MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.
hub
Adabins: Depth estimation using adap- tive bins
49 Pith papers cite this work. Polarity classification is still indexing.
49
Pith papers citing it
hub tools
co-cited works
representative citing papers
A rule-based strikingness measure is added to TKGR metrics to weight rare events higher, revealing that models weaken on striking events and ensemble gains come mostly from trivial fits.
Vector Scaffolding uses Interior Gradient Aggregation, Progressive Stratification, and Rapid Inflation Scheduling to achieve 2.5x faster optimization and up to 1.4 dB higher PSNR in differentiable vectorization.
LMMs perceive videos but underexploit visual content for causal reasoning due to textual shortcuts; ProCauEval diagnoses this and ADPO training reduces reliance on priors.
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
Introduces ViTextCaps dataset and PhonoSTFG phonological graph fusion framework for Vietnamese scene-text image captioning, showing cross-modal graph edges harm performance.
Calibration error tracks curvature via shared margin-dependent exponential tails; a margin-aware objective improves out-of-sample calibration across optimizers.
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.
Orthogonal transformations before order reduction in matrix zonotopes produce order-of-magnitude smaller reachable set volumes while keeping generator counts comparable.
FRTSearch reframes fast radio transient detection as instance segmentation on dynamic spectra and uses the segmented shapes to infer dispersion measure and time of arrival, achieving 98% recall with over 99.9% fewer false positives than traditional methods.
Large vision-language models exhibit severe object hallucination that varies with training instructions, and the proposed POPE polling method evaluates it more stably and flexibly than prior approaches.
PhysEditBench is a protocol-conditioned benchmark evaluating image editors on dense prediction of depth, normal, albedo, roughness, and metallic maps from RGB images using curated data and fixed scoring rules.
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
LiBrA-Net achieves real-time native 4K video dehazing via Lie-algebraic bilateral affine fields and releases the first 4K paired dehazing video benchmark with per-frame annotations.
Pixal3D performs pixel-aligned 3D generation from images via back-projected multi-scale feature volumes, achieving fidelity close to reconstruction while supporting multi-view and scene synthesis.
SD-GAN uses the EMA generator as a teacher to distill perceptual knowledge to the training generator, improving FID scores, stabilizing training, and providing guidance uncorrelated with standard adversarial loss.
KARMA-MV is a new benchmark showing that causal knowledge graphs improve VLMs on causal audio-visual reasoning in music videos.
ARFP is a key-conditioned reversible face cloaking method that resists unauthorized restoration attacks while enabling authorized recovery with tamper indication.
Neighbor2Inverse adapts the Neighbor2Neighbor principle to train a denoising network directly in the image domain for low-dose PBI-CT by using independently noised subsampled projections.
Sphere clouds neutralize density attacks on private 3D maps for visual localization while depth guidance from ToF sensors restores translation scale for accurate pose estimation.
Remote SAMsing pipeline boosts SAM2 coverage on remote sensing scenes from 30-68% to 91-98% via multi-pass masking and boundary-aware merging while preserving mask quality.
RWoDSN extracts feature points from point clouds via a novel DSN descriptor and random walk graph analysis, reporting 22% higher recall than prior state-of-the-art with 0.784 precision.
citing papers explorer
-
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.
-
Strikingness-Aware Evaluation for Temporal Knowledge Graph Reasoning
A rule-based strikingness measure is added to TKGR metrics to weight rare events higher, revealing that models weaken on striking events and ensemble gains come mostly from trivial fits.
-
Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization
Vector Scaffolding uses Interior Gradient Aggregation, Progressive Stratification, and Rapid Inflation Scheduling to achieve 2.5x faster optimization and up to 1.4 dB higher PSNR in differentiable vectorization.
-
Perception Without Engagement: Dissecting the Causal Discovery Deficit in LMMs
LMMs perceive videos but underexploit visual content for causal reasoning due to textual shortcuts; ProCauEval diagnoses this and ADPO training reduces reliance on priors.
-
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
-
Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention
Introduces ViTextCaps dataset and PhonoSTFG phonological graph fusion framework for Vietnamese scene-text image captioning, showing cross-modal graph edges harm performance.
-
Too Sharp, Too Sure: When Calibration Follows Curvature
Calibration error tracks curvature via shared margin-dependent exponential tails; a margin-aware objective improves out-of-sample calibration across optimizers.
-
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
-
Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classes
SARR modifies trigonometric rotation encodings with object symmetry orders to produce unique continuous poses, enabling standard CNNs to outperform existing methods on symmetry-aware 6D pose estimation without custom losses or 3D models.
