{"total":22,"items":[{"citing_arxiv_id":"2605.23192","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing","primary_cat":"cs.CV","submitted_at":"2026-05-22T03:19:24+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.21479","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"WikiVQABench: A Knowledge-Grounded Visual Question Answering Benchmark from Wikipedia and Wikidata","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:58:24+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"WikiVQABench is a human-curated collection of Wikipedia-based VQA items that require both visual evidence and external knowledge from Wikidata to answer correctly.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20646","ref_index":23,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"DisImpact: Quantifying the Physi-Social Impact of Natural Disasters Through Social Media","primary_cat":"cs.SI","submitted_at":"2026-05-20T03:09:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.19411","ref_index":23,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"BrepForge: Factorized B-rep Synthesis via Wireframe Composition and Boundary-Conditioned Surface Instantiation","primary_cat":"cs.GR","submitted_at":"2026-05-19T06:04:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"BrepForge factorizes B-rep synthesis into face-aware autoregressive wireframe composition followed by boundary-conditioned surface instantiation using learning-free geometric priors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16813","ref_index":26,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","primary_cat":"cs.GR","submitted_at":"2026-05-16T05:04:10+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.15104","ref_index":200,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","primary_cat":"cs.CL","submitted_at":"2026-05-14T17:22:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13838","ref_index":23,"ref_count":2,"confidence":0.55,"is_internal_anchor":false,"paper_title":"R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow","primary_cat":"cs.CV","submitted_at":"2026-05-13T17:58:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"R-DMesh generates high-fidelity 4D meshes aligned to video by disentangling base mesh, motion, and a learned rectification jump offset inside a VAE, then using Triflow Attention and rectified-flow diffusion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13233","ref_index":111,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Doppler Prompting for Stable mmWave-based Human Pose Estimation","primary_cat":"cs.HC","submitted_at":"2026-05-13T09:24:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PULSE stabilizes mmWave human pose estimation by screening Doppler motion prompts before injecting them into spatial magnitude reasoning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09680","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Cost-of-Ethics Crisis: Beliefs, Decisions, and Justifications in the Job Searches of Computer Science Students in Canada and the United States","primary_cat":"cs.CY","submitted_at":"2026-05-10T17:58:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"CS students and recent grads prioritize pay and workplace culture over ethics in job searches and justify conflicting decisions with shared explanations such as money or lack of alternatives.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16355","ref_index":103,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Generative 3D Gaussians with Learned Density Control","primary_cat":"cs.GR","submitted_at":"2026-05-08T17:54:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06658","ref_index":23,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Relit-LiVE: Relight Video by Jointly Learning Environment Video","primary_cat":"cs.CV","submitted_at":"2026-05-07T17:58:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.04524","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"High-Fidelity Single-Image Head Modeling with Industry-Grade Topology","primary_cat":"cs.CV","submitted_at":"2026-05-06T06:07:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.03378","ref_index":45,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection","primary_cat":"cs.CR","submitted_at":"2026-05-05T05:37:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ARGUS defends LLM agents from context-aware prompt injections by tracking information provenance and verifying decisions against trustworthy evidence, reducing attack success to 3.8% while retaining 87.5% task utility.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02302","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Structural MAT: Clean and Scalable Medial Axis Simplification via Explicit Surface Correspondence","primary_cat":"cs.GR","submitted_at":"2026-05-04T07:51:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00658","ref_index":173,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","primary_cat":"cs.CV","submitted_at":"2026-05-01T13:40:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"UniVidX unifies diverse video generation tasks into one conditional diffusion model using stochastic condition masking, decoupled gated LoRAs, and cross-modal self-attention.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00548","ref_index":23,"ref_count":2,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Colorful-Noise: Training-Free Low-Frequency Noise Manipulation for Color-Based Conditional Image Generation","primary_cat":"cs.CV","submitted_at":"2026-05-01T10:02:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A training-free technique manipulates low-frequency noise in diffusion models to control image color and structure using low-frequency priors.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08111","ref_index":35,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"TTCD:Transformer Integrated Temporal Causal Discovery from Non-Stationary Time Series Data","primary_cat":"cs.LG","submitted_at":"2026-04-27T19:44:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21717","ref_index":105,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Monte Carlo PDE Solvers for Nonlinear Radiative Boundary Conditions","primary_cat":"cs.GR","submitted_at":"2026-04-22T04:26:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19976","ref_index":75,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Lucky High Dynamic Range Smartphone Imaging","primary_cat":"cs.CV","submitted_at":"2026-04-21T20:35:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"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.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18939","ref_index":175,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"TabEmb: Joint Semantic-Structure Embedding for Table Annotation","primary_cat":"cs.LG","submitted_at":"2026-04-21T00:25:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"TabEmb decouples LLM-based semantic column embeddings from graph-based structural modeling to produce joint representations that improve table annotation tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17325","ref_index":21,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation","primary_cat":"cs.CL","submitted_at":"2026-04-19T08:39:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"QREAM rewrites documents to question-focused style using iterative ICL and distilled FT models, boosting RAG performance by up to 8% relative improvement.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.16294","ref_index":29,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Are Researchers Being Replaced by Artificial Intelligence?","primary_cat":"cs.CY","submitted_at":"2026-04-14T19:07:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"AI is shifting researchers from creators to curators of generated content, risking loss of intellectual ownership and genuine understanding of science.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}