5561 papers
The paper proposes SHINE, a training-free framework that leverages pretrained diffusion models like FLUX to achieve physically plausible, high-fidelity image composition with accurate lighting and reflections, while introducing the ComplexCompo benchmark to rigorously evaluate performance in challenging scenarios.
This paper introduces QuadGPT, the first end-to-end autoregressive framework that generates native quadrilateral meshes with superior geometric and topological quality by employing a unified tokenization method for mixed topologies and a specialized Reinforcement Learning fine-tuning strategy.
DistillKac is a fast, few-step image generation framework that leverages damped wave equations and stochastic Kac representation to enforce finite-speed probability transport, enabling stable classifier-free guidance and efficient endpoint-only distillation for high-quality sample synthesis.
This paper addresses the limitations of existing visual emotion evaluation methods for Multimodal Large Language Models (MLLMs) by proposing an open-vocabulary, automated Emotion Statement Judgment framework that reveals current models' strengths in context-based interpretation but highlights significant gaps in understanding subjective perception compared to humans.
The paper introduces COMPASS, a robust framework that generates efficient and valid conformal prediction intervals for medical segmentation metrics by calibrating directly in the model's feature space rather than treating the segmentation-to-metric pipeline as a black box.
The paper introduces CircuitSense, a hierarchical benchmark of over 8,000 circuit problems that evaluates Multi-modal Large Language Models across perception, analysis, and design tasks, revealing a critical performance gap where models excel at visual recognition but struggle significantly with deriving symbolic equations and performing mathematical reasoning essential for engineering design.
This paper introduces NeuroAdapter, a visual decoding framework that directly conditions latent diffusion models on brain representations to achieve competitive image reconstruction while enabling interpretable analysis of how specific cortical areas influence the generative process through a novel bidirectional interpretability framework.
DiffInk is a novel latent diffusion Transformer framework that employs a dual-regularized VAE to disentangle glyph content and writing style, enabling efficient and high-fidelity full-line online handwriting generation that outperforms existing state-of-the-art methods.
This paper introduces SMART-R1, a novel R1-style reinforcement fine-tuning framework that combines metric-oriented policy optimization with an iterative SFT-RFT-SFT training strategy to significantly enhance the realism and generalization of multi-agent traffic simulation, achieving state-of-the-art performance on the Waymo Open Sim Agents Challenge.
The paper introduces EditReward, a human-aligned reward model trained on a new large-scale human preference dataset that achieves state-of-the-art performance in evaluating instruction-guided image editing and effectively filters high-quality data to significantly improve the training of open-source editing models.
Stylos is a single-forward 3D Gaussian framework that achieves geometry-aware, view-consistent 3D style transfer on unposed content by leveraging a Transformer backbone with dual attention pathways and a voxel-based 3D style loss, enabling high-quality zero-shot stylization without per-scene optimization or precomputed poses.
This paper introduces CB, a novel multilingual and multicultural benchmark based on comics that evaluates Multimodal Large Language Models across three progressively difficult tasks, revealing significant performance gaps between current models and human capabilities in cultural awareness.
This paper introduces LVTINO, a novel zero-shot inverse solver that leverages Video Consistency Models to achieve high-definition video restoration with superior temporal consistency and computational efficiency compared to existing frame-by-frame image-based methods.
DragFlow introduces a novel region-based editing framework that leverages the strong generative priors of DiT models like FLUX to overcome the distortions and supervision limitations of traditional point-based drag editing, achieving state-of-the-art performance through affine transformations, personalization adapters, and multimodal guidance.
The paper proposes ChainMPQ, a training-free method that mitigates relation hallucinations in Large Vision-Language Models by constructing an interleaved chain of multi-perspective questions and accumulated visual-textual memories to guide progressive relational reasoning.
To overcome the challenges of individual variability in echocardiography probe guidance, the authors propose VA-Adapter, a lightweight module that integrates vision-action sequences into an ultrasound foundation model to enable online inference of individual 3D cardiac structures, achieving superior performance with significantly fewer parameters than existing methods.
TTOM is a training-free framework that enhances compositional video generation by optimizing new parameters guided by layout-attention objectives and employing a parametric memory mechanism for streaming inference, thereby achieving superior text-image alignment and generalization without direct latent intervention.
The paper introduces "Splat the Net," a novel volumetric representation that combines the high expressivity of neural radiance fields with the real-time efficiency of 3D Gaussian Splatting by using neural primitives with exact analytical line integrals, achieving comparable quality and speed with significantly fewer primitives and parameters.
This paper introduces LinearSR, a holistic framework that enables stable and efficient photorealistic image super-resolution by overcoming linear attention's historical training instability and perception-distortion trade-off through novel strategies like ESGF, SNR-based MoE, and TAG, achieving state-of-the-art quality with exceptional computational efficiency.
The paper proposes PHyCLIP, a vision-language model that unifies hierarchical and compositional semantic structures by employing an -product metric on a Cartesian product of hyperbolic factors, thereby outperforming existing single-space approaches in various representation learning tasks.