2 citations · 3 across the 11 of their papers we have counts for
11 papers
Learning When Visual Context Matters for Mouse Behavior Analysis
Weihan Li, Jingyang Ke, Yule Wang +3
Understanding mouse behavior at scale is a foundational problem in neuroscience, with two core tasks: classifying frames into known behaviors and segmenting recordings into recurri…
OnlineX: Unified Online 3D Reconstruction and Understanding with Active-to-Stable State Evolution
Chong Xia, Fangfu Liu, Yule Wang +2
Recent advances in generalizable 3D Gaussian Splatting (3DGS) have enabled rapid 3D scene reconstruction within seconds, eliminating the need for per-scene optimization. However, e…
WavBench: Benchmarking Reasoning, Colloquialism, and Paralinguistics for End-to-End Spoken Dialogue Models
Yangzhuo Li, Shengpeng Ji, Yifu Chen +6
With the rapid integration of advanced reasoning capabilities into spoken dialogue models, the field urgently demands benchmarks that transcend simple interactions to address real-…
A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivity
Chengrui Li, Yunmiao Wang, Yule Wang +3
Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity. Although their functional conn…
Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusion
Yule Wang, Joseph Yu, Chengrui Li +2
Understanding how neural populations in higher visual areas encode object-centered visual information remains a central challenge in computational neuroscience. Prior works have in…
A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement
Chengrui Li, Yunmiao Wang, Yule Wang +3
A fully disentangled variational auto-encoder (VAE) aims to identify disentangled latent components from observations. However, enforcing full independence between all latent compo…
Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
Yule Wang, Chengrui Li, Weihan Li +1
Understanding the neural basis of behavior is a fundamental goal in neuroscience. Current research in large-scale neuro-behavioral data analysis often relies on decoding models, wh…
Learning Time-Varying Multi-Region Brain Communications via Scalable Markovian Gaussian Processes
Weihan Li, Yule Wang, Chengrui Li +1
Understanding and constructing brain communications that capture dynamic communications across multiple regions is fundamental to modern system neuroscience, yet current methods st…
A Differentiable Partially Observable Generalized Linear Model with Forward-Backward Message Passing
Chengrui Li, Weihan Li, Yule Wang +1
The partially observable generalized linear model (POGLM) is a powerful tool for understanding neural connectivity under the assumption of existing hidden neurons. With spike train…
Multi-Region Markovian Gaussian Process: An Efficient Method to Discover Directional Communications Across Multiple Brain Regions
Weihan Li, Chengrui Li, Yule Wang +1
Studying the complex interactions between different brain regions is crucial in neuroscience. Various statistical methods have explored the latent communication across multiple bra…
Forward Divergence Based Variational Importance Sampling
Chengrui Li, Yule Wang, Weihan Li +1
Maximizing the log-likelihood is a crucial aspect of learning latent variable models, and variational inference (VI) stands as the commonly adopted method. However, VI can encounte…