2658 papers
This paper proposes QSTar, a novel query-guided spatial-temporal-frequency interaction method enhanced by a Query Context Reasoning block, which significantly improves Audio-Visual Question Answering performance by deeply integrating question-guided clues and audio frequency characteristics with visual perception, outperforming existing multimodal approaches on multiple benchmarks.
MeanCache is a training-free framework that accelerates Flow Matching inference by replacing instantaneous velocity caching with an average-velocity approach using cached Jacobian-vector products and a trajectory-stability scheduling strategy, achieving significant speedups (up to 4.56X) while maintaining high generation quality across models like FLUX.1 and HunyuanVideo.
PhysDrape is a hybrid neural-physical solver that combines a Physics-Informed Graph Neural Network with a differentiable two-stage force and collision projection system to achieve physically realistic garment draping with negligible interpenetration and superior fidelity compared to existing deep learning methods.
To address the challenges of parameter-efficient domain adaptation in V2X collaborative perception, the paper proposes FlowAdapt, a framework leveraging optimal transport theory and a progressive knowledge transfer mechanism to filter redundant data and preserve fine-grained semantics, achieving state-of-the-art performance with only 1% trainable parameters.
This paper proposes SToRM, a novel framework that employs a lightweight importance predictor, supervised training with pseudo-labels, and an anchor-context merging module to significantly reduce visual token redundancy in multi-modal LLMs for autonomous driving, achieving up to 30x computational savings while maintaining end-to-end performance comparable to using all tokens.
The paper introduces 3DMedAgent, a unified agent that leverages a flexible MLLM and long-term structured memory to coordinate heterogeneous tools for decomposing complex 3D CT analysis into tractable 2D-based subtasks, thereby enabling general-purpose 3D medical understanding without 3D-specific fine-tuning.
This paper demonstrates that neural networks learning equivariant operators in a latent space can effectively generalize to out-of-distribution symmetric transformations on simple datasets like rotated MNIST, while also highlighting the significant challenges involved in scaling this approach to more complex data.
OVerSeeC is a zero-shot modular framework that leverages large language models and open-vocabulary segmentation to generate executable global costmaps from satellite imagery and natural language instructions, enabling autonomous navigation to adapt to novel entities and dynamic mission constraints without requiring fixed ontologies.
This paper introduces Open-Vocabulary Domain Generalization in Semantic Segmentation (OVDG-SS), a new setting and benchmark for autonomous driving that addresses both unseen domains and categories, and proposes S2-Corr, a state-space-driven mechanism to refine text-image correlations in Vision-Language Models to achieve robust performance across diverse urban environments.
UniMatch is a novel coarse-to-fine framework that establishes dense semantic correspondences between strongly non-isometric, cross-category 3D shapes by leveraging class-agnostic segmentation, multimodal language models for part identification, and a rank-based contrastive learning scheme to overcome the limitations of prior isometry-dependent methods.
InfScene-VF proposes a diffusion-based framework for arbitrary-size image super-resolution that eliminates boundary artifacts and enables memory-efficient, parallelized inference on gigapixel imagery by introducing Variance-Corrected Fusion and Spatially-Decoupled Variance Correction to achieve spatially continuous joint-denoising.
This paper proposes an online data manipulation scheme that decomposes training images into independent object, scene, and camera components and recomposes them with perturbed poses to generate diverse training data, thereby improving the data efficiency and performance of monocular 3D object detection models across both fully and sparsely supervised settings.
This paper presents a cycle-consistent tuning framework that leverages lightweight LoRA adaptation of pretrained diffusion models to achieve robust, high-fidelity layered image decomposition, specifically for challenging logo-object separation, by enforcing bidirectional reconstruction consistency and iteratively refining performance through a progressive self-improving process.
This paper proposes "See It, Say It, Sorted," a lightweight, training-free, and plug-and-play framework that mitigates visual hallucination in large vision-language models by iteratively supervising each reasoning step with dynamically extracted visual evidence, thereby significantly improving reasoning accuracy without requiring additional model training.
This paper introduces a unified language modeling approach for semantic and panoptic segmentation in images and videos that discretizes masks into run-length encoded tokens, employing novel compression strategies to enable autoregressive generation despite computational constraints.
WISER is a training-free framework for Zero-Shot Composed Image Retrieval that unifies Text-to-Image and Image-to-Image paradigms through a "retrieve-verify-refine" pipeline, leveraging wider search, adaptive fusion, and self-reflection to significantly outperform existing methods across diverse benchmarks.
The paper introduces PackUV, a novel 4D Gaussian representation and fitting method that maps volumetric video attributes into structured UV atlases for efficient, codec-compatible storage and streaming, while demonstrating superior temporal consistency and rendering fidelity on the newly proposed large-scale PackUV-2B dataset.
This paper proposes HART, an annotation-free framework that leverages a novel Advantage Preference Group Relative Policy Optimization (AP-GRPO) algorithm to enable Large Multimodal Models to autonomously identify and verify key high-resolution image regions, thereby improving reasoning performance without requiring costly human grounding labels.
This paper introduces Infinite Self-Attention (InfSA) and its linear-time variant, Linear-InfSA, a spectral reformulation of self-attention as a diffusion process on token graphs that achieves state-of-the-art ImageNet accuracy and enables efficient, memory-free inference at ultra-high resolutions (up to 9216×9216) by replacing the quadratic softmax cost with a Neumann series approximation.
This paper introduces WildActor, a framework for unconstrained identity-preserving human video generation that leverages the large-scale Actor-18M dataset and novel attention mechanisms to overcome existing limitations in maintaining consistent full-body identities across dynamic shots, viewpoints, and motions.