WikiVQABench is a human-curated collection of Wikipedia-based VQA items that require both visual evidence and external knowledge from Wikidata to answer correctly.
Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is method (57%).
27
Pith papers citing it
Method
57% of classified citations
citation-role summary
method 4
background 3
citation-polarity summary
years
2026 27representative citing papers
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
ARGUS cuts context-aware prompt-injection success from 28.8% to 3.8% on AgentLure while keeping 87.5% clean utility, beating prior defenses on the security-utility tradeoff.
DisImpact introduces a two-stage MLLM framework to classify disaster-related social media posts into ten impact categories and compute a unified physi-social impact index validated against FEMA and NASA ground-truth data.
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance with small text-to-voice gaps.
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.
Relit-LiVE jointly predicts relit videos and viewpoint-aligned environment maps inside a single diffusion process to achieve physically consistent video relighting without camera pose input.
A single-image head reconstruction method uses coarse-to-fine optimization with normal consistency, landmarks, and geometry-aware constraints on curvature and conformality to produce meshes with industry-grade topology and preserved facial identity.
A new MAT simplification algorithm uses explicit surface correspondence tracking and priority-controlled edge collapses to preserve structural features like fillet alignments on discrete meshes.
UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.
A training-free technique manipulates low-frequency noise in diffusion models to control image color and structure using low-frequency priors.
TTCD uses a non-stationary feature learner and reconstruction-guided distillation inside a transformer to infer contemporaneous and lagged causal graphs from non-stationary time series without strong noise assumptions.
LUCID detects hallucinations in LLM-KG reasoning by extracting node/edge features from attention and semantics then integrating them with KG structure in a GNN, achieving SOTA on nine new benchmark datasets versus 15 baselines.
A relaxed Picard iteration plus heteroscedastic boundary denoising lets Monte Carlo PDE solvers solve heat equations with nonlinear radiation boundary conditions more accurately than linearization.
Lightweight networks combine bracketed smartphone exposures as convex combinations of raw pixels to produce artifact-free HDR images that generalize from synthetic training to real captures.
GPC learns a motion vocabulary via Finite Scalar Quantization and end-to-end RL, then trains an autoregressive transformer for next-token control generation, achieving 99.98% motion reproduction success with emergent robustness.
A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
The paper surveys Indic NLP evolution and proposes 'Culture Sensing' to integrate indigenous oral knowledge into foundation models for cultural preservation.
Linkify augments assembly graphs with corrected interface point clouds and trains GATv2 for masked part prediction, outperforming non-graph baselines on Fusion 360 data.
QuadLink generates anisotropic quad-dominant meshes from point clouds via autoregressive anchor prediction and centroid-conditioned linking, with a Tri-to-Quad data converter and quad-first assembly.
citing papers explorer
-
WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata
WikiVQABench is a human-curated collection of Wikipedia-based VQA items that require both visual evidence and external knowledge from Wikidata to answer correctly.
-
BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation
BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.
-
ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
ARGUS cuts context-aware prompt-injection success from 28.8% to 3.8% on AgentLure while keeping 87.5% clean utility, beating prior defenses on the security-utility tradeoff.
-
DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media
DisImpact introduces a two-stage MLLM framework to classify disaster-related social media posts into ten impact categories and compute a unified physi-social impact index validated against FEMA and NASA ground-truth data.
-
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
A dataset-agnostic framework converts text tool-calling benchmarks to paired audio evaluations via TTS, speaker variation and noise, then evaluates seven omni-modal models showing model- and task-dependent performance with small text-to-voice gaps.
-
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
R-DMesh proposes a VAE-based disentanglement of base mesh, motion trajectories, and rectification offset plus Triflow Attention and rectified-flow diffusion to produce 4D meshes aligned to video despite initial pose mismatch.
-
Generative 3D Gaussians with Learned Density Control
DeG models 3D Gaussians via learned octree density and uses VecSeq Sobol re-indexing to turn set generation into sequence modeling, claiming SOTA quality in single-image-to-3D.
-
Relit-LiVE: Relight Video by Jointly Learning Environment Video
Relit-LiVE jointly predicts relit videos and viewpoint-aligned environment maps inside a single diffusion process to achieve physically consistent video relighting without camera pose input.
-
High-Fidelity Single-Image Head Modeling with Industry-Grade Topology
A single-image head reconstruction method uses coarse-to-fine optimization with normal consistency, landmarks, and geometry-aware constraints on curvature and conformality to produce meshes with industry-grade topology and preserved facial identity.
-
Structural MAT: Clean and Scalable Medial Axis Simplification via Explicit Surface Correspondence
A new MAT simplification algorithm uses explicit surface correspondence tracking and priority-controlled edge collapses to preserve structural features like fillet alignments on discrete meshes.
-
UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.
-
Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation
A training-free technique manipulates low-frequency noise in diffusion models to control image color and structure using low-frequency priors.
-
TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data
TTCD uses a non-stationary feature learner and reconstruction-guided distillation inside a transformer to infer contemporaneous and lagged causal graphs from non-stationary time series without strong noise assumptions.
-
Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning
LUCID detects hallucinations in LLM-KG reasoning by extracting node/edge features from attention and semantics then integrating them with KG structure in a GNN, achieving SOTA on nine new benchmark datasets versus 15 baselines.
-
Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions
A relaxed Picard iteration plus heteroscedastic boundary denoising lets Monte Carlo PDE solvers solve heat equations with nonlinear radiation boundary conditions more accurately than linearization.
-
Lucky High Dynamic Range Smartphone Imaging
Lightweight networks combine bracketed smartphone exposures as convex combinations of raw pixels to produce artifact-free HDR images that generalize from synthetic training to real captures.
-
GPC: Large-Scale Generative Pretraining for Transferable Motor Control
GPC learns a motion vocabulary via Finite Scalar Quantization and end-to-end RL, then trains an autoregressive transformer for next-token control generation, achieving 99.98% motion reproduction success with emergent robustness.
-
Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing
A new keyframe selection framework combines structural, tracking, and semantic criteria to select reliable anchor frames for diffusion-based video editing under occlusion.
-
Doppler Prompting for Stable mmWave-based Human Pose Estimation
PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.
-
TabEmb: Joint Semantic-Structure Embedding for Table Annotation
TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.
-
Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation
QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.
-
Rethinking Indic AI from a Lens of Cultural Heritage Preservation
The paper surveys Indic NLP evolution and proposes 'Culture Sensing' to integrate indigenous oral knowledge into foundation models for cultural preservation.
-
Linkify: Learning from Interface-Augmented Assembly Graphs
Linkify augments assembly graphs with corrected interface point clouds and trains GATv2 for masked part prediction, outperforming non-graph baselines on Fusion 360 data.
-
QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
QuadLink generates anisotropic quad-dominant meshes from point clouds via autoregressive anchor prediction and centroid-conditioned linking, with a Tri-to-Quad data converter and quad-first assembly.
-
Towards Interactive Multimodal Representation of ML Functions for Human Understanding of ML
Three interactive visualizations of machine learning data on transparent datasets are created to promote curiosity and reduce fear of ML among teenagers and diverse audiences.
-
Are Researchers Being Replaced by Artificial Intelligence?
AI is shifting researchers from creators to curators of generated content, risking loss of intellectual ownership and genuine understanding of science.
- Cost-of-Ethics Crisis: Beliefs, Decisions, and Justifications in the Job Searches of Computer Science Students in Canada and the United States