18 papers
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…
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…
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
Beining Wu, Fuyou Mao, Jiong Lin +7
Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers, yet current Generative Engine Optimization (GEO) methods optimiz…
Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis
Rong Fu, Ziming Wang, Chunlei Meng +5
As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy complia…
TempoNet: Slack-Quantized Transformer-Guided Reinforcement Scheduler for Adaptive Deadline-Centric Real-Time Dispatchs
Rong Fu, Yibo Meng, Guangzhen Yao +7
Real-time schedulers must reason about tight deadlines under strict compute budgets. We present TempoNet, a reinforcement learning scheduler that pairs a permutation-invariant Tran…
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…