4973 papers
The paper introduces GameVerse, a comprehensive benchmark featuring a novel reflect-and-retry paradigm and a hierarchical taxonomy across 15 games, demonstrating that Vision-Language Models can effectively improve their gameplay policies through video-based reflection by combining failure trajectories with expert tutorials.
The paper introduces ASMIL, a unified framework that addresses unstable attention dynamics, overfitting, and over-concentrated attention in attention-based multiple instance learning for whole slide imaging by employing an anchor model with a normalized sigmoid function and token random dropping, resulting in significant performance improvements over state-of-the-art methods.
This chapter explores the potential of generative AI to enhance K-16+ science literacy by proposing a coherent architectural framework that aligns the teaching, learning, and assessment of scientific knowledge and reasoning, while addressing associated challenges and outlining future research needs.
The paper proposes Graph-of-Mark (GoM), a novel pixel-level visual prompting technique that overlays scene graphs onto images to capture object relationships, thereby significantly enhancing the spatial reasoning and zero-shot performance of multimodal language models.
This paper introduces a system-level inference optimization for Diffusion Transformer-based video generation that employs a sequence-parallel Causal-RoPE mechanism and operator fusion to overcome memory and latency bottlenecks, achieving near real-time speeds and sub-second first-frame latency on an eight-GPU cluster.
This paper reveals that Chain-of-Thought prompting often underperforms direct answering in medical visual question answering due to a "medical perception bottleneck," and proposes training-free grounding interventions to restore visual accuracy and improve model reasoning.
This paper introduces SJD-PV, a training-free acceleration framework for autoregressive image generation that leverages phrase-level speculative verification based on token co-occurrence statistics to jointly validate multiple correlated tokens, achieving up to 30% faster decoding without compromising visual fidelity.
This paper presents the first demonstration of a low-latency, always-on fully-connected mesh network using four RFSoC-based software-defined radios that achieves an aggregate throughput of 1.2 Gbps to simultaneously stream twelve real-time, uncompressed 4K video feeds over 2x2 MIMO links.
This paper presents SDN-SYN PoW, an adaptive defense architecture that leverages a Software-Defined Networking controller to dynamically adjust non-interactive Proof-of-Work difficulty based on real-time traffic analysis, effectively mitigating multi-domain SYN floods while maintaining negligible overhead for legitimate clients.
This paper introduces SIL-GPO, a reinforcement learning framework that combines graph attention networks with self-imitation learning to optimize the joint deployment and routing of heterogeneous edge AI and microservices, significantly reducing end-to-end latency and improving resource utilization compared to existing methods.
The paper proposes CalibFusion, a Transformer-based differentiable calibration framework that learns to implicitly refine Radar-Camera extrinsics end-to-end to overcome the challenges of textureless, cluttered water-surface environments and significantly improve fusion-based 2D object detection.
This paper investigates whether semantic noise initialization, known to improve image diffusion models, transfers to text-to-video generation, finding that while it shows a slight positive trend on temporal metrics, it does not significantly outperform standard Gaussian noise due to weak or unstable signals in the noise space.
AutoFigure-Edit is an end-to-end system that generates fully editable, high-quality scientific illustrations from long-form text with flexible style adaptation via reference images, leveraging long-context understanding and native SVG support to overcome limitations in editability and efficiency found in existing automated tools.
The paper introduces MultiGen, a novel diffusion-based game engine that incorporates an explicit, persistent external memory to enable user-editable world structures and support coherent, real-time multiplayer interactions, overcoming the limitations of conventional next-frame prediction models.
This paper introduces VB, a novel benchmark designed to evaluate vision-language models' ability to determine image visibility and appropriately abstain from answering when evidence is insufficient, utilizing controlled minimal edits and specialized metrics to reveal that top-tier models like GPT-4o and Gemini 3.1 Pro significantly outperform open-source alternatives in confidence-aware accuracy and perspective reasoning.
The paper introduces RADAR, a multimodal benchmark comprising expert-annotated 3D abdominal CT scans and radiology report edits that enables the systematic evaluation of AI models on fine-grained clinical reasoning tasks, specifically image-text alignment and discrepancy assessment during the radiology report review process.
The paper proposes ECHO, a multi-agent framework that utilizes iterative hypergraph operations and a "Link-then-Bind" strategy to mitigate cascading errors in Multimedia Event Extraction, achieving significant performance improvements over state-of-the-art methods on the M2E2 benchmark.
This paper presents an innovative, mobile-device-based 3D imaging approach using Structure-from-Motion and segmentation algorithms to reconstruct and analyze aggregate size and shape from stockpiles, offering a convenient and affordable solution for onsite quality assurance in road construction and geotechnics.
The paper introduces "Narrative Weaver," a novel framework that achieves controllable, long-range visual consistency in generative AI by integrating multimodal narrative planning with a dynamic memory bank, validated through extensive experiments and a newly released e-commerce advertising dataset.
This study evaluates the adaptability of the TerraMind geospatial foundation model to hyperspectral imaging tasks without native pretraining, finding that while band selection strategies allow for moderate performance, deep learning models with native spectral support remain superior, thereby highlighting the critical need for future architectures to incorporate native spectral tokenization.