activity
20212026
most citedNeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes

14 citations · 42 across the 21 of their papers we have counts for

collaborators
Showing cs.LGShow all

14 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

-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…

cs.LG2026

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…

cs.LG2025

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…