{"total":17,"rows":[{"id":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41,"area":"lr"},{"id":"2512.24165","title":"DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models","created":"2025-12-30","cited_by_count":19,"area":"lr"},{"id":"2604.04917","title":"Vero: An Open RL Recipe for General Visual Reasoning","created":"2026-04-06","cited_by_count":11,"area":"lr"},{"id":"2511.22586","title":"Revisiting the Necessity of Lengthy Chain-of-Thought in Vision-centric Reasoning Generalization","created":"2025-11-27","cited_by_count":8,"area":"lr"},{"id":"2511.13054","title":"ViSS-R1: Self-Supervised Reinforcement Video Reasoning","created":"2025-11-17","cited_by_count":6,"area":"lr"},{"id":"2512.04222","title":"ReasonX: MLLM-Guided Intrinsic Image Decomposition","created":"2025-12-03","cited_by_count":5,"area":"lr"},{"id":"2512.14944","title":"PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2512.12633","title":"DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model","created":"2025-12-14","cited_by_count":3,"area":"lr"},{"id":"2603.16256","title":"When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame Repetition","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2603.17693","title":"Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos","created":"2026-03-18","cited_by_count":2,"area":"lr"},{"id":"2604.20705","title":"SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models","created":"2026-04-22","cited_by_count":2,"area":"lr"},{"id":"2603.26365","title":"Dynamic Token Compression for Efficient Video Understanding through Reinforcement Learning","created":"2026-03-27","cited_by_count":1,"area":"lr"},{"id":"2604.12966","title":"Boosting Visual Instruction Tuning with Self-Supervised Guidance","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2607.27670","title":"JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2606.11918","title":"The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2610.16172","title":"EventLens: Event-Structure Reinforcement Learning for Video Understanding","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.18834","title":"Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}