Computer Science
Computing Nash equilibrium policies in multi-agent Pursuit-Evasion games (PEG) is challenging due to the exponential growth of the joint state and action spaces with the number of agents. Existing approaches either rely on offline…
Engineering design intent is often communicated through rasterized orthographic drawings. However, downstream workflows inherently require editable and parametrically defined 3D computer-aided design (CAD) models. To bridge this gap, we…
We study batch verification in QMA query and communication complexity, where the goal is to understand how the resources needed to verify $m$ copies of a Boolean function $f$ depend on $m$. We give a general technique for proving lower…
Code comprehension and code review are already critically important software engineering tasks, and the rising use of AI code generation tools is only increasing that importance. Generative AI has the possibility of supporting these…
Behavioral alignment in large language models often masks fragile internal safety representations. Recent work suggests that refusal behavior is mediated by low-dimensional directions in activation space. This raises questions about how…
Indoor scene relighting demands photorealism, precise spatial control, and strict multi-view consistency. While diffusion-based image editing models enable semantic lighting manipulation via text prompts, enforcing exact 3D light placement…
Pretrained generative robot policies based on flow matching and diffusion have achieved impressive results across a wide range of manipulation tasks. Yet real-world deployments routinely expose failure modes outside the pretraining…
Cloud-based deep learning enables large-scale medical image analysis but raises significant privacy concerns when sensitive patient images are outsourced for model development. Image disguising has recently emerged as a promising…
Weak randomness has broken deployed cryptography through implementation bugs, boot entropy scarcity, and backdoored generators. Inexpensive wireless sensors concentrate the risk because many boot or operate in highly deterministic…
We present Clean2FX, a study and demo of label-conditioned clean-to-effect transformation for electric guitar audio. Given a clean guitar input and a target effect label, the task is to synthesize the corresponding effected signal while…
Visibility in media is pivotal for identity development and for broadening societal views of gender and sexuality. Queer representation has increased in recent years, yet damaging stereotypes and tropes persist. Here, we focus on queer…
Human egocentric video is a scalable supervision source for humanoid policy learning, but current pipelines struggle with hand-object occlusion, oversimplified motion, or specialized capture hardware. We introduce AgenticFocus, a Mixed…
In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space. In deep learning, this idea is known as the linear representation hypothesis and underpins many…
Despite rapid AI adoption in education, rigorous evaluation of AI-powered educational (AIED) systems remains critically underdeveloped, particularly in second language (L2) education, one of the most common yet least evaluated AI…
Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, many real-world settings violate this assumption, requiring…
Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original.…
Intent-based network management is the emerging paradigm for 6G service lifecycle automation, with the 3GPP intent management framework (TS~28.312) defining creation, translation, fulfilment, and assurance stages. Existing fulfilment and…
Recent advances in 3D Gaussian Splatting (3DGS) have enabled high-quality, render-ready scene representations for novel-view synthesis. However, most existing 3DGS pipelines rely on multi-view observations (or non-causal access to future…
Heterogeneous graph built on notes, lyric syllables, and accompaniment events is a natural representation of symbolic music score, providing a substrate for both philological analysis and computational tasks. Music features are therefore…
As 3D software proliferates, software artifacts now extend beyond code and 2D user interfaces to include 3D assets. Among these assets, collision meshes are critical as they define the geometry used by physics engines for collision…