans, and thus lacks the realism and nuance of human-AI interactions in the wild, while also…