collaborators

7 papers

cs.AI2026

Action Conditioned Bisimulation For GUI Agent Memory

Hongbo Zhang, Liuyang Song, Quanquan Li +3

An agent that remembers what it did on a web page must decide when two pages count as the same. Memories built on observation similarity merge pages that look alike but behave diff…

cs.CV2026

Query Independent Variable Rate Visual Token Coding

Hongbo Zhang, Zihao Yang, Liuyang Song +4

Visual-token compression for vision--language models is posed almost entirely as a selection problem: decide which tokens to keep and discard the rest. The criteria that work best…

cs.CL2026

When Successful Memories Mislead Embodied Agents:Memory Adaption For Task-Conditioned Execution

Quanquan Li, Hongbo Zhang, Yihe Chi +5

Experience reuse can reduce repeated exploration in embodied agents, but a trajectory that succeeded previously may be unsuitable for the current execution context. Existing memory…

cs.CV2026

BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring

Liuyang Song, Yi Zhang, Zhongyi Deng +2

Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which region or how those regions are a…

q-bio.MN2026

Control-Anchored Residual Flow Matching Conditioned on Gene Geometry for Virtual Cell Perturbation Modeling

Quanquan Li, Yihe Chi, Liuyang Song +10

A central task in virtual cell modeling is predicting single-cell transcriptional responses to unseen genetic perturbations and drug combinations, and biological networks provide v…

cs.CL2026

FutureBridge: Token Selection Beyond Local Preference in Collaborative Decoding

Quanquan Li, Hongbo Zhang, Yihe Chi +9

Token-level collaboration allows a large language model (LLM) to assist a small language model (SLM) when their predictions diverge. Existing methods either use LLM-generated inter…

cs.LG2026

AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

Shengyang Li, Yiting Dong, Liuyang Song +5

Federated learning enables collaborative model training across distributed edge devices while strictly preserving data privacy. To facilitate practical deployment on resource-const…