6 papers
ICRL: Learning to Internalize Self-Critique with Reinforcement Learning
Jianbo Lin, Xiaomin Yu, Yi Xin +7
Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on…
FURINA: A Fully Customizable Role-Playing Benchmark via Scalable Multi-Agent Collaboration Pipeline
Haotian Wu, Shufan Jiang, Chios Chen +5
As large language models (LLMs) advance in role-playing (RP) tasks, existing benchmarks quickly become obsolete due to their narrow scope, outdated interaction paradigms, and limit…
Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph
Wentao Wang, Heqing Zou, Tianze Luo +8
Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated strong semantic understanding capabilities, but struggles to perform precise spatio-temporal understand…
Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
Ruizhe Chen, Zhiting Fan, Tianze Luo +7
Video Temporal Grounding (VTG) aims to localize relevant temporal segments in videos given natural language queries. Despite recent progress with large vision-language models (LVLM…
HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding
Heqing Zou, Tianze Luo, Guiyang Xie +7
Multimodal large language models have become a popular topic in deep visual understanding due to many promising real-world applications. However, hour-long video understanding, spa…
Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages
Heqing Zou, Fengmao Lv, Desheng Zheng +2
Multilingual speech emotion recognition aims to estimate a speaker's emotional state using a contactless method across different languages. However, variability in voice characteri…