{"total":20,"items":[{"citing_arxiv_id":"2606.22182","ref_index":57,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dual-Stream EEG Decoding for 3D Visual Perception","primary_cat":"cs.CV","submitted_at":"2026-06-20T18:25:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.11295","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Interpretable Neural Marked Statistics for Cosmological Inference","primary_cat":"astro-ph.CO","submitted_at":"2026-06-09T18:00:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A neural marking scheme trained with contrastive learning tightens constraints on σ8 by 2.9× and Ωm by 1.8× over classical marks at k_max=0.2 h/Mpc while breaking their degeneracy at the Fisher level.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09108","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RAM: Reachability Across Morphologies","primary_cat":"cs.RO","submitted_at":"2026-06-08T07:00:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"RAM is a morphology-conditioned implicit neural representation trained on 3e10 forward-kinematics samples that serves as a fast, differentiable surrogate for pose reachability and generalizes to unseen morphologies while accounting for self-collisions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07399","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Automatic, Debiased, and Invariant Counterfactual Generation under General Interventions","primary_cat":"stat.ML","submitted_at":"2026-06-05T15:40:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ADIGen generates counterfactuals under general interventions via Riesz regression, causal invariance, and orthogonal learning, with excess-risk bounds featuring product-bias remainder and invariant risk across environments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03909","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation","primary_cat":"cs.CV","submitted_at":"2026-06-02T17:06:14+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SparseStreet applies node-based learnable pruning followed by static background compression to 3D Gaussian Splatting, reporting up to 80% reduction in primitives with minimal quality loss on Waymo and nuScenes street scene data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03420","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PHAF-Personalized Hand Avatars in a Flash","primary_cat":"cs.CV","submitted_at":"2026-06-02T10:05:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A method to generate personalized hand avatars from two views in a fraction of the time of optimization-based approaches.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.02096","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos","primary_cat":"cs.CV","submitted_at":"2026-06-01T11:28:17+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"WebSpline uses learnable cubic Hermite splines guided by a Structural Proxy Graph to deliver state-of-the-art quality dynamic 3D Gaussian rendering from monocular videos at over 10x the speed of prior methods on iPhone and NVIDIA benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.23888","ref_index":27,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","primary_cat":"cs.CV","submitted_at":"2026-05-22T17:49:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GenRecon lifts object-level generative priors to scene-scale reconstruction by chunking scenes and using projection-based conditioning on multi-view features, claiming 16% better results than prior methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09989","ref_index":61,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","primary_cat":"cs.RO","submitted_at":"2026-05-11T05:06:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Kong, J. Cen, R. Chen, W. Zhang, L. Pan, K. Chen, and Z. Liu. Segment any point cloud sequences by distilling vision foundation models, 2023. URLhttps://arxiv.org/ abs/2306.09347. [60] A. Haque, M. Tancik, A. A. Efros, A. Holynski, and A. Kanazawa. Instruct-nerf2nerf: Editing 3d scenes with instructions, 2023. URLhttps://arxiv.org/abs/2303.12789. [61] K. Liu, F. Zhan, J. Zhang, M. Xu, Y . Yu, A. E. Saddik, C. Theobalt, E. Xing, and S. Lu. Weakly supervised 3d open-vocabulary segmentation, 2024. URLhttps://arxiv.org/abs/2305. 14093. [62] J. Min, Y . Jeon, J. Kim, and M. Choi. S2M2: Scalable stereo matching model for reliable depth estimation, 2025. URLhttps://arxiv.org/abs/2507.13229. [63] L. Bartolomei, F."},{"citing_arxiv_id":"2605.09606","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models","primary_cat":"cs.CR","submitted_at":"2026-05-10T15:35:42+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Image-to-3D models successfully generate harmful geometries in most cases with under 0.3% caught by commercial filters; existing safeguards are weak but a stacked defense cuts harmful outputs to under 1% at 11% false-positive cost.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"This family instantiatesdeceptive replicas: visually realistic geometry that supports intimidation or de- ception. The UK Violent Crime Reduction Act prohibits manufacture of Realistic Imitation Firearms [28]; U.S. fed- eral law requires imitation firearms to carry a blaze orange tip [7]; China bans replicas matching the color and contour of military firearms [24]. We collect three cases: real firearms, toy guns, and sci-fi guns-the latter two to test whether models suppress toy-like appearance and default to generat- ing visually realistic non-compliant replicas. Our evaluation specifically examines whether the model defaults to generat- ing visually realistic non-compliant weapon-like replicas. Prototype Set"},{"citing_arxiv_id":"2605.07894","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SpatialPrompt: XR-Based Spatial Intent Expression as Executable Constraints for AI Generative 3D Design","primary_cat":"cs.HC","submitted_at":"2026-05-08T15:38:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"SpatialPrompt turns spatial sketches and voice prompts into executable constraints for controllable AI 3D generation in XR, enabling iterative collaborative creation with color-coded contributions.","context_count":1,"top_context_role":"other","top_context_polarity":"unclear","context_text":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts. (2022). arXiv:2212.08751 [cs.CV] doi:10.48550/arXiv.2212.08751 [17] Jakob Nielsen. 