arXiv preprints from January 1, 2026 through September 26, 2026 — 10:17:08 EST
Neural network pruning remains essential for deploying deep learning models on resource-constrained devices, yet existing approaches primarily target parameter reduction without directly controlling computational cost. This yields unpredictable inference latency in deployment scenarios where strict Multiply-Accumulate (MAC) operation...
Causality underpins all logical reasoning. However, the causal structure in quantum processes can be far from intuitive, often differing from its classical counterpart in relativity, which is defined by the light cone. In particular, in systems with measurement and post-selection, causal influence can occur between spacelike separated...
Traditional side-channels take advantage of secrets being used as inputs to unsafe instructions, used for memory accesses, or used in control flow decisions. Constant-time programming, which restricts such code patterns, has been widely adopted as a defense against these vulnerabilities. However, new hardware optimizations in the form...
Autoregressive language models are next-token predictors and have been criticized for only optimizing surface plausibility (i.e., local coherence) rather than maintaining correct latent-state representations (i.e., global coherence). Because Theory of Mind (ToM) tasks crucially depend on reasoning about latent mental states of oneself...
Enterprise-scale knowledge management faces significant challenges in integrating multi-source heterogeneous data and enabling effective semantic reasoning. Traditional knowledge graphs often struggle with implicit relationship discovery and lack sufficient semantic understanding for complex question answering. To address these...
Predicting non-covalent host-guest recognition remains challenging due to the complex interplay of electrostatics, dispersion, and steric effects, and the limited transferability of existing docking approaches to synthetic supramolecular systems. Here we present DeepHostGuest, a geometric deep-learning framework that learns...
We develop a topological approach to prove the generalized Lax conjecture using the fact that determinants of sufficiently big symmetric linear pencils are able to express the rigidly convex sets of RZ polynomials of any degree $d$. Monicity of the representation is assessed through a topological argument that allows us to perturbate...
We study the problem of scheduling delay-sensitive jobs over spot and on-demand cloud instances to minimize average cost while meeting an average delay constraint. Jobs arrive as a general stochastic process, and incur different costs based on the instance type. This work provides the first analytical treatment of this problem using...
This study proposes an algorithm titled a statistical firefly algorithm (SFA) for truss topology optimization. In the proposed algorithm, historical results of fireflies' motions are used in hypothesis testing to limit the motions of fireflies that are suggested by current information exchanges between fireflies only to those that are...
We recast spinful superconductivity as a \textit{quaternion field theory}, where a quaternion is a four-component hypercomplex number with units $(\boldsymbol{e}_x,\boldsymbol{e}_y,\boldsymbol{e}_z)$, that encodes the spin-singlet/triplet gap in a single field $q(\mathbf{k})$. This yields a compact Bogoliubov-de Gennes (BdG)...
Vision-Language Models (VLMs) integrate visual and textual knowledge into unified representations that increasingly underpin modern retrieval and recommendation systems. However, it remains unclear how reliably these models utilize their cross-modal knowledge when ranking multimodal items, and whether their knowledge grounding can be...
Recent progress in large language models (LLMs) has improved code generation, but most evaluations still test isolated, small-scale code (e.g., a single function) under default or unspecified software environments. As a result, it is unclear whether LLMs can reliably generate executable code tailored to a user's specific environment....
Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this paper, we develop a learning-based framework, namely DALD-PCAC that leverages Levels of Detail (LoD) to...
Document understanding (VRDU) in regulated domains is particularly challenging, since scanned documents often contain sensitive, evolving, and domain specific knowledge. This leads to two major challenges: the lack of manual annotations for model adaptation and the difficulty for pretrained models to stay up-to-date with...
Building upon FutureX, which established a live benchmark for general-purpose future prediction, this report introduces FutureX-Pro, including FutureX-Finance, FutureX-Retail, FutureX-PublicHealth, FutureX-NaturalDisaster, and FutureX-Search. These together form a specialized framework extending agentic future prediction to high-value...
A major goal of computational neuroscience has been to explain how the primate ventral visual stream (VVS) transforms visual input into temporally evolving neural representations that support robust visual perception. Historically, most modeling efforts have assumed static conditions: monkeys fixate a dot, images are briefly flashed,...
Conventional imaging requires a line of sight to create accurate visual representations of a scene. In certain circumstances, however, obtaining a suitable line of sight may be impractical, dangerous, or even impossible. Non-line-of-sight (NLOS) imaging addresses this challenge by reconstructing the scene from indirect measurements....
Large language models (LLMs) have demonstrated their instruction-following capabilities and achieved powerful performance on various tasks. Inspired by their success, recent works in the molecular domain have led to the development of large molecular language models (LMLMs) that integrate 1D molecular strings or 2D molecular graphs...
The disjoint amalgamation property (DAP), which asserts that all spans of a class of models can be amalgamated with minimal intersection, is an important property in the context of abstract elementary classes, with connections to both Grossberg's question and Shelah's categoricity conjecture. We prove that, in a nice AEC $\mathbf{K}$...
The primordial 7Li abundance predicted by standard Big Bang Nucleosynthesis (BBN) exceeds that inferred from old, metal-poor stars by a factor of about 3-4. In standard BBN, most primordial 7Li is produced as 7Be in the early Universe and later converted by electron capture. Additional production or destruction channels of 7Be, such...
Ultrasound vortices have rapidly expanded their applications to areas like particle trapping, contactless manipulation, acoustic communications. In ultrasonic imaging and therapy involving bone tissues, these vortex beams offer intriguing possibilities but transmitting them through bone (especially the skull) poses challenges....
Audio-visual speech recognition (AVSR) typically improves recognition accuracy in noisy environments by integrating noise-immune visual cues with audio signals. Nevertheless, high-noise audio inputs are prone to introducing adverse interference into the feature fusion process. To mitigate this, recent AVSR methods often adopt...
We present a pedagogical analysis of a fully connected three-state Markov process, focusing on the validity and limitations of the continuous-time approximation to discrete-time dynamics. While the correspondence between a discrete-time transition matrix and a continuous-time generator is often introduced formally, the conditions...
Cross-chain bridges constitute the single largest vector of systemic risk in Decentralized Finance (DeFi), accounting for over \$2.8 billion in losses since 2021. The fundamental vulnerability lies in the binary nature of existing bridge security models: a bridge is either fully operational or catastrophically compromised, with no...
Reliable flow measurements are essential in many industries, but current instruments often fail to accurately estimate multiphase flows, which are frequently encountered in real-world operations. Combining machine learning (ML) algorithms with accurate single-phase flowmeters has therefore received extensive research attention in...