{"total":4,"items":[{"citing_arxiv_id":"2606.28049","ref_index":27,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"AirGroundBench: Probing Spatial Intelligence in Multimodal Large Models under Heterogeneous Multi-View Embodied Collaboration","primary_cat":"cs.CV","submitted_at":"2026-06-26T12:51:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AirGroundBench is a new diagnostic benchmark exposing that MLLMs handle basic spatial perception but struggle with cross-view alignment, transformation reasoning, and embodied navigation under heterogeneous air-ground views.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22182","ref_index":98,"ref_count":1,"confidence":0.88,"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":"2605.18445","ref_index":14,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"What's Holding Back Latent Visual Reasoning?","primary_cat":"cs.CV","submitted_at":"2026-05-18T14:14:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Latent visual reasoning fails in current models because standard datasets make oracle latents uninformative and inference-time latents collapse away from useful representations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.23108","ref_index":73,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Artificial Phantasia: Emergent Mental Imagery in Large Language Models","primary_cat":"cs.AI","submitted_at":"2025-09-27T04:36:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLMs achieve higher accuracy than humans on compositional imagery tasks previously argued to require pictorial representations, supporting emergent propositional mental imagery in AI.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}