arXiv preprints from January 1, 2026 through September 12, 2026 — 21:24:27 EST
Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers, limiting trust and explainability. This paper presents Explanation-Guided Training (EGT), a...
Few-shot class-incremental learning (FSCIL) aims to continuously recognize novel classes under limited data, which suffers from the key stability-plasticity dilemma: balancing the retention of old knowledge with the acquisition of new knowledge. To address this issue, we divide the task into two different stages and propose a...
Spike-timing-dependent plasticity (STDP) provides a biologically-plausible learning mechanism for spiking neural networks (SNNs); however, Hebbian weight updates in architectures with recurrent connections suffer from pathological weight dynamics: unbounded growth, catastrophic forgetting, and loss of representational diversity. We...
The development of reliable methods for multi-label classification (MLC) has become a prominent research direction in remote sensing (RS). As the scale of RS data continues to expand, annotation procedures increasingly rely on thematic products or crowdsourced procedures to reduce the cost of manual annotation. While cost-effective,...
Table reasoning, a task to answer questions by reasoning over data presented in tables, is an important topic due to the prevalence of knowledge stored in tabular formats. Recent solutions use Large Language Models (LLMs), exploiting the semantic understanding and reasoning capabilities of LLMs. A common paradigm of such solutions...
Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and personalization. Recent work on Bi-directional Preference Optimization (BiPO) shows that dense steering vectors can be learned directly from preference data in a Direct Preference...
Echocardiographic diagnosis is vital for cardiac screening yet remains challenging. Existing echocardiography foundation models do not effectively capture the relationships between quantitative measurements and clinical manifestations, whereas medical reasoning multimodal large language models (MLLMs) require costly construction of...
Low Earth Orbit (LEO) satellite networks are emerging as an essential communication infrastructure, with standardized 5G-based non-terrestrial networks and their integration with terrestrial systems envisioned as a key feature of 6G. However, current LEO systems still exhibit significant latency variations, limiting their suitability...
Effective memory management is essential for large language model agents to navigate long-horizon tasks. Recent research has explored using Reinforcement Learning to develop specialized memory manager agents. However, existing approaches rely on final task performance as the primary reward, which results in severe reward sparsity and...
The advent of Large Multimodal Models (LMMs) offers a promising technology to tackle the limitations of modular design in autonomous driving, which often falters in open-world scenarios requiring sustained environmental understanding and logical reasoning. Besides, embodied artificial intelligence facilitates policy optimization...
In this paper, we establish an analogue of Craig Interpolation Property for a many-sorted variant of first-order hybrid logic. We develop a forcing technique that dynamically adds new constants to the underlying signature in a way that preserves consistency, even in the presence of models with possibly empty domains. Using this...
Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verification, existing methods suffer from...
In the era of digital animation, the quest to produce lifelike facial animations for virtual characters has led to the development of various retargeting methods. While the retargeting facial motion between models of similar shapes has been very successful, challenges arise when the retargeting is performed on stylized or exaggerated...
Group Relative Policy Optimization (GRPO) significantly enhances the reasoning performance of Large Language Models (LLMs). However, this success heavily relies on expensive external verifiers or human rules. Such dependency not only leads to significant computational costs and training latency, but also yields sparse rewards that...
Recently it was shown that many classic graph problems -- Independent Set, Dominating Set, Hamiltonian Cycle, and more -- can be solved in subexponential time on unit-ball graphs. More precisely, these problems can be solved in $2^{O(n^{1-1/d})}$ time on unit-ball graphs in $\mathbb R^d$, which is tight under ETH. The result can be...
Let F be a finite family of graphs. In the F-Deletion problem, one is given a graph G and an integer k, and the goal is to find k vertices whose deletion results in a graph with no minor from the family F. This may be regarded as a far-reaching generalization of Vertex Cover and Feedback vertex Set. In their seminal work, Fomin,...
As digital twins (DTs) evolve to become more agentic through the integration of artificial intelligence (AI), they acquire capabilities that extend beyond dynamic representation of their target systems. This paper presents a taxonomy of agentic DTs organised around three fundamental dimensions: the locus of agency (external, internal,...
In this work, we aim to enable legged robots to learn how to interpret human social cues and produce appropriate behaviors through physical human guidance. However, learning through physical engagement can place a heavy burden on users when the process requires large amounts of human-provided data. To address this, we propose a...
Online on-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon by analyzing how the sampling policy's coverage evolves throughout on-policy training. We propose...
In this paper, we propose a novel multimodal framework, Multimodal Language-Guided Network (MMLGNet), to align heterogeneous remote sensing modalities like Hyperspectral Imaging (HSI) and LiDAR with natural language semantics using vision-language models such as CLIP. With the increasing availability of multimodal Earth observation...
Tax code prediction is a crucial yet underexplored task in automating invoicing and compliance management for large-scale e-commerce platforms. Each product must be accurately mapped to a node within a multi-level taxonomic hierarchy defined by national standards, where errors lead to financial inconsistencies and regulatory risks....
Large Language Models (LLMs) are increasingly integrated into academic research pipelines; however, the Terms of Service governing their use remain under-examined. We present a comparative analysis of the Terms of Service of five major LLM providers (Anthropic, DeepSeek, Google, OpenAI, and xAI) collected in November 2025. Our...
Real-time multi-camera 3D reconstruction is crucial for 3D perception, immersive interaction, and robotics. Existing methods struggle with multi-view fusion, camera extrinsic uncertainty, and scalability for large camera setups. We propose SPARK, a self-calibrating real-time multi-camera point cloud reconstruction framework that...
With large language models demonstrating significant potential in code generation tasks, their application to onboard control of resource-constrained Unmanned Aerial Vehicles has emerged as an important research direction. However, a notable contradiction exists between the high resource consumption of large models and the real-time,...
The demand for real-time visual understanding and interaction in complex scenarios is increasingly critical for unmanned aerial vehicles. However, a significant challenge arises from the contradiction between the high computational cost of large Vision language models and the limited computing resources available on UAV edge devices....