Ran Liu
8 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces SHADOWMERGE, a novel poisoning attack that successfully compromises graph-based agent memory by exploiting relation-channel conflicts, achieving a high attack success rate across multiple real-world benchmarks.
The paper introduces AdvCL, a framework that repurposes adversarial perturbations as a geometric control signal to stabilize continual learning in large language models, significantly reducing forgetting and enhancing robustness.
This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.
A model-driven approach is proposed for generating families of reinforcement learning training environments using a hybrid genetic algorithm and model transformations.
The paper proposes CLASP, an end-to-end system with IMC acceleration for continual learning on edge platforms, addressing challenges of noisy computation and poor support for resource-efficient training.
The paper proposes oracle-guided fine-tuning to improve post-editing of ASR transcripts by using curated pools of corrections, regularizers, and hard negatives.
This paper introduces MemT-1.0, a new architecture of memory foundation models that internalize memory as part of model computation.
Debiasing feed terms to improve engagement predictions