Skip to content
conftrace_

Xiaosen Zheng

6 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot Β· Bronze πŸŒ‰ Interdisciplinary Bridge Β· Bronze πŸ—ΊοΈ Taxonomy Completionist (14) πŸ‘‘ Triple Crown

Venues

ICLR (3) ACL (1) ICML (1) NeurIPS (1)

Top co-authors

Jing Jiang (6) Min Lin (5) Tianyu Pang (5) Chao Du (4) Qian Liu (4) Guangtao Zeng (1) Longxu Dou (1) Xiangming Gu (1) Niklas Muennighoff (1) Ye Wang (1)

Research topics

Machine Learning (4) Artificial Intelligence (3) Natural Language Processing (2) Application Areas (2) Core AI (2) Optimization & Theory (2) Deep Learning (1) Applications (1) Core Methods (1) Learning Paradigms (1) Learning Types (1) Models (1) Resources & Methods (1)

Keywords

large language model (2) adversarial learning (1) few-shot learning (1) text classification (1) web corpus (1) language model alignment (1) deep learning (1) diffusion model (1) scaling law (1) data attribution (1) jailbreak attack (1) data mixture (1) attribution method (1) multi-agent environment (1) defense mechanism (1) counterfactual evaluation (1) language model pretraining (1) automatic benchmark (1) harmful behavior (1) adversarial image (1)

Papers

Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates ICLR 2025 RegMix: Data Mixture as Regression for Language Model Pre-training ICLR 2025 Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast ICML 2024 Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses NeurIPS 2024 Intriguing Properties of Data Attribution on Diffusion Models ICLR 2024 An Empirical Study of Memorization in NLP ACL 2022