January 2026

arXiv:2601.20072v1 Announce Type: new Abstract: We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image reconstruction and classification using both unlabeled and labeled samples with dynamically selected pseudo-labels. SSMAE introduces a validation-driven gating mechanism that activates pseudo-labeling only after the model achieves reliable, high-confidence predictions that are consistent across both weakly and strongly augmented views of […]

Ver mais

arXiv:2601.20071v1 Announce Type: new Abstract: Gradient-regularized value learning methods improve sample efficiency by leveraging learned models of transition dynamics and rewards to estimate return gradients. However, existing approaches, such as MAGE, struggle in stochastic or noisy environments, limiting their applicability. In this work, we address these limitations by extending distributional reinforcement learning on continuous state-action spaces to model not only the distribution over scalar state-action value functions but also over their gradients. We refer to this approach as […]

Ver mais

arXiv:2601.20069v1 Announce Type: new Abstract: Training a single network with multiple objectives often leads to conflicting gradients that degrade shared representations, forcing them into a compromised state that is suboptimal for any single task–a problem we term latent representation collapse. We introduce Domain Expansion, a framework that prevents these conflicts by restructuring the latent space itself. Our framework uses a novel orthogonal pooling mechanism to construct a latent space where each objective is assigned to a mutually orthogonal […]

Ver mais

arXiv:2601.20067v1 Announce Type: new Abstract: Priority encoders are typically considered expensive hardware components in terms of complexity, especially at high bit precisions or input lengths (e.g., above 512 bits). However, if the complexity can be reduced, priority encoders can feasibly accelerate a variety of key applications, such as high-precision integer arithmetic and content-addressable memory. We propose a new paradigm for constructing priority encoders by generalizing the previously proposed two-level priority encoder structure. We extend this concept to three […]

Ver mais

arXiv:2601.20064v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation aims to assign labels to every pixel in an image based on text labels. Existing approaches typically utilize vision-language models (VLMs), such as CLIP, for dense prediction. However, VLMs, pre-trained on image-text pairs, are biased toward salient, object-centric regions and exhibit two critical limitations when adapted to segmentation: (i) Foreground Bias, which tends to ignore background regions, and (ii) Limited Spatial Localization, resulting in blurred object boundaries. To address these […]

Ver mais

arXiv:2601.20061v1 Announce Type: new Abstract: Hyperdimensional Computing (HDC) represents data using extremely high-dimensional, low-precision vectors, termed hypervectors (HVs), and performs learning and inference through lightweight, noise-tolerant operations. However, the high dimensionality, sparsity, and repeated data movement involved in HDC make these computations difficult to accelerate efficiently on conventional processors. As a result, executing core HDC operations: binding, permutation, bundling, and similarity search: on CPUs or GPUs often leads to suboptimal utilization, memory bottlenecks, and limits on real-time performance. […]

Ver mais

arXiv:2601.20060v1 Announce Type: new Abstract: Let $P$ be a generic set of $n$ points in the plane, and let $P=Rcup B$ be a coloring of $P$ in two colors. We are interested in the number of crossings between the minimum spanning trees (MSTs) of $R$ and $B$, denoted by $crossAB(R,B)$. We define the emph{bicolored MST crossing number} of $P$, denoted by $cross(P)$, as $cross(P) = max_{P= Rcup B}(crossAB(R,B))$. We prove a linear upper bound for $cross(P)$ when $P$ […]

Ver mais

arXiv:2601.20055v1 Announce Type: new Abstract: Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce verification-guided answers through iterative refinement. Our approach decomposes LLM outputs into atomic claims, autoformalizes them into first-order logic, and verifies their logical consistency using automated theorem proving. We introduce three key innovations: (1) multi-model consensus via formal semantic equivalence checking […]

Ver mais

arXiv:2601.20054v1 Announce Type: new Abstract: Multi-vehicle autonomous driving couples strategic interaction with hybrid (discrete-continuous) maneuver planning under shared safety constraints. We introduce IBR-GCS, an Iterative Best Response (IBR) planning approach based on the Graphs of Convex Sets (GCS) framework that models highway driving as a generalized noncooperative game. IBR-GCS integrates combinatorial maneuver reasoning, trajectory planning, and game-theoretic interaction within a unified framework. The key novelty is a vehicle-specific, strategy-dependent GCS construction. Specifically, at each best-response update, each vehicle […]

Ver mais

arXiv:2601.20051v1 Announce Type: new Abstract: The rise of chronic diseases related to diet, such as obesity and diabetes, emphasizes the need for accurate monitoring of food intake. While AI-driven dietary assessment has made strides in recent years, the ill-posed nature of recovering size (portion) information from monocular images for accurate estimation of “how much did you eat?” is a pressing challenge. Some 3D reconstruction methods have achieved impressive geometric reconstruction but fail to recover the crucial real-world scale […]

Ver mais