arXiv preprints from January 1, 2026 through September 23, 2026 — 14:26:13 EST
Fine-grained sparsity promises higher parametric capacity without proportional per-token compute, but often suffers from training instability, load balancing, and communication overhead. We introduce STEM (Scaling Transformers with Embedding Modules), a static, token-indexed approach that replaces the FFN up-projection with a...
In this paper, we find that the generation of 3D human motions and 2D human videos is intrinsically coupled. 3D motions provide the structural prior for plausibility and consistency in videos, while pre-trained video models offer strong generalization capabilities for motions. Based on this, we present CoMoVi, a co-generative...
We introduce a new extrinsic discretization of tangent vector fields on triangle meshes that is continuous, with bounded derivatives that are continuous almost everywhere, supporting pointwise evaluation and integration of differential operators. We achieve this by building a continuous normal field over the mesh via Phong...
Coded computing has emerged as a key framework for addressing the impact of stragglers in distributed computation. While polynomial functions often admit exact recovery under existing coded computing schemes, non-polynomial functions require approximate reconstruction from a finite number of evaluations, posing significant challenges....
Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from them, or do not disclose their training data or recipe. As a result, the open-source community lacks the foundations needed to improve on the...
Addressing itinerary modification is crucial for enhancing the travel experience as it is a frequent requirement during traveling. However, existing research mainly focuses on fixed itinerary planning, leaving modification underexplored due to the scarcity of need-to-modify itinerary data. To bridge this gap, we formally define the...
Talking head generation is increasingly important in virtual reality (VR), especially for social scenarios involving multi-turn conversation. Existing approaches face notable limitations: mesh-based 3D methods can model dual-person dialogue but lack realistic textures, while large-model-based 2D methods produce natural appearances but...
Network slicing is an architectural enabling technology that logically decouples the current cellular networks into infrastructure providers (InPs) and Network Slice Tenants (NSTs). The network resources (e.g., radio access resources at each cell) are owned by the InP, and are shared by the NSTs to provide a service to their mobile...
We present a pseudocode algorithm for translating our (Elementary) Mathematical Data Model schemes into relational ones and associated sets of non-relational constraints, used by MatBase, our intelligent data and knowledge base management system prototype. We prove that this algorithm is very fast, solid, complete, and optimal. We...
This work establishes the fundamental limits of the classical problem of multi-user distributed computing of linearly separable functions. In particular, we consider a distributed computing setting involving $L$ users, each requesting a linearly separable function over $K$ basis subfunctions from a master node, who is assisted by $N$...
In the context of multi-agent multi-armed bandits (MA-MAB), fairness is often reduced to outcomes: maximizing welfare, reducing inequality, or balancing utilities. However, evidence in psychology, economics, and Rawlsian theory suggests that fairness is also about process and who gets a say in the decisions being made. We introduce a...
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which these agents act. Even the most sophisticated methods of alignment, such as Reinforcement...
This paper explores a new opportunity to improve the performance of transaction processing at the application side by merging structurely similar statements or transactions. Concretely, we re-write transactions to 1) merge similar statements using specific SQL semantics; 2) eliminate redundant reads; and 3) merge contending statements...
Inferring physical actions from visual observations is a fundamental capability for advancing machine intelligence in the physical world. Achieving this requires large-scale, open-vocabulary video action datasets that span broad domains. We introduce Action100M, a large-scale dataset constructed from 1.2M Internet instructional videos...
Time Series Foundation Models (TSFMs) have emerged as a promising approach for zero-shot financial forecasting, demonstrating strong transferability and data efficiency gains. However, their adoption in financial applications is hindered by fundamental limitations in uncertainty quantification: current approaches either rely on...
Large Language Models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial ``jailbreak'' attacks designed to bypass safety guardrails. Current safety alignment methods depend heavily on static external red teaming, utilizing fixed defense prompts or pre-collected adversarial datasets. This leads to a rigid...
The paper introduces a white-box attack on computer vision models using SHAP values. It demonstrates how adversarial evasion attacks can compromise the performance of deep learning models by reducing output confidence or inducing misclassifications. Such attacks are particularly insidious as they can deceive the perception of an...
Combinatorial optimization augmented machine learning (COAML) has recently emerged as a powerful paradigm for integrating predictive models with combinatorial decision-making. By embedding combinatorial optimization oracles into learning pipelines, COAML enables the construction of policies that are both data-driven and...
Deploying Python-based AI agents on resource-constrained edge devices presents a critical runtime optimization challenge: high thread counts are needed to mask I/O latency, yet Python's Global Interpreter Lock (GIL) serializes execution. We demonstrate that naive thread pool scaling causes a "saturation cliff": a performance...
Comprehending genomic information is essential for biomedical research, yet extracting data from complex distributed databases remains challenging. Large language models (LLMs) offer potential for genomic Question Answering (QA) but face limitations due to restricted access to domain-specific databases. GeneGPT is the current...
Intrinsic evaluation metrics for conditional language models, such as perplexity or bits-per-character, are widely used in both mono- and multilingual settings. These metrics are rather straightforward to use and compare in monolingual setups, but rest on a number of assumptions in multilingual setups. One such assumption is that...
Instantaneous noise-based logic (INBL) is a novel computing approach that encodes binary information using stochastic processes. It uses 2M orthogonal stochastic reference noises for M noise-bits to construct an exponentially large Hilbert space (hyperspace) of dimension 2^M. INBL offers a classical alternative to quantum-style...
Image segmentation plays a central role in computer vision. However, widely used evaluation metrics, whether pixel-wise, region-based, or boundary-focused, often struggle to capture the structural and topological coherence of a segmentation. In many practical scenarios, such as medical imaging or object delineation, small inaccuracies...
Modeling wireless channels accurately remains a challenge due to environmental variations and signal uncertainties. Recent neural networks can learn radio frequency~(RF) signal propagation patterns, but they process each voxel on the ray independently, without considering global context or environmental factors. Our paper presents a...
Large language models have achieved remarkable capabilities across domains, yet mechanisms underlying sophisticated reasoning remain elusive. Recent reasoning models outperform comparable instruction-tuned models on complex cognitive tasks, attributed to extended computation through longer chains of thought. Here we show that enhanced...