6369 papers
This paper presents a graph-based online Lidar odometry method that enhances trajectory estimation and map accuracy by registering scans against multiple overlapping submaps and performing retrospective refinement of their anchor points, achieving superior performance on automotive datasets while maintaining real-time operation.
This paper proposes GenCLIP, a novel framework for zero-shot anomaly detection that enhances generalization and stability through multi-layer prompting, a dual-branch inference strategy balancing category specificity with generalization, and an adaptive text prompt filtering mechanism.
FAST is an efficient scheduler designed to overcome the scalability and performance limitations of existing solutions for All-to-All(v) communication in dynamic Mixture-of-Experts workloads by addressing traffic skew and incast congestion while drastically reducing synthesis time on modern GPU clusters.
This paper introduces BusterX, an MLLM-powered framework for AI-generated video forgery detection that combines the comprehensive GenBuster-200K dataset and the multi-track GenBuster-Bench to shift from black-box classification to interpretable visual reasoning, achieving superior accuracy and explanation quality compared to leading models.
This paper introduces DVD-Quant, a novel data-free post-training quantization framework for Video Diffusion Transformers that utilizes Bounded-init Grid Refinement, Auto-scaling Rotated Quantization, and -Guided Bit Switching to achieve a 2 speedup and enable W4A4 quantization without compromising visual fidelity.
This paper introduces "Alchemist," a novel methodology that leverages pre-trained generative models to curate a compact, high-quality, general-purpose supervised fine-tuning dataset, which significantly enhances the aesthetic quality and alignment of public text-to-image models while preserving diversity.
This paper presents a systematic literature review of 80 studies on "systems of twinned systems," a paradigm that integrates the System of Systems and Digital Twin concepts to address modern engineering complexity, resulting in a new classification framework compatible with existing theories.
This paper introduces Instance Data Condensation (IDC), a novel framework utilizing Random Local Fourier Feature Extraction and Multi-level Feature Distribution Matching to synthesize a highly compact (10% volume) dataset for Image Super-Resolution that achieves performance comparable to the original full dataset while significantly reducing computational and storage requirements.
This paper introduces "Linear Layouts," a novel framework that models tensor layouts as linear algebra operations over to enable generic, efficient, and bug-free layout definitions and conversions for deep learning workloads, successfully integrating with the Triton compiler to overcome the limitations of existing case-by-case approaches.
This paper introduces a robustness-aware framework that jointly selects tools and plans contact-rich manipulation trajectories by leveraging an energy-based metric to optimize for disturbance resilience in robotic tool-use tasks.
This paper proposes a structured methodology that integrates the Robot Operating System (ROS) with Model-Based Systems Engineering (MBSE) through a specialized SysML metamodel called MeROS and an adapted V-model, aiming to enhance the semantic coherence, structural traceability, and reliable coordination of complex heterogeneous robotic systems.
VisualPrompter is a novel, training-free framework that enhances text-to-image synthesis by employing a self-reflection module to identify missing concepts and a fine-grained optimization mechanism to refine prompts, thereby achieving state-of-the-art semantic alignment between user descriptions and generated images.
This paper introduces Token Bottleneck (ToBo), a self-supervised learning framework that compresses dynamic scenes into a compact token to predict future states with minimal hints, thereby enabling robust sequential scene understanding and robotic manipulation across both simulated and real-world environments.
This paper introduces NarrLV, the first comprehensive benchmark for evaluating long video generation models by defining Temporal Narrative Atoms to quantify narrative richness and employing an MLLM-based framework to assess narrative expression, revealing current model capabilities and limitations.
This paper introduces TomatoMAP, a comprehensive dataset of 64,464 multi-angle, multi-pose tomato images with detailed annotations for seven regions of interest and 50 growth stages, which was validated to demonstrate that a cascading deep learning framework achieves fine-grained phenotyping accuracy and speed comparable to human experts.
The paper proposes Gaussian Set Surface Reconstruction (GSSR), a method that optimizes individual Gaussian placement and alignment to achieve accurate 3D geometry reconstruction and uniform surface distribution, thereby overcoming the geometric limitations of existing 3D Gaussian Splatting variants while preserving high-quality rendering.
TrinityDNA is a novel, bio-inspired foundational model that integrates structural feature capture, symmetry handling, multi-scale attention, and evolutionary training to efficiently model long DNA sequences, significantly advancing gene function prediction and regulatory discovery while introducing a new long-sequence CDS annotation benchmark.
This paper introduces an interactive, no-code framework with a graphical interface and graph-based representation to democratize scenario generation for autonomous driving validation in CARLA, enabling non-technical users to efficiently create, manage, and execute diverse test scenarios without programming expertise.
This paper introduces a novel SCC-constrained bilevel model to demonstrate that synchronous generators at advantageous grid locations can exploit the localized nature of short-circuit current services to exercise market power, significantly inflating revenues and consumer costs, thereby highlighting the urgent need for specific market design mitigations.
DianJin-OCR-R1 is a reasoning-enhanced vision-language model that improves OCR accuracy by interleaving its own recognition with expert tool outputs, guiding the model to iteratively re-examine images and integrate evidence to reduce hallucinations and enhance fine-grained perception.