{"work":{"id":"ef2c21b6-ae25-436a-bac3-f8d625541320","openalex_id":null,"doi":null,"arxiv_id":"2503.13377","raw_key":null,"title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","authors":null,"authors_text":"Ye Wang, Ziheng Wang, Boshen Xu, Yang Du, Kejun Lin, Zihan Xiao","year":2025,"venue":"cs.CV","abstract":"Temporal Video Grounding (TVG), the task of locating specific video segments based on language queries, is a core challenge in long-form video understanding. While recent Large Vision-Language Models (LVLMs) have shown early promise in tackling TVG through supervised fine-tuning (SFT), their abilities to generalize remain limited. To address this, we propose a novel post-training framework that enhances the generalization capabilities of LVLMs via reinforcement learning (RL). Specifically, our contributions span three key directions: (1) Time-R1: we introduce a reasoning-guided post-training framework via RL with verifiable reward to enhance the capabilities of LVLMs on the TVG task. (2) TimeRFT: we explore data-efficient post-training strategies on our curated RL-friendly dataset, which trains the model to progressively comprehend difficult samples, leading to better generalization. (3) TVGBench: we carefully construct a small yet comprehensive benchmark for LVLM evaluation, assessing 11 types of queries and featuring balanced distributions across both videos and queries. Extensive experiments demonstrate that Time-R1 achieves state-of-the-art performance across multiple downstream datasets using only 2.5K training data, while improving its general video understanding capabilities.","external_url":"https://arxiv.org/abs/2503.13377","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-04T03:29:31.223272+00:00","pith_arxiv_id":"2503.13377","created_at":"2026-05-10T03:29:21.544201+00:00","updated_at":"2026-07-04T03:29:31.223272+00:00","title_quality_ok":true,"display_title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding","render_title":"Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding"},"hub":{"state":{"work_id":"ef2c21b6-ae25-436a-bac3-f8d625541320","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":35,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-02-24T18:50:52+00:00","last_pith_cited_at":"2026-07-01T09:18:59+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-07-04T09:26:42.292835+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":9}],"polarity_counts":[{"context_polarity":"background","n":9}],"runs":{},"summary":{},"graph":{},"authors":[]}}