Daniel Kang
15 papers · 2019–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Conference Polyglot (5) π§ Keyword Pioneer π£ Hot Topic Early Bird π Interdisciplinary Bridge π Academic Marathon (6)
π
Conference Polyglot
(5)
π
Academic Marathon
(6)
π
Cross-Pollinator
(13)
π§¬
Topic Evolution
π₯
Mega-Team
(23)
ποΈ
Keyword Collector
(57)
π
Century Club
(12)
β
The Questioner
Conferences
ACL (5)
ICML (4)
EACL (2)
NAACL (2)
ICCV (1)
RSS (1)
Top co-authors
Research topics
Keywords
llm agent
(3)
large language model
(3)
model compression
(3)
benchmark evaluation
(2)
reinforcement learning
(2)
image generation
(1)
natural language generation
(1)
deep reinforcement learning
(1)
factual accuracy
(1)
adversarial attack
(1)
knowledge distillation
(1)
text generation
(1)
text summarization
(1)
code generation
(1)
log loss
(1)
sequential decision making
(1)
ai safety
(1)
software engineering
(1)
model safety
(1)
robot perception
(1)
Papers
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Knowledge Poisoning Attacks
ACL 2026
SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents
EACL 2026
Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
EACL 2026
UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
ACL 2025
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
NAACL 2025
CVE-Bench: A Benchmark for AI Agentsβ Ability to Exploit Real-World Web Application Vulnerabilities
ICML 2025
REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?
ACL 2025
Trustless Audits without Revealing Data or Models
ICML 2024
InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
ACL 2024
Position: A Safe Harbor for AI Evaluation and Red Teaming
ICML 2024
Removing RLHF Protections in GPT-4 via Fine-Tuning
NAACL 2024
Q-Diffusion: Quantizing Diffusion Models
ICCV 2023
Improved Natural Language Generation via Loss Truncation
ACL 2020
Network Offloading Policies for Cloud Robotics: A Learning-Based Approach
RSS 2019
LIT: Learned Intermediate Representation Training for Model Compression
ICML 2019