9421 papers
This paper proposes a data-driven loss weighting (DLW) scheme that employs a bilevel optimization framework to train a neural network for predicting adaptive weights, thereby enhancing the performance and generalization of variational image denoising models across diverse and complex noise patterns.
The paper introduces SciTune, a framework that aligns large language models with human-curated scientific multimodal instructions, resulting in a model (LLaMA-SciTune) that significantly outperforms state-of-the-art systems on scientific visual and language benchmarks, even surpassing human performance in certain categories.
The paper introduces MM-LIMA, a multimodal large language model that achieves superior performance compared to MiniGPT-4 by utilizing a trainable data selector to filter and fine-tune on a small, high-quality dataset of just 200 examples, demonstrating that less but higher-quality instruction data is more effective for alignment.
LaMI proposes a late multi-image fusion method that augments text-only Large Language Models with test-time visual signals generated via parallel sampling, significantly improving visual commonsense reasoning and NLP performance without the high costs of full multimodal training or the degradation of textual capabilities.
This paper proposes LDNLM, a deep learning-based method that linearizes the traditional Nonlocal Means algorithm using a linear attention mechanism to achieve efficient and interpretable multiplicative noise removal with competitive performance.
This paper introduces unPIC, a modular framework that identifies Camera-Relative Object Coordinates (CROCS) as a superior intermediate geometric representation for image-to-3D generation, enabling more accurate, consistent, and feedforward 3D point cloud creation that outperforms existing state-of-the-art models.
This paper proposes HFI, a training-free and efficient framework that detects latent diffusion model-generated images and performs implicit watermarking by measuring aliasing artifacts in reconstructed images, thereby overcoming the limitations of existing methods that rely on reconstruction distance overfitted to background information.
The paper introduces RobustSpring, a comprehensive benchmark and dataset that evaluates the robustness of optical flow, scene flow, and stereo vision models against 20 types of image corruptions, addressing the gap in existing benchmarks that primarily focus on accuracy rather than resilience to real-world perturbations.
The paper introduces IMPLICITSTAINER, a deterministic, resolution-agnostic deep learning framework that utilizes neural implicit functions to efficiently generate high-fidelity, reproducible virtual immunohistochemical stains from H&E images, overcoming the limitations of existing patch-based and stochastic methods in clinical applications.
This paper introduces DeceptionDecoded, a large-scale benchmark and intent-guided simulation framework designed to evaluate and improve vision-language models' ability to detect misleading creator intent in multimodal news, addressing their current reliance on superficial cues and enhancing their robustness in misinformation governance.
GoT-R1 is a novel framework that leverages reinforcement learning with a dual-stage multi-dimensional reward system to enhance the semantic-spatial reasoning capabilities of multimodal large language models, significantly improving their ability to generate images from complex prompts involving precise object relationships and attributes.
Muddit introduces a unified discrete diffusion transformer that leverages pretrained visual priors and a lightweight text decoder to achieve fast, parallel, and high-quality generation across both text and image modalities, outperforming larger autoregressive models in efficiency and quality.
This paper introduces VisText-Mosquito, a unified multimodal dataset and framework that integrates visual detection, segmentation, and textual explanation to enable AI-driven proactive identification and analysis of mosquito breeding sites for disease prevention.
PRIX is a lightweight, camera-only end-to-end autonomous driving framework that utilizes a Context-aware Recalibration Transformer and a generative planning head to predict safe trajectories directly from raw pixels, achieving state-of-the-art performance on NavSim and nuScenes benchmarks while significantly reducing model size and inference costs compared to LiDAR-dependent or BEV-based approaches.
ZARA is a training-free, retrieval-augmented agent framework that converts motion sensor data into verifiable textual priors to enable robust, open-set human activity recognition without requiring parameter retraining.
This paper introduces DoSReMC, a domain shift resilient framework that enhances cross-domain generalization in mammography classification by fine-tuning only batch normalization and fully connected layers alongside adversarial training, thereby addressing performance degradation caused by data distribution variations without requiring full model retraining.
The paper proposes Delta Rectified Flow Sampling (DRFS), a novel inversion-free framework for text-to-image editing that mitigates over-smoothing artifacts by explicitly modeling velocity field discrepancies and introducing a time-dependent shift term, thereby unifying optimization and ODE editing approaches while achieving superior quality and controllability on the PIE Benchmark.
CARINOX is a unified framework that enhances the compositional alignment of text-to-image diffusion models by synergizing initial noise optimization and exploration with a principled, human-judgment-correlated reward selection strategy, achieving significant performance gains over state-of-the-art methods without requiring model fine-tuning.
This paper introduces PnP-CM, a plug-and-play framework that reinterprets consistency models as proximal operators to solve diverse linear and nonlinear inverse problems with high-quality reconstructions in as few as two to four neural function evaluations, eliminating the need for task-specific training while outperforming existing methods.
This paper introduces new synthetic and real-world video datasets for predicting dynamic physical properties like elasticity, viscosity, and friction, and evaluates various inference methods—including classical computer vision, prompt-based adaptation of video foundation models, and multi-modal large language models—demonstrating that pre-trained generative and self-supervised video models achieve performance comparable to each other and approaching an oracle baseline, while currently outperforming MLLMs.