6135 papers
This paper introduces Samyama, a high-performance, unified graph-vector database written in Rust that integrates persistent storage, vector indexing, native optimization solvers, and agentic LLM enrichment into a single engine, achieving competitive throughput and latency on commodity hardware while offering GPU-accelerated enterprise features.
The paper proposes CEMR, a novel subgraph matching algorithm that significantly improves efficiency on large graphs by eliminating redundant computations through common extension merging and reusing, while further optimizing performance with two pruning techniques.
This paper proposes and analyzes three communication-efficient distributed algorithms that achieve finite-time quantized average consensus in open multi-agent systems with dynamic directed links, arbitrary bounded processing delays, and continuous node turnover, while establishing novel topological conditions for convergence and demonstrating superior performance through simulations.
This paper proposes the concepts of step automata and step Turing machines (STM) as a natural extension of traditional automata and Turing machines to bridge the gap between classical computation and concurrency by enabling the execution of atomic action steps without partial orders.
This paper proposes a systematic framework using Robust Positive Invariant sets to compute formally guaranteed trajectory tracking error bounds for autonomous helicopters, comparing three controller architectures to balance tracking performance with the conservatism of the derived error bounds.
This paper introduces WhispEar, a bidirectional framework that leverages a normal-to-whisper model to generate scalable pseudo-parallel data for training a whisper-to-normal conversion system, thereby overcoming data scarcity challenges and achieving superior performance on a newly released bilingual whispered-normal corpus.
The paper proposes S2S-FDD, a novel framework that bridges the semantic gap between high-dimensional industrial time-series signals and natural language by converting sensor data into descriptive summaries and utilizing a multi-turn tree-structured reasoning process with historical documents to achieve explainable, zero-shot fault diagnosis.
This paper presents a new reconfigurable haptic interface that utilizes a modular network of hybrid motor-brake cable actuation modules to deliver rich, multi-degree-of-freedom force feedback, capable of rendering smooth active forces up to 6 N and high-magnitude passive collision forces up to 186 N.
Speed3R is a sparse feed-forward 3D reconstruction model that overcomes the quadratic computational bottleneck of dense attention by employing a dual-branch mechanism to focus on informative tokens, achieving a 12.4x inference speedup with minimal accuracy trade-offs.
This paper introduces "See & Switch," a vision-based interactive framework for Programming by Demonstration that utilizes eye-in-hand images to enable reliable online conditional branching and anomaly detection in dexterous robot tasks, achieving high accuracy across diverse conditions and novice users.
ImageEdit-R1 is a novel multi-agent framework that employs reinforcement learning to coordinate specialized vision-language and generative agents, enabling dynamic, context-aware image editing that outperforms existing monolithic models and baselines in handling complex, multi-step user instructions.
CinemaWorld is a generative augmented reality system for the Meta Quest 3 that uses multimodal large language models and generative AI to extract features from 2D movie scenes and automatically synthesize synchronized 3D mixed reality content, thereby enhancing viewer immersion and enjoyment as validated through technical, user, and expert evaluations.
This paper proposes a novel plug-and-play ranking architecture that leverages Large Vision-Language Models (LVLMs) and a relational-aware loss function to explicitly model cross-view interactions, thereby significantly enhancing the accuracy and stability of UAV-to-satellite image geolocalization.
This paper proposes a novel evaluation framework for generative models that replaces traditional continuous feature-based metrics with training-free and no-reference metrics operating in discrete visual token space, demonstrating superior correlation with human judgments across a new large-scale benchmark called VisForm.
This paper proposes In-Context Reinforcement Learning (ICRL), a novel framework that eliminates the need for supervised fine-tuning by leveraging few-shot prompting during reinforcement learning rollouts to progressively teach large language models how to effectively use external tools, ultimately achieving state-of-the-art performance in a data-efficient, zero-shot manner.
This paper proposes a training-free pipeline using multimodal large language models to generate diverse, high-fidelity synthetic defect images for power line insulators, which significantly improves classification performance and data efficiency in low-data regimes by augmenting limited real-world datasets.
This paper analyzes a geometric balancing game on line arrangements, determining the minimum initial number of pebbles required for Alice to prevent Bob from emptying any box and proving that this threshold scales as for lines in general position.
The paper proposes TALON, a test-time adaptive learning framework for on-the-fly category discovery that overcomes the limitations of static hash-based methods by dynamically updating semantic prototypes and the feature encoder to continuously integrate new knowledge, while employing margin-aware logit calibration to prevent category explosion and significantly improve novel-class accuracy.
Although the study finds that Large Language Model-based relevance judgment systems do not outperform embedding-based retrieval on standard TREC-DL 2019 benchmarks due to the short-sightedness inherent in human annotations, it argues that these models possess the theoretical capability to surpass embedding methods by better understanding relevance through reasoning.
This paper introduces an augmented Model Predictive Control method for agile earth observation satellites that effectively balances high-performance nonlinear control capabilities with the computational simplicity required for hardware implementation, validated through both numerical simulations and physical experiments.