We present LOVER, a \underline{L}ong to sh\underline{O}rt \underline{V}ideo \underline{E}vidence \underline{R}einforced model for grounded question answering (GQA). LOVER highlights three innovations over existing reinforcement-learning (RL) based video reasoning models: (1) \textbf{Long-to-short Video Evidence Curricu...
Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities account for success or failure. Each task requires recovering spatial evidence, representing geometry, and reasoning over it. We disentangle these capabilities by comparin...
Peng-Zhan Sun, Jun-Bin Xiao, Ramanathan Rajaraman et al.· 0 citations
Rita is proposed as a novel RL paradigm that performs consistently superior to the supervised finetuning approaches and vanilla RL-finetuned frameworks and adopts a difficulty-aware data filtering strategy that selects informative easy-to-medium samples for RL using rollout error rate and reward variance.
Peng-Zhan Sun, Shiu-hong Kao, Shi-Jie Li et al.· 1 citation
Experiments show that MyBuddy significantly enhances the performance of foundation models on BuddyVQA, a benchmark for companion-style question answering (QA) on egocentric streaming video, and generalize to other streaming and common video QA benchmarks, demonstrating the applicability and effectiveness of the approac...
Hangyu Qin, Jun-Bin Xiao, Sheng Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.