3462 papers
This paper introduces DRIFT, a dual-path Transformer model that effectively fuses fine-grained local and coarse-grained global features from sparse 4D radar point clouds to achieve state-of-the-art performance in automated driving perception tasks like object detection and free road estimation.
The paper introduces TemporalDoRA, a parameter-efficient fine-tuning method that integrates lightweight temporal attention into the low-rank adaptation branch of vision encoders to enhance robustness against linguistic variations in surgical video question answering, validated by a new colonoscopy dataset and improved Out-of-Template performance.
This paper introduces the concept of "Interaction Smells" in multi-turn human-LLM code generation, establishes a taxonomy based on real-world data, analyzes their distribution across leading models, and proposes the Invariant-aware Constraint Evolution (InCE) framework to effectively mitigate these issues and improve task success rates.
The paper proposes TriFusion-SR, a wavelet-guided conditional diffusion framework that jointly performs tri-modal medical image fusion and super-resolution by decomposing features into frequency bands and employing rectified wavelet features with adaptive spatial-frequency fusion to achieve state-of-the-art performance in resolution and perceptual quality.
ProGS introduces a novel streaming-friendly codec that organizes 3D Gaussian Splatting data into an octree structure with mutual information enhancement, achieving a 45-fold reduction in file size and over 10% visual improvement while enabling progressive coding for varying bandwidth conditions.
This paper introduces Robotic Scene Cloning (RSC), a novel method that enhances zero-shot robotic manipulation by editing existing operation trajectories through visual prompting and condition injection to generate accurate, scene-consistent samples that significantly improve policy generalization in real-world environments.
This paper introduces GSStream, a novel volumetric scene streaming system for 3D Gaussian Splatting that leverages collaborative viewport prediction and deep reinforcement learning-based bitrate adaptation to overcome bandwidth challenges and deliver high-quality, real-time immersive experiences.
The paper proposes FrameDiT, a novel video generation architecture that introduces Matrix Attention to efficiently model global spatio-temporal dynamics by processing frames as matrices, thereby achieving state-of-the-art video quality and temporal coherence while maintaining computational efficiency comparable to local factorized attention.
This paper introduces the concept of "local stability" to assess how minor changes in item values affect their rankings, particularly within dense regions of similar-quality items, and proposes efficient sampling-based algorithms (LStability and Detect-Dense-Region) with theoretical guarantees to compute this measure and identify such regions.
This paper formalizes the concept of idempotent backward slices and presents a sound, efficient algorithm for extracting them from Gated Static Single Assignment (GSA) form to enable a novel sparse code-size reduction optimization that merges non-contiguous instructions, achieving up to 7.24% size reduction in specific benchmarks.
This paper proposes a regularized ensemble Kalman filter framework that integrates sensor displacement data into stochastic phase-field models of brittle fracture to infer the evolving displacement and phase-field states, thereby correcting model predictions while ensuring physical consistency through a novel regularization step.
The paper introduces WVA, a global optimization control plane co-designed with the \texttt{llmd} inference engine that leverages internal saturation states and fragmentation-aware strategies to achieve significantly higher throughput, fewer request failures, and lower power consumption compared to traditional Kubernetes autoscalers when managing heterogeneous LLM workloads.
FetalAgents is a novel multi-agent system that dynamically orchestrates specialized vision experts to deliver robust, end-to-end fetal ultrasound analysis and structured clinical reporting across multiple tasks, outperforming existing specialized models and multimodal large language models.
This paper proposes a task-based scheduling framework that ensures end-to-end data freshness in safety-critical multi-rate systems by introducing a Consensus Offset Search algorithm to align task releases with data lifespan constraints, thereby eliminating the artificial latency of Logical Execution Time and the inefficiency of redundant oversampling while preserving Global EDF schedulability.
This paper introduces Step-Aware Contrastive Alignment (SACA), a novel framework that enhances Vision-Language Navigation in Continuous Environments by utilizing a perception-grounded auditor to extract dense, step-level supervision from imperfect trajectories, thereby overcoming the limitations of compounding errors in supervised fine-tuning and sparse rewards in reinforcement fine-tuning to achieve state-of-the-art performance.
This paper introduces ENIGMA-360, a publicly released, temporally synchronized ego-exo dataset containing 360 annotated procedural videos from real industrial scenarios to advance human behavior understanding and establish baselines for tasks like action segmentation and interaction detection.
This paper introduces LAP, a novel procedure planning model that leverages a fine-tuned Vision Language Model to convert visual observations into distinctive text embeddings for a diffusion-based planner, achieving state-of-the-art performance on multiple benchmarks by effectively resolving visual ambiguities through language.
This paper presents a compact, spring-based, tendon-driven continuum robot inspired by caterpillar locomotion and equipped with artificial bristle sensors, which integrates with commercial robotic arms to enable effective, compliant exploration and surface perception in confined spaces with a mean position error of 4.32 mm.
This paper establishes that minimizing the longest edge length in a simultaneous geometric embedding of two paths on an integer grid is NP-hard, while providing an algorithm to minimize the grid perimeter when one path is -monotone and the other is -monotone.
This paper argues that commercial videogames serve as a powerful, underutilized research environment at the intersection of human-computer interaction and cognitive science, offering ecologically valid contexts to study perception, attention, and executive functioning through a systematic framework that maps game affordances to cognitive demands.