1994. Heuristic Evaluation. InUsability Inspection Methods, Jakob Nielsen and Robert L. Mack (Eds.). John Wiley & Sons, Inc., New York, NY, USA, 25-62. https://dl.acm.org/doi/10.5555/189200.189209 [18] Jakob Nielsen and Thomas K. Landauer. 1993. A Mathematical Model of the Finding of Usability Problems. InProceedings of the INTERACT '93 and CHI '93 Conference on Human Factors in Computing Systems. 206-213. doi:10.1145/169059. 169166 [19] Ben Poole, Ajay Jain, Jonathan T. Barron, et al. 2022. DreamFusion: Text-to-3D using 2D Diffusion.arXiv preprint arXiv:2209."},{"citing_arxiv_id":"2604.21400","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes","primary_cat":"cs.CV","submitted_at":"2026-04-23T08:07:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17211","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents","primary_cat":"cs.CV","submitted_at":"2026-04-19T02:43:00+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"EmbodiedHead introduces a Rectified-Flow Diffusion Transformer with differentiable renderer and single-stream listening-speaking conditioning to achieve real-time high-fidelity conversational avatars.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12626","ref_index":16,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting","primary_cat":"cs.RO","submitted_at":"2026-04-14T11:52:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Habitat-GS integrates 3D Gaussian Splatting scene rendering and Gaussian avatars into Habitat-Sim, yielding agents with stronger cross-domain generalization and effective human-aware navigation.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Habitat-GS inherits the Habitat ecosystem's high-performance infrastructure and training APIs while upgrading the rendering pipeline from mesh to 3DGS and natively integrating drivable gaussian avatars, uniquely combining photo- realistic rendering, dynamic high-fidelity humanoids, and a mature open-source research ecosystem. 2.2 Neural Rendering Neural Radiance Fields (NeRF) [16] demonstrated that implicit neural scene representations can synthesize photorealistic novel views from multi-view im- ages.Subsequentworkssignificantlyimprovedtrainingspeedandrenderingqual- ity [2,17]. However, NeRF's volume rendering paradigm requires per-pixel ray marching, yielding frame rates far below the real-time requirements of embodied Habitat-GS 5"},{"citing_arxiv_id":"2604.07177","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Splats under Pressure: Exploring Performance-Energy Trade-offs in Real-Time 3D Gaussian Splatting under Constrained GPU Budgets","primary_cat":"cs.GR","submitted_at":"2026-04-08T15:05:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Emulation of constrained GPUs reveals performance-energy trade-offs for real-time 3D Gaussian Splatting on edge devices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06475","ref_index":24,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"AE-ViT: Stable Long-Horizon Parametric Partial Differential Equations Modeling","primary_cat":"cs.LG","submitted_at":"2026-04-07T21:19:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"AE-ViT combines a convolutional autoencoder with a latent-space transformer and multi-stage parameter plus coordinate injection to deliver stable long-horizon predictions for parametric PDEs, cutting relative rollout error by roughly five times versus prior DL-ROMs and ViTs on advection-diffusion-re","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.06358","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GS-Surrogate: Deformable Gaussian Splatting for Parameter Space Exploration of Ensemble Simulations","primary_cat":"cs.GR","submitted_at":"2026-04-07T18:37:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"GS-Surrogate creates a canonical Gaussian field that is sequentially deformed by simulation parameters to enable real-time, controllable 3D exploration of ensemble data while separating simulation variations from visualization adjustments.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Existing approaches for parameter-space exploration of ensemble simulations fall into two main categories. The first one relies on stan- dard high-dimensional data visualization techniques applied directly to collected ensemble inputs and outputs. Parallel coordinates [27, 33], scatter plots [25, 28], radial plots [10, 14], glyphs [9], and matrix-based views [29] have all been used to analyze relationships across ensemble members. A fundamental limitation shared by all these methods is that analysis remains confined to parameter configurations that were explicitly simulated. The second category, including our GS-Surrogate, uses surrogate models to predict outcomes at new, unsampled parameter configurations, extending exploration beyond the limits of the collected"},{"citing_arxiv_id":"2603.08096","ref_index":26,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization","primary_cat":"cs.CV","submitted_at":"2026-03-09T08:37:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2309.16797","ref_index":232,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","primary_cat":"cs.CL","submitted_at":"2023-09-28T19:01:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2305.02463","ref_index":40,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Shap-E: Generating Conditional 3D Implicit Functions","primary_cat":"cs.CV","submitted_at":"2023-05-03T23:59:13+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}