6 papers
Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing
Yujuan Pang, Jiaxin Li, Xin Sheng +2
Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks. Prior work shows RLVR works with few…
Building a Precise Video Language with Human-AI Oversight
Zhiqiu Lin, Chancharik Mitra, Siyuan Cen +13
Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable ov…
MOVA: Towards Scalable and Synchronized Video-Audio Generation
OpenMOSS Team, Donghua Yu, Mingshu Chen +38
Audio is indispensable for real-world video, yet generation models have largely overlooked audio components. Current approaches to producing audio-visual content often rely on casc…
Through the Valley: Path to Effective Long CoT Training for Small Language Models
Renjie Luo, Jiaxi Li, Chen Huang +1
Long chain-of-thought (CoT) supervision has become a common strategy to enhance reasoning in language models. While effective for large models, we identify a phenomenon we call Lon…
StreamForest: Efficient Online Video Understanding with Persistent Event Memory
Xiangyu Zeng, Kefan Qiu, Qingyu Zhang +9
Multimodal Large Language Models (MLLMs) have recently achieved remarkable progress in video understanding. However, their effectiveness in real-time streaming scenarios remains li…
WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale
Jiaxi Li, Xingxing Zhang, Xun Wang +6
Large language models (LLMs) with extended context windows enable tasks requiring extensive information integration but are limited by the scarcity of high-quality, diverse dataset…