{"total":18,"rows":[{"id":"2410.16198","title":"Improve Vision Language Model Chain-of-thought Reasoning","created":"2024-10-21","cited_by_count":136,"area":"lr"},{"id":"2412.05237","title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","created":"2024-12-06","cited_by_count":127,"area":"lr"},{"id":"2505.03318","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","created":"2025-05-06","cited_by_count":90,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2504.16656","title":"Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning","created":"2025-04-23","cited_by_count":49,"area":"lr"},{"id":"2410.06166","title":"Temporal Reasoning Transfer from Text to Video","created":"2024-10-08","cited_by_count":38,"area":"lr"},{"id":"2511.00405","title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings","created":"2025-11-01","cited_by_count":38,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2502.11775","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","created":"2025-02-17","cited_by_count":24,"area":"lr"},{"id":"2503.21819","title":"Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach","created":"2025-03-26","cited_by_count":24,"area":"lr"},{"id":"2504.03151","title":"Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)","created":"2025-04-04","cited_by_count":23,"area":"lr"},{"id":"2504.00640","title":"POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation","created":"2025-04-01","cited_by_count":22,"area":"lr"},{"id":"2501.01426","title":"Unifying Specialized Visual Encoders for Video Language Models","created":"2025-01-02","cited_by_count":10,"area":"lr"},{"id":"2606.13061","title":"LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck","created":"2026-06-11","cited_by_count":5,"area":"lr"},{"id":"2605.14448","title":"Think When Needed: Adaptive Reasoning-Driven Multimodal Embeddings with a Dual-LoRA Architecture","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2508.08275","title":"MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis","created":"2025-07-31","cited_by_count":2,"area":"lr"},{"id":"2602.02341","title":"LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2603.10370","title":"GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning","created":"2026-03-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}