-
Orthogonal Transformations for Efficient Data-Driven Reachability Analysis
Orthogonal transformations before order reduction in matrix zonotopes produce order-of-magnitude smaller reachable set volumes while keeping generator counts comparable.
-
FRTSearch: Unified Detection and Parameter Inference of Fast Radio Transients using Instance Segmentation
FRTSearch reframes fast radio transient detection as instance segmentation on dynamic spectra and uses the segmented shapes to infer dispersion measure and time of arrival, achieving 98% recall with over 99.9% fewer false positives than traditional methods.
-
Evaluating Object Hallucination in Large Vision-Language Models
Large vision-language models exhibit severe object hallucination that varies with training instructions, and the proposed POPE polling method evaluates it more stably and flexibly than prior approaches.
-
PhysEditBench: A Protocol-Conditioned Benchmark for Dense Physical-Map Prediction with Image Editors
PhysEditBench is a protocol-conditioned benchmark evaluating image editors on dense prediction of depth, normal, albedo, roughness, and metallic maps from RGB images using curated data and fixed scoring rules.
-
On What We Can Learn from Low-Resolution Data
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
-
Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
-
LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing
LiBrA-Net achieves real-time native 4K video dehazing via Lie-algebraic bilateral affine fields and releases the first 4K paired dehazing video benchmark with per-frame annotations.
-
Pixal3D: Pixel-Aligned 3D Generation from Images
Pixal3D performs pixel-aligned 3D generation from images via back-projected multi-scale feature volumes, achieving fidelity close to reconstruction while supporting multi-view and scene synthesis.
-
Improving Generative Adversarial Networks with Self-Distillation
SD-GAN uses the EMA generator as a teacher to distill perceptual knowledge to the training generator, improving FID scores, stabilizing training, and providing guidance uncorrelated with standard adversarial loss.
-
KARMA-MV: A Benchmark for Causal Question Answering on Music Videos
KARMA-MV is a new benchmark showing that causal knowledge graphs improve VLMs on causal audio-visual reasoning in music videos.
-
Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition
ARFP is a key-conditioned reversible face cloaking method that resists unauthorized restoration attacks while enabling authorized recovery with tamper indication.
-
Neighbor2Inverse: Self-Supervised Denoising for Low-Dose Region-of-Interest Phase Contrast CT
Neighbor2Inverse adapts the Neighbor2Neighbor principle to train a denoising network directly in the image domain for low-dose PBI-CT by using independently noised subsampled projections.
-
Depth-Guided Privacy-Preserving Visual Localization Using 3D Sphere Clouds
Sphere clouds neutralize density attacks on private 3D maps for visual localization while depth guidance from ToF sensors restores translation scale for accurate pose estimation.
-
Remote SAMsing: From Segment Anything to Segment Everything
Remote SAMsing pipeline boosts SAM2 coverage on remote sensing scenes from 30-68% to 91-98% via multi-pass masking and boundary-aware merging while preserving mask quality.
-
Random Walk on Point Clouds for Feature Detection
RWoDSN extracts feature points from point clouds via a novel DSN descriptor and random walk graph analysis, reporting 22% higher recall than prior state-of-the-art with 0.784 precision.
-
CDSA-Net:Collaborative Decoupling of Vascular Structure and Background for High-Fidelity Coronary Digital Subtraction Angiography
CDSA-Net decouples vascular structure extraction and background restoration in coronary DSA via hierarchical geometric priors and adaptive noise modeling to eliminate artifacts while preserving tissue fidelity.
-
Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
N-HMC performs posterior sampling entirely in the initial noise space of diffusion models to solve inverse problems more robustly, with NA-NHMC adapting to unknown noise levels and outperforming prior methods on multiple tasks.
-
Agent-Aided Design for Dynamic CAD Models
AADvark extends agent-aided CAD design to dynamic 3D assemblies with movable parts by integrating constraint solvers and visual feedback to create a verification signal for the agent.
-
Efficient Search of Implantable Adaptive Cells for Medical Image Segmentation
IAC-LTH accelerates IAC search for medical segmentation by progressively pruning unstable operations via Jensen-Shannon divergence on per-edge importance distributions, delivering comparable patient-level Dice scores with substantially lower wall-clock cost.
-
Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis
Iterative Gaussian Synopsis creates compact multi-level LOD hierarchies for 3D Gaussian Splatting via top-down unfolding with adaptive pruning, preserving quality while cutting storage.
-
Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR
SOLAR prevents latent rehearsal decay in online continual SSL by adaptively managing replay buffers with deviation proxies and an explicit overlap loss, delivering both fast convergence and state-of-the-art final accuracy on vision benchmarks.
-
SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation
SyncBreaker jointly attacks image and audio streams with Multi-Interval Sampling and Cross-Attention Fooling to degrade speech-driven talking head generation more than single-modality baselines.
-
UniRecGen: Unifying Multi-View 3D Reconstruction and Generation
UniRecGen unifies reconstruction and generation via shared canonical space and disentangled cooperative learning to produce complete, consistent 3D models from sparse views.
-
Introducing Environmental Constraints to Grasping Strategies for Paper-Like Flexible Materials Using a Soft Gripper
Systematic grasping strategies for paper-like materials are developed and tested with a soft gripper by exploiting environmental constraints to improve force control and success rates.
-
VFM-SDM: A vision foundation model-based framework for training-free, marker-free, and calibration-free structural displacement measurement
VFM-SDM enables accurate multi-directional structural displacement measurement from video using pre-trained vision models for camera estimation and point tracking, combined with geometry constraints, without task-specific training or preparation.
-
Architecture-agnostic Lipschitz-constant Bayesian header and its application to resolve semantically proximal classification errors with vision transformers
LipB-ViT adds bi-Lipschitz Bayesian layers to vision transformers and uses uncertainty-aware fusion to identify corrupted labels with over 93% recall at 15% noise, beating kNN baselines.
-
Skipping the Zeros in Diffusion Models for Sparse Data Generation
SED modifies diffusion models to generate only non-zero values in sparse data, preserving sparsity patterns, cutting computation, and matching or beating standard DM performance on benchmarks.
-
Physics-Guided Deep Learning For High Resolution X-ray Imaging
Physics-guided U-Net removes non-stationary artifacts from X-ray images, raising mean SSIM from 0.345 to 0.906 and 0.0679 to 0.945 in synthetic tests while preserving filament profiles better than Fourier filtering or DFFN.
-
CEZSAR: A Contrastive Embedding Method for Zero-Shot Action Recognition
CEZSAR uses contrastive learning to align video and sentence embeddings with automatic negative sampling, claiming state-of-the-art zero-shot action recognition on UCF-101 and Kinetics-400.
-
Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimation
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
-
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Weak-to-strong knowledge distillation applied early and then turned off accelerates convergence to target performance in visual learning tasks by factors of 1.7-4.8x.
-
Path-Sampled Integrated Gradients
Path-sampled integrated gradients generalizes integrated gradients by averaging gradients over sampled baselines on the linear path, proving equivalence to a weighted version that improves convergence rate to O(m^{-1}) and reduces variance by a factor of 1/3 under uniform sampling.
-
Protecting and Preserving Protest Dynamics for Responsible Analysis
A responsible computing framework substitutes real protest imagery with labeled synthetic reproductions from conditional image synthesis to enable privacy-aware analysis of collective action patterns.
-
Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction
A multilevel perceptual CRF model using Swin Transformer, HPF fusion, HA adapters, and dynamic scaling attention achieves state-of-the-art monocular depth estimation on NYU Depth v2, KITTI, and MatterPort3D with reduced error and fast inference.
-
Gemini Robotics: Bringing AI into the Physical World
Gemini Robotics is a Vision-Language-Action model for robot control that handles complex tasks robustly and adapts with minimal data, supported by an embodied reasoning extension.
-
Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation
Grad-ECLIP is an equivalent but flawed variant of attention-based interpretation, with two principles proposed to ensure model explanations reflect the original model.
-
XiYOLO: Energy-Aware Object Detection via Iterative Architecture Search and Scaling
XiYOLO uses iterative energy-aware neural architecture search and scaling to produce object detectors with stronger accuracy-energy tradeoffs than YOLO baselines on GPUs and NPUs.
-
EDFNet: Early Fusion of Edge and Depth for Thin-Obstacle Segmentation in UAV Navigation
Early RGB-Depth-Edge fusion in EDFNet provides a competitive baseline for thin-obstacle segmentation on the DDOS dataset, with the best pretrained U-Net model reaching 0.244 Thin-Structure Evaluation Score.
-
Generalization Under Scrutiny: Cross-Domain Detection Progresses, Pitfalls, and Persistent Challenges
A survey that organizes methods for cross-domain object detection into a taxonomy, analyzes domain shift across detection stages, and outlines persistent challenges.
-
Quantum-inspired tensor networks in machine learning models
Tensor networks developed for quantum states are reviewed as tools for machine learning models, with assessment of their potential computational, explanatory, and privacy advantages alongside remaining challenges.