Computer Science
Unified multimodal models (UMMs) with interleaved reasoning, which generate both textual and visual steps as part of intermediate reasoning traces, have demonstrated great potential for visual mathematical reasoning tasks. However, we…
Self-supervised learning for symbolic music has advanced largely through token-level pretraining, but such representations remain tied to tokenizer-specific sequences and often provide time-span-level embeddings only indirectly. In this…
We present the design of a language extension that allows the use of ellipses ("...") in patterns and expressions, which facilitates function definitions on lists that are more succinct and direct than the standard recursive ones. The…
We present PinFT, a miniature five-axis capacitive force/torque sensor designed for direct tip-level integration into tweezer-like tools. The sensor employs a compact three-PCB stack with segmented plated through-hole electrodes and a…
We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved. Using a six-category failure taxonomy validated by two independent human annotators (Cohen's $\kappa$ =…
Macrocyclic peptides are an increasingly important therapeutic modality, but existing computational methods for modeling their structures and properties are limited in scope and do not generalize well across the synthetically accessible…
Automated failure attribution uses LLMs to identify where and why agentic systems fail. As agents become more capable, their failures become subtler, making automated attribution increasingly important. We introduce Who&When Pro, a…
Adversarial team games (ATGs) with asymmetric information, such as adversarial path-finding, goal search, and reachability games on graphs, require strategies that are robust to hidden opponent types, such as a hidden goal flag, and to…
Modern ML serving increasingly lets learned, unbounded components (routers, latency-SLO admitters, admit ladders) decide a tenant's quality of service; when one is wrong, the assured SLO can silently break, and the Kubernetes layers beneath…
Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such as trending topics, breaking news, cultural events, and cross-surface user…
Object pose estimation is a fundamental problem in 3D vision. Although recent state-of-the-art approaches achieve strong performance, they often overfit to existing benchmarks and exhibit limited generalization to novel categories and…
We describe details of a formal framework to study the interaction between traffic policers, implemented using phantom queues or token buckets, and any arbitrary congestion control algorithm (CCA). This framework allows network providers to…
We consider covering and partitioning a simple polygon into pieces which either have unit geodesic radius or unit geodesic diameter, using the $\ell_2$-metric for distances. There is no known method for finding an exact solution to these…
Electronic health record (EHR) data are inherently multimodal, and leveraging multiple modalities can improve predictive performance. However, most existing approaches rely on deep fusion, which obscures how individual modalities contribute…
Static analysis is widely used for finding security weaknesses in source code before deployment, but it often produces far more alerts than analysts can review. We study how well large language models (LLMs) can adjudicate (classify as a…
Industrial sound design requires audio generation systems that not only produce realistic audio, but also preserve the perceptual identity of a reference, support controllable variation, and remain efficient for practical workflows.…
Archive-based exploration methods such as Go-Explore select which visited state to return to using visitation rarity, and frontier methods return to the boundary of the unknown; neither asks whether the unexplored region behind a boundary…
Voice phishing (vishing) attacks have traditionally been limited by the need for human operators. The rapid emergence of high-quality AI voice synthesis and large language models (LLMs) reduces this bottleneck and enables scalable,…
State estimation is essential for quadruped robots, enabling robust locomotion, navigation, and control. While many estimators have been proposed in the literature, existing implementations are often tied to specific robots or software…
Many neural networks operations have a multiplicative nature rather than additive: halving or doubling a norm are analogous relatively but require unequal optimization distances when taking linear steps. Adaptive optimizers such as Adam…