arXiv preprints from January 1, 2026 through September 14, 2026 — 05:31:55 EST
Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a single general-purpose model typically requires scaling to sizes that are prohibitively expensive to train and deploy. On the other hand, while smaller domain-specialized models are much more...
Modern AI technologies enable autonomous vehicles to perceive complex scenes, predict human behavior, and make real-time driving decisions. However, these data-driven components often operate as black boxes, lacking interpretability and rigorous safety guarantees. Autonomous vehicles operate in dynamic, mixed-traffic environments...
In this paper, we explore new connections between the cycles in the graph of low-density parity-check (LDPC) codes and the eigenvalues of the corresponding adjacency matrix. The resulting observations are used to derive fast, simple, recursive formulas for the number of cycles $N_{2k}$ of length $2k$, $k<g$, in a bi-regular graph of...
In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing multi-modal tasks with high accuracy, are also severely susceptible to carefully launched security...
Binary Neural Networks (BNNs), where weights and activations are constrained to binary values (+1, -1), are a highly efficient alternative to traditional neural networks. Unfortunately, typical BNNs, while binarizing linear layers (matrix-vector multiplication), still implement other network layers (batch normalization, softmax,...
Designing intuitive interfaces for robotic control remains a central challenge in enabling effective human-robot interaction, particularly in assistive care settings. Eye gaze offers a fast, non-intrusive, and intent-rich input modality, making it an attractive channel for conveying user goals. In this work, we present GAMMA (Gaze...
Protein-protein interaction (PPI) represents a central challenge within the biology field, and accurately predicting the consequences of mutations in this context is crucial for drug design and protein engineering. Deep learning (DL) has shown promise in forecasting the effects of such mutations, but is hindered by two primary...
Background: Cyber-attacks have evolved rapidly in recent years, many individuals and business owners have been affected by cyber-attacks in various ways. Cyber-attacks include various threats such as ransomware, malware, phishing, and Denial of Service (DoS)-related attacks. Challenges: Traditional models such as Generative Artificial...
Predicting enzyme-substrate interactions has long been a fundamental problem in biochemistry and metabolic engineering. While existing methods could leverage databases of expert-curated enzyme-substrate pairs for models to learn from known pair interactions, the databases are often sparse, i.e., there are only limited and incomplete...
Automatic speech editing aims to modify spoken content based on textual instructions, yet traditional cascade systems rely on explicit temporal alignment and complex preprocessing. To address these limitations, we propose CosyEdit, an end-to-end speech editing model adapted from CosyVoice through task-specific post-training and a...
Self-attention is the central computational primitive of Vision Transformers, yet we lack a principled understanding of what information attention mechanisms exchange between tokens. Attention maps describe where weight mass concentrates; they do not reveal whether queries and keys trade position, content, or both. We introduce...
We propose Mesh4D, a feed-forward model for monocular 4D mesh reconstruction. Given a monocular video of a dynamic object, our model reconstructs the object's complete 3D shape and motion, represented as a deformation field. Our key contribution is a compact latent space that encodes the entire animation sequence in a single pass....
Nighttime color constancy still remains a challenging problem in computational photography due to low-light noise and complex illumination conditions. We present RL-AWB, a novel framework combining statistical methods with deep reinforcement learning for nighttime white balance. Our method begins with a statistical algorithm tailored...
Recently, Quantum Visual Fields (QVFs) have shown promising improvements in model compactness and convergence speed for learning the provided 2D or 3D signals. Meanwhile, novel-view synthesis has seen major advances with Neural Radiance Fields (NeRFs), where models learn a compact representation from 2D images to render 3D scenes,...
Vision-Language-Action (VLA) models have recently shown strong generalization, with some approaches seeking to explicitly generate linguistic reasoning traces or predict future observations prior to execution. However, explicit reasoning typically incurs non-negligible inference latency, which constrains the temporal resolution...
Building on ideas of Gurevich and Shelah for the Gödel Class, we present a new probabilistic proof of the finite model property for the Guarded Fragment of First-Order Logic. Our proof is conceptually simple and yields the optimal doubly-exponential upper bound on the size of minimal models. We precisely analyse the obtained bound, up...
Recovering clean and accurate geometry from images is essential for robotics and augmented reality. However, existing geometry foundation models still suffer severely from flying pixels and the loss of fine details. In this paper, we present pixel-perfect visual geometry models that can predict high-quality, flying-pixel-free point...
U.S. AI security policy is increasingly shaped by an $\textit{LLM Mirage}$, the belief that national security risks scale in proportion to the compute used to train frontier language models. That premise fails in two ways. It miscalibrates strategy because adversaries can obtain weaponizable capabilities with task-specific systems...
We prove tight lower bounds for online multicalibration, establishing an information-theoretic separation from marginal calibration. In the general setting where group functions can depend on both context and the learner's predictions, we prove an $Ω(T^{2/3})$ lower bound on expected multicalibration error using just three disjoint...
Referring Expression Segmentation (RES) and Comprehension (REC) respectively segment and detect the object described by an expression, while Referring Expression Generation (REG) generates an expression for the selected object. Existing datasets and methods commonly support single-target expressions only, i.e., one expression refers...
Functional grasping with dexterous robotic hands is a key capability for enabling tool use and complex manipulation, yet progress has been constrained by two persistent bottlenecks: the scarcity of large-scale datasets and the absence of integrated semantic and geometric reasoning in learned models. In this work, we present CorDex, a...
As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL) pipelines have begun incorporating multiple rewards, each capturing a distinct preference, to...
The diversity, quantity, and quality of manipulation data are critical for training effective robot policies. However, due to hardware and physical setup constraints, collecting large-scale real-world manipulation data remains difficult to scale across diverse environments. Recent work uses text-prompt conditioned image diffusion...
Large language models suffer from "hallucinations"-logical inconsistencies induced by semantic noise. We propose that current architectures operate in a "Metric Phase," where causal order is vulnerable to spontaneous symmetry breaking. Here, we identify robust inference as an effective Symmetry-Protected Topological phase, where...
Camera-controlled generative video re-rendering methods, such as ReCamMaster, have achieved remarkable progress. However, despite their success in single-view setting, these works often struggle to maintain consistency across multi-view scenarios. Ensuring spatio-temporal coherence in hallucinated regions remains challenging due to...