0

Shumin Deng

Papers
27

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
27papers

Authored papers

27

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

arXiv 2026

2026

SkillNet: Create, Evaluate, and Connect AI Skills

arXiv 2026

2026

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

arXiv 2026

2026

From Data to Behavior: Predicting Unintended Model Behaviors Before Training

arXiv 2026

2026

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

arXiv 2026

2026

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

arXiv 2025

2025

LightMem: Lightweight and Efficient Memory-Augmented Generation

arXiv 2025

2025

OceanGym: A Benchmark Environment for Underwater Embodied Agents

arXiv 2025

2025

Automating Steering for Safe Multimodal Large Language Models

arXiv 2025

2025

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging

arXiv 2025

2025

How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training

arXiv 2025

2025

CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners

arXiv 2025

2025

Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms

arXiv 2025

2025

Exploring Model Kinship for Merging Large Language Models

arXiv 2024

2024

KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection

arXiv 2024

2024

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

arXiv 2024

2024

FlipAttack: Jailbreak LLMs via Flipping

arXiv 2024

2024

Agent Planning with World Knowledge Model

arXiv 2024

2024

Knowledge Circuits in Pretrained Transformers

arXiv 2024

2024

LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities

arXiv 2023

2023

From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal

ICCV 2023 1

2023

When Do Program-of-Thoughts Work for Reasoning?

arXiv 2023

2023

Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

arXiv 2023

2023

Reasoning with Language Model Prompting: A Survey

arXiv 2022

2022

Multimodal Analogical Reasoning over Knowledge Graphs

arXiv 2022

2022

LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting

COLING 2022 10

2021

Molecular Contrastive Learning with Chemical Element Knowledge Graph

arXiv 2021

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 27 papers