8 papers
Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation
Shuaishuai Cao, Shuwei Peng, Meng Tang +5
Semantic segmentation models are trained and evaluated against human-drawn masks, yet remote-sensing annotations are often coarse, incomplete, or misaligned; high overlap scores ma…
InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model
Youjin Wang, Jiaqiao Zhao, Rong Fu +5
Balancing fine-grained local modeling with long-range dependency capture under computational constraints remains a central challenge in sequence modeling. While Transformers provid…
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…
Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence
Rong Fu, Xiaowen Ma, Kun Liu +8
Deploying expressive learning models directly on programmable dataplanes promises line-rate, low-latency traffic analysis but remains hindered by strict hardware constraints and th…
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…
NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces
Rong Fu, Chunlei Meng, Haoyu Zhao +4
The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimiz…
SwiftRepertoire: Few-Shot Immune-Signature Synthesis via Dynamic Kernel Codes
Rong Fu, Yang Li, Yabin Jin +3
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…
zkCraft: Prompt-Guided LLM as a Zero-Shot Mutation Pattern Oracle for TCCT-Powered ZK Fuzzing
Rong Fu, Jia Yee Tan, Ziyu Kong +5
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…