Dongrui Liu
22 papers · 2021–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Cross-Pollinator (13) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (6) π Academic Marathon (5)
πΊοΈ
Taxonomy Completionist
(50)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π€
Dynamic Duo
(10)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(101)
β
The Questioner
π
Century Club
(17)
Conferences
ACL (11)
AAAI (3)
NIPS (3)
CVPR (2)
EMNLP (2)
ICLR (1)
Top co-authors
Keywords
large language model
(7)
deep neural network
(3)
model merging
(3)
representation learning
(2)
attention head
(2)
mutual information
(2)
attention mechanism
(2)
generalization power
(2)
vision transformer
(1)
domain generalization
(1)
benchmark evaluation
(1)
game theory
(1)
self-attention mechanism
(1)
in-context learning
(1)
image generation
(1)
zero-shot learning
(1)
deep learning theory
(1)
multimodal learning
(1)
adversarial training
(1)
feature learning
(1)
Papers
ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
ACL 2026
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
ACL 2026
AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
ACL 2026
IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
AAAI 2026
Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models
AAAI 2026
LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
ACL 2025
EvoBench: Towards Real-world LLM-Generated Text Detection Benchmarking for Evolving Large Language Models
ACL 2025
VLSBench: Unveiling Visual Leakage in Multimodal Safety
ACL 2025
The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models
ACL 2025
Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective
ACL 2025
LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
ACL 2025
Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
CVPR 2025
The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations
EMNLP 2025
X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability
EMNLP 2025
REEF: Representation Encoding Fingerprints for Large Language Models
ICLR 2025
Explaining Generalization Power of a DNN Using Interactive Concepts
AAAI 2024
Identifying Semantic Induction Heads to Understand In-Context Learning
ACL 2024
Towards the Dynamics of a DNN Learning Symbolic Interactions
NIPS 2024
MLP Can Be A Good Transformer Learner
CVPR 2024
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
ACL 2024
Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities
NIPS 2023
Interpreting Representation Quality of DNNs for 3D Point Cloud Processing
NIPS 2021