32 citations · 157 across the 45 of their papers we have counts for
48 papers
Disentangling Task-Relevant Latent Dynamics for Reward Modeling
Dayou Li, Jionghao Wang, Peihao Wang +9
Reward design remains a major bottleneck for reinforcement learning in robotic manipulation. Handcrafted dense rewards can compensate for the limited guidance provided by sparse re…
Revisiting Spectral Representations in Generative Diffusion Models
Yuehao Wang, Peihao Wang, Hanwen Jiang +3
Diffusion models have shown remarkable performance on diverse generation tasks. Recent work finds that imposing representation alignment on the hidden states of diffusion networks…
FUSE: FK-Steered Multi-Modal Flow Matching for Efficient Simulation-Based Posterior Estimation
Weichen Qin, Yufan Xie, Peihao Wang +8
Simulation-Based Inference (SBI) is critical for scientific discovery, with generative models offering a promising path toward efficient inference. However, existing methods strugg…
When Do Graph Foundation Models Transfer? A Data-Centric Theory
Jiajun Zhu, Ying Chen, Peihao Wang +4
Graph foundation models (GFMs) aim to reuse a single backbone across diverse graph domains, yet their transfer is often uneven and can exhibit negative transfer. While most prior w…
-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Latent Space
Peihao Wang, Ruisi Cai, Zhen Wang +4
Scaling inference-time compute for Large Language Models (LLMs) has unlocked unprecedented reasoning capabilities. However, existing inference-time scaling methods typically rely o…
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
Peihao Wang, Shan Yang, Xijun Wang +8
Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability…
Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation for Neurosymbolic Reasoning
Peihao Wang, Zhangyang Wang
We develop a theoretical framework that explains how discrete symbolic structures can emerge naturally from continuous neural network training dynamics. By lifting neural parameter…
FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
Hengyu Liu, Yuehao Wang, Chenxin Li +6
3D Gaussian splatting (3DGS) has enabled various applications in 3D scene representation and novel view synthesis due to its efficient rendering capabilities. However, 3DGS demands…
Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models
Haoyu Wang, Peihao Wang, Mufei Li +4
Modern large language models (LLMs) are inherently auto-regressive, requiring input to be serialized into flat sequences regardless of their structural dependencies. This serializa…
CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy
Jiakai Zhang, Shouchen Zhou, Haizhao Dai +5
Pose estimation from unordered images is fundamental for 3D reconstruction, robotics, and scientific imaging. Recent geometric foundation models, such as DUSt3R, enable end-to-end…
Steepest Descent Density Control for Compact 3D Gaussian Splatting
Peihao Wang, Yuehao Wang, Dilin Wang +8
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time, high-resolution novel view synthesis. By representing scenes as a mixture of Gaussian primitives, 3D…
Can Test-Time Scaling Improve World Foundation Model?
Wenyan Cong, Hanqing Zhu, Peihao Wang +7
World foundation models, which simulate the physical world by predicting future states from current observations and inputs, have become central to many applications in physical in…
Rethinking Addressing in Language Models via Contexualized Equivariant Positional Encoding
Jiajun Zhu, Peihao Wang, Ruisi Cai +3
Transformers rely on both content-based and position-based addressing mechanisms to make predictions, but existing positional encoding techniques often diminish the effectiveness o…
Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing
Peihao Wang, Ruisi Cai, Yuehao Wang +4
Structured State Space Models (SSMs) have emerged as alternatives to transformers. While SSMs are often regarded as effective in capturing long-sequence dependencies, we rigorously…
Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method
Yan Zheng, Zhenxiao Liang, Xiaoyan Cong +4
We explore the oscillatory behavior observed in inversion methods applied to large-scale text-to-image diffusion models, with a focus on the "Flux" model. By employing a fixed-poin…
Large Spatial Model: End-to-end Unposed Images to Semantic 3D
Zhiwen Fan, Jian Zhang, Wenyan Cong +10
Reconstructing and understanding 3D structures from a limited number of images is a well-established problem in computer vision. Traditional methods usually break this task into mu…
Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Ruisi Cai, Yeonju Ro, Geon-Woo Kim +4
The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved e…
Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity
Jinze Zhao, Peihao Wang, Junjie Yang +6
Sparse Mixture-of-Experts (SMoE) architectures have gained prominence for their ability to scale neural networks, particularly transformers, without a proportional increase in comp…
Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
Xinyu Zhao, Guoheng Sun, Ruisi Cai +13
As Large Language Models (LLMs) excel across tasks and specialized domains, scaling LLMs based on existing models has garnered significant attention, which faces the challenge of d…
Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
Mukund Varma T, Peihao Wang, Zhiwen Fan +3
In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image…
Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study
Jinze Zhao, Peihao Wang, Zhangyang Wang
Mixture-of-Experts (MoE) represents an ensemble methodology that amalgamates predictions from several specialized sub-models (referred to as experts). This fusion is accomplished t…
Taming Mode Collapse in Score Distillation for Text-to-3D Generation
Peihao Wang, Dejia Xu, Zhiwen Fan +8
Despite the remarkable performance of score distillation in text-to-3D generation, such techniques notoriously suffer from view inconsistency issues, also known as "Janus" artifact…
SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity
Peihao Wang, Zhiwen Fan, Dejia Xu +8
Score distillation has emerged as one of the most prevalent approaches for text-to-3D asset synthesis. Essentially, score distillation updates 3D parameters by lifting and back-pro…
Meta ControlNet: Enhancing Task Adaptation via Meta Learning
Junjie Yang, Jinze Zhao, Peihao Wang +2
Diffusion-based image synthesis has attracted extensive attention recently. In particular, ControlNet that uses image-based prompts exhibits powerful capability in image tasks such…