1 citations · 1 across the 9 of their papers we have counts for
9 papers
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…
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…
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…
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…
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…
Unraveling Feature Extraction Mechanisms in Neural Networks
Xiaobing Sun, Jiaxi Li, Wei Lu
The underlying mechanism of neural networks in capturing precise knowledge has been the subject of consistent research efforts. In this work, we propose a theoretical approach base…
Decomposed Prompt Tuning via Low-Rank Reparameterization
Yao Xiao, Lu Xu, Jiaxi Li +2
While prompt tuning approaches have achieved competitive performance with high efficiency, we observe that they invariably employ the same initialization process, wherein the soft…
Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parsers
Jiaxi Li, Wei Lu
Recent advancements in pre-trained language models (PLMs) have demonstrated that these models possess some degree of syntactic awareness. To leverage this knowledge, we propose a n…