1 citations · 1 across the 8 of their papers we have counts for
10 papers
Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL
Qinwei Ma, Jingzhe Shi, Simin Fan +3
ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in ELBO-based RL has large impact…
Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting
Qinwei Ma, Jingzhe Shi, Jiahao Qiu +1
Recent work has questioned the effectiveness and robustness of neural network architectures for time series forecasting tasks. We summarize these concerns and analyze groundly thei…
PRISM-Physics: Causal DAG-Based Process Evaluation for Physics Reasoning
Wanjia Zhao, Qinwei Ma, Jingzhe Shi +7
Benchmarks for competition-style reasoning have advanced evaluation in mathematics and programming, yet physics remains comparatively explored. Most existing physics benchmarks eva…
ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Hanyang Chen, Mark Zhao, Rui Yang +15
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However…
Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
Kaisen Yang, Tinghe Zhang, Rushi Shah +4
Many LLMs plan before they act, yet planning and execution are often still entangled in one long generation trace, enforced only through prompts, or split across separate component…
Gradient Imbalance in Direct Preference Optimization
Qinwei Ma, Jingzhe Shi, Can Jin +3
Direct Preference Optimization (DPO) has been proposed as a promising alternative to Proximal Policy Optimization (PPO) based Reinforcement Learning with Human Feedback (RLHF). How…
Intrinsic Entropy of Context Length Scaling in LLMs
Jingzhe Shi, Qinwei Ma, Hongyi Liu +3
Long Context Language Models have drawn great attention in the past few years. There has been work discussing the impact of long context on Language Model performance: some find th…
RapVerse: Coherent Vocals and Whole-Body Motions Generations from Text
Jiaben Chen, Xin Yan, Yihang Chen +7
In this work, we introduce a challenging task for simultaneously generating 3D holistic body motions and singing vocals directly from textual lyrics inputs, advancing beyond existi…
Scaling Law for Time Series Forecasting
Jingzhe Shi, Qinwei Ma, Huan Ma +1
Scaling law that rewards large datasets, complex models and enhanced data granularity has been observed in various fields of deep learning. Yet, studies on time series forecasting…
CHOPS: CHat with custOmer Profile Systems for Customer Service with LLMs
Jingzhe Shi, Jialuo Li, Qinwei Ma +3
Businesses and software platforms are increasingly turning to Large Language Models (LLMs) such as GPT-3.5, GPT-4, GLM-3, and LLaMa-2 for chat assistance with file access or as rea…