3447 papers
The paper proposes MetaDAT, a trajectory prediction framework that combines meta-learning pre-training with a data-adaptive test-time updating mechanism to achieve robust, fast, and accurate online adaptation under distribution shifts by dynamically adjusting learning rates and focusing on informative hard samples.
This paper demonstrates that binary vulnerabilities in WebAssembly modules, such as buffer overflows and use-after-free errors, can compromise web application security by enabling attacks like SQL injections and XS-Leaks, while also offering best practices to mitigate these risks.
This paper constructs a functor to define dynamics for an algebraic model of interacting components, generalizing the AlChemy artificial life model and exploring how category theory can formally connect algebraic structures with dynamical systems in artificial chemistry.
The paper proposes GIIM, a novel graph-based framework that enhances multi-view medical image diagnosis by simultaneously modeling intra-view relationships and inter-view dynamics while effectively handling missing data to improve predictive accuracy and robustness.
ShapeMark is a robust and diversity-preserving watermarking method for diffusion models that encodes watermark bits into structured noise patterns rather than individual values and employs a randomization design to prevent fixed patterns, thereby achieving state-of-the-art robustness against lossy scenarios while maintaining high generation quality.
This paper introduces a preconditioned SE(3) Stein Variational Gradient Descent framework that reformulates point-cloud surface coverage as a manifold-aware sampling problem, enabling robots to generate high-quality, SE(3)-constrained trajectories that outperform existing optimization-based and sampling-as-optimization methods in both simulation and real-world experiments.
The paper introduces SEA-Nav, a reinforcement learning framework that combines differentiable control barrier functions, adaptive collision replay, and kinematic constraints to enable quadruped robots to achieve safe, agile, and efficient navigation in densely cluttered environments with minute-level training time.
TopoOR introduces a novel topological scene representation for surgical operating rooms that leverages higher-order structures and attention mechanisms to preserve complex multimodal relationships and manifold geometry, thereby outperforming traditional graph and LLM-based methods in safety-critical tasks like sterility breach detection and robot phase prediction.
This paper reports on the authors' experience developing three professional software engineering curricula and proposes a systematic, content-mapping-based approach with guiding principles for effectively integrating Requirements Engineering courses into these dynamic and modular programs.
This paper introduces the Patrologia Graeca Corpus, a large-scale open resource featuring OCR-processed, lemmatized, and part-of-speech tagged text from degraded nineteenth-century bilingual Greek-Latin editions, which achieves state-of-the-art recognition accuracy and establishes a new benchmark for noisy polytonic Greek processing.
This paper introduces OmniEarth, a comprehensive benchmark comprising 9,275 images and 44,210 verified instructions that evaluates Vision-Language Models across 28 geospatial tasks with a focus on perception, reasoning, and robustness, revealing significant performance gaps in current models for remote sensing applications.
The paper introduces MORE-R1, a novel Large Vision-Language Model that leverages a two-stage training process combining Supervised Fine-Tuning on automatically constructed stepwise reasoning data and Reinforcement Learning with Group Relative Policy Optimization to achieve state-of-the-art performance in Multimodal Object-Entity Relation Extraction.
PruneSID is a training-free, synergistic importance-diversity framework that significantly enhances Vision-Language Model efficiency by employing Principal Semantic Components Analysis and Intra-group Non-Maximum Suppression to achieve state-of-the-art accuracy with extreme token compression and faster prefilling speeds.
StyleVLA is a physics-informed Vision Language Action model built on Qwen3-VL-4B that generates diverse, kinematically feasible driving trajectories tailored to specific styles, significantly outperforming state-of-the-art proprietary models on domain-specific autonomous driving tasks.
This paper proposes a novel component-aware, self-refining framework that combines a Self-Attention-based Autoencoder, a Coordinate-Preserving Gated Fusion module, and a Spatially Adaptive Refinement Revisor to generate high-fidelity, semantically accurate photorealistic images from freehand sketches, significantly outperforming existing GAN and diffusion models across diverse facial and non-facial datasets.
This paper introduces Diagonal Distillation, an asymmetric autoregressive framework that leverages temporal context and implicit optical flow to enable high-fidelity, real-time streaming video generation with a 277.3x speedup while mitigating error accumulation and motion incoherence.
This paper reports on the synthesis and seeks feedback for the future evaluation of an Artefact Model for Regulatory Requirements Engineering (AM4RRE), aiming to bridge the gap between organizational regulatory processes and ad-hoc software development practices to achieve systematic, integrated compliance by design.
The paper proposes SurgFed, a language-guided multi-task federated learning framework that utilizes Language-guided Channel Selection and Language-guided Hyper Aggregation to overcome tissue and task diversity challenges, thereby improving surgical video segmentation and depth estimation across heterogeneous clinical environments.
This paper introduces EmbC-Test, a Retrieval-Augmented Generation (RAG) pipeline that leverages project-specific artifacts to ground large language models, enabling the automated generation of syntactically correct and runtime-valid embedded C tests that reduce testing time by up to 66% while producing 270 tests per hour.
This paper introduces a hybrid algebraic verification technique implemented in TalisMan2.0 that utilizes parallel multimodular reasoning to efficiently verify arithmetic circuits with large operands while avoiding the computational overhead of big integer arithmetic.