AI safety researcher

Tongliang Liu

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months19 papers

Defenses 3Evaluation and benchmarks 2Interpretability 1Analysis and theory 1

AI safety papers from the last year

On this site: 65 papers

November 2026

Chain-of-Thought Oversight Requires Separate Evidence for Faithfulness and Monitorability
Nov 1arXiv ↗

September 2026

Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual Reasoning
Sep 30Evaluation and benchmarksarXiv ↗
Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement
Sep 21InterpretabilityarXiv ↗
Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment
Sep 20Analysis and theoryarXiv ↗

August 2026

When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
Aug 4Evaluation and benchmarksarXiv ↗
Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection
Aug 1DefensesarXiv ↗

July 2026

Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization
Jul 14DefensesarXiv ↗

June 2026

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs
Jun 11arXiv ↗

April 2026

February 2026

January 2026

Privacy-Preserving Model Transcription with Differentially Private Synthetic Distillation
Jan 27arXiv ↗

December 2025

November 2025

DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection
Nov 16arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.