{"total":20,"rows":[{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736,"area":"lr"},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451,"area":"lr"},{"id":"2406.09403","title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models","created":"2024-06-13","cited_by_count":268,"area":"lr"},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"id":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2411.19488","title":"Interleaved-Modal Chain-of-Thought","created":"2024-11-29","cited_by_count":51,"area":"lr"},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44,"area":"lr"},{"id":"2503.19312","title":"ImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning","created":"2025-03-25","cited_by_count":37,"area":"lr"},{"id":"2503.13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2025-03-17","cited_by_count":18,"area":"lr"},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2506.05328","title":"AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs","created":"2025-06-05","cited_by_count":16,"area":"lr"},{"id":"2508.05954","title":"Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents","created":"2025-08-08","cited_by_count":8,"area":"lr"},{"id":"2508.18032","title":"Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation","created":"2025-08-25","cited_by_count":5,"area":"lr"},{"id":"2403.07720","title":"Multi-modal Auto-regressive Modeling via Visual Words","created":"2024-03-12","cited_by_count":4,"area":"lr"},{"id":"2406.18925","title":"Selective Vision is the Challenge for Visual Reasoning: A Benchmark for Visual Argument Understanding","created":"2024-06-27","cited_by_count":3,"area":"lr"},{"id":"2604.24625","title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","created":"2026-04-27","cited_by_count":3,"area":"lr"},{"id":"2605.04040","title":"Large Language Models are Universal Reasoners for Visual Generation","created":"2026-05-05","cited_by_count":1,"area":"lr"},{"id":"2607.23445","title":"Omni-Prune: Query-Aware Unified Token Pruning for Efficient Omnimodal Large Language Models","created":"2026-07-26","cited_by_count":1,"area":"lr"},{"id":"2608.14179","title":"Can Language Models Understand mmWave Data? Benchmarking Large Language Models for mmWave Radar-Based Human Understanding","created":"2026-08-14","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"}],"next_cursor":null}