Computer Science
Semantic caching defines answer reuse on embedding similarity: two utterances share a stored answer when a similarity score clears a threshold, with no notion of authorization, versioning, or of what makes two demands the same. This note…
Implicit neural representations (INRs) offer compact encoding of volumes, but as lossy approximators, inevitably have prediction errors. We consider INRs that can simultaneously encode relative error scales by predicting distributions using…
While autoregressive models optimize the exact data likelihood via the chain rule, diffusion models are typically trained with denoising objectives. We develop conservation laws based on generalized extrinsic information transfer (GEXIT)…
For an edge-weighted graph $G=(V,E)$ and a stretch parameter $t\geq 1$, a $t$-spanner is a subgraph $H\subseteq G$ such that the shortest path distances in $G$ and $H$ satisfy $\delta_H(u,v)\leq t\, \delta_G(u,v)$ for all $u,v\in V$. In…
Rapid technological change is reshaping society through emerging domains such as autonomous vehicles and smart manufacturing, creating new research challenges in system design, operation, security, and training. Researchers often rely on…
Agent systems based on large language models (LLMs) are increasingly deployed for autonomous tasks, yet existing evaluations mostly focus on task success rather than whether agents know when to abstain. This gap poses real risks: under…
We present SyncSpace, a system that achieves both spatial alignment and visual consistency between a generated 3DGS world and physical space. We first scan the space via depth sensing to extract 3D bounding boxes, which we render into a…
Every mainstream GPU is built compute-heavy and capacity-light: it pairs enormous arithmetic throughput with too little memory to hold a modern model. In contrast, large language model decoding requires little compute and a large amount of…
Teleoperating remotely operated vehicles (ROVs) in flooded, cluttered infrastructure is fundamentally limited by narrow 2D egocentric views and subsea communication latency. We present a multimodal teleoperation architecture built on a…
This report contains the proceedings of the 21st International Workshop on Termination (WST 2026), which was held in Lisbon on July 25. It was affiliated with the 13th International Joint Conference on Automated Reasoning (IJCAR 2026),…
Social intelligence, the ability to interpret others' emotions, beliefs, and intentions, is often assessed with the Reading the Mind in the Eyes Test (RMET), in which participants infer mental states from images of the eye region. Yet RMET…
Single-shot fringe projection profilometry (FPP) networks that regress depth directly can exploit a shape-prior shortcut, recovering depth from object boundaries rather than from fringe phase. On a photorealistic synthetic benchmark (15,600…
Reversible logic has long promised substantial reductions in energy dissipation, yet prior demonstrations have not scaled to commercially relevant systems. This work presents a quantitative framework for evaluating reversible logic through…
Constrained decoding is essential in generative retrieval, where document identifiers generated directly from a query must exactly match a predefined library of valid IDs. At scale, decoding is often constrained using a trie with beam…
We study a symbolic search space for the Collatz conjecture based on finite exponent codes of the accelerated map. Each code records the number of divisions by two after every 3n + 1 step and determines three quantities: real drift, a…
Collaborative decision-making is a fundamental capability in multi-robot systems, such as connected autonomous vehicles. However, perceptual noise and adversarial attacks in collaborators can severely affect decision reliability. Overall,…
Large language models (LLMs) store factual knowledge in their parameters. While recent work has shown that this knowledge resides in MLP layers, existing constructive and mechanistic interpretability models of fact-storage in LLMs fail to…
Endpoint devices remain a primary target for cyberattacks, yet commercial Endpoint Detection and Response (EDR) platforms are often too costly and operationally complex for small and resource-constrained organizations. This paper presents…
Understanding music requires understanding localized relationships across data modalities, e.g., how time in performance audio maps onto position in a score image. Yet supervision for such local correspondences is difficult to obtain-in…
Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden. To make those transitions visible, we…