1 citations · 2 across the 12 of their papers we have counts for
14 papers
Smooth Scaling Laws Hide Stepwise Token Learning
Pingjie Wang, Zechen Hu, Peiru Yang +2
Language model loss follows remarkably regular scaling laws over model and data size, yet it remains unclear why the aggregate loss should exhibit a power-law form. Existing explan…
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection
Haowen Wang, Yaxin Du, Jian Yang +9
Mid-training has become an important stage in modern LLM development, using large-scale curated mixtures to strengthen capabilities before final post-training. Its data selection p…
Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs
Hongcheng Liu, Yuhao Wang, Zhe Chen +5
Omni Large Language Models (Omni-LLMs) have demonstrated impressive capabilities in holistic multi-modal perception, yet they consistently falter in complex scenarios requiring syn…
Mining Useful General Data for Low-Resource Domain Adaptation
Pingjie Wang, Hongcheng Liu, Yusheng Liao +5
Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarcity of domain-specific data. While in-domain data is limited, there exists a vast…
When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs
Hongcheng Liu, Pingjie Wang, Yuhao Wang +3
Multimodal large language models (MLLMs) have shown strong capabilities across a broad range of benchmarks. However, most existing evaluations focus on passive inference, where mod…
Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning
Siqu Ou, Hongcheng Liu, Pingjie Wang +4
While chains-of-thought (CoT) have advanced complex reasoning in multimodal large language models (MLLMs), existing methods remain confined to text or static visual domains, often…
Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selection
Ziqing Fan, Siyuan Du, Shengchao Hu +5
Selecting high-quality pre-training data for large language models (LLMs) is crucial for enhancing their overall performance under limited computation budget, improving both traini…
DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models
YiQiu Guo, Yuchen Yang, Zhe Chen +5
The reliability of large language models remains a critical challenge, particularly due to their susceptibility to hallucinations and factual inaccuracies during text generation. E…
Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
Zhe Chen, Yusheng Liao, Shuyang Jiang +4
Large language models hold promise for addressing medical challenges, such as medical diagnosis reasoning, research knowledge acquisition, clinical decision-making, and consumer he…
A Generalist Audio Foundation Model for Comprehensive Body Sound Auscultation
Pingjie Wang, Liudan Zhao, Zihan Zhao +6
Accurate and efficient auscultation-based diagnostics are vital for early disease detection, especially in resource-limited settings where specialized clinical expertise is scarce.…
HSDreport: Heart Sound Diagnosis with Echocardiography Reports
Zihan Zhao, Pingjie Wang, Liudan Zhao +7
Heart sound auscultation holds significant importance in the diagnosis of congenital heart disease. However, existing methods for Heart Sound Diagnosis (HSD) tasks are predominantl…
Reconstruct the Pruned Model without Any Retraining
Pingjie Wang, Ziqing Fan, Shengchao Hu +3
Structured pruning is a promising hardware-friendly compression technique for large language models (LLMs), which is expected to be retraining-free to avoid the enormous retraining…
M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation
Hongcheng Liu, Pingjie Wang, Yu Wang +1
Video-grounded dialogue generation (VDG) requires the system to generate a fluent and accurate answer based on multimodal knowledge. However, the difficulty in multimodal knowledge…
MSG-BART: Multi-granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-grounded Dialogue Generation
Hongcheng Liu, Zhe Chen, Hui Li +3
Generating dialogue grounded in videos requires a high level of understanding and reasoning about the visual scenes in the videos. However, existing large visual-language models ar…