collaborators

7 papers

cs.SE2026

ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents

Youjin Wang, Run Zhou, Yingjie Ma +6

Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy to deploy but often fragile under distr…

cs.LG2026

SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes

Rong Fu, Muge Qi, Yang Li +11

Repertoire-level analysis of T cell receptors offers a biologically grounded signal for disease detection and immune monitoring, yet practical deployment is impeded by label sparsi…

cs.CR2026

zkCraft: Prompt-Guided LLM as a Zero-Shot Mutation Pattern Oracle for TCCT-Powered ZK Fuzzing

Rong Fu, Jia Yee Tan, Youjin Wang +7

Zero-knowledge circuits enable privacy-preserving and scalable systems but are difficult to implement correctly due to the tight coupling between witness computation and circuit co…

cs.NI2026

Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence

Rong Fu, Xiaowen Ma, Kun Liu +9

Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and th…

cs.CV2026

Social-JEPA: Emergent Geometric Isomorphism

Haoran Zhang, Youjin Wang, Yi Duan +6

World models compress rich sensory streams into compact latent codes that anticipate future observations. We let separate agents acquire such models from distinct viewpoints of the…

cs.LG2026

NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces

Rong Fu, Chunlei Meng, Youjin Wang +5

The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimiz…