{"total":27,"rows":[{"id":"2511.21395","title":"Monet: Reasoning in Latent Visual Space Beyond Images and Language","created":"2025-11-26","cited_by_count":82,"area":"lr"},{"id":"2512.12623","title":"Reasoning Within the Mind: Dynamic Multimodal Interleaving in Latent Space","created":"2025-12-14","cited_by_count":28,"area":"lr"},{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2510.12603","title":"Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space","created":"2025-10-14","cited_by_count":23,"area":"lr"},{"id":"2602.01166","title":"Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models","created":"2026-02-01","cited_by_count":22,"area":"lr"},{"id":"2601.06803","title":"Forest Before Trees: Latent Superposition for Efficient Visual Reasoning","created":"2026-01-11","cited_by_count":18,"area":"lr"},{"id":"2605.22012","title":"LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning","created":"2026-05-21","cited_by_count":7,"area":"lr"},{"id":"2602.09850","title":"Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning","created":"2026-02-10","cited_by_count":6,"area":"lr"},{"id":"2602.05359","title":"Multimodal Latent Reasoning via Hierarchical Visual Cues Injection","created":"2026-02-05","cited_by_count":3,"area":"lr"},{"id":"2604.10500","title":"Visual Enhanced Depth Scaling for Multimodal Latent Reasoning","created":"2026-04-12","cited_by_count":3,"area":"lr"},{"id":"2605.12163","title":"Self-Consistent Latent Reasoning: Long Latent Sequence Reasoning for Vision-Language Model","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2606.05769","title":"Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction","created":"2026-06-04","cited_by_count":3,"area":"lr"},{"id":"2604.25299","title":"The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2605.30587","title":"ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-Language Models","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.24849","title":"IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation","created":"2026-06-23","cited_by_count":2,"area":"lr"},{"id":"2608.00743","title":"LUT: Latent Utility Training for Visual Reasoning","created":"2026-08-01","cited_by_count":2,"area":"lr"},{"id":"2511.11704","title":"Simple Vision-Language Math Reasoning via Rendered Text","created":"2025-11-12","cited_by_count":1,"area":"lr"},{"id":"2606.00562","title":"DeepLatent: Think with Images via Parallel Latent Visual Reasoning","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2607.00461","title":"Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning","created":"2026-07-01","cited_by_count":1,"area":"lr"},{"id":"2607.11106","title":"Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools","created":"2026-07-13","cited_by_count":1,"area":"lr"},{"id":"2605.28422","title":"VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2608.03450","title":"Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2608.04124","title":"Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question Answering","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2609.19878","title":"Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.38717","title":"Soft Spatial Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.05097","title":"ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.10563","title":"SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}