Xingjun Ma
- Papers
- 33
Cite
Notes
Only stored in your browser.
Authored papers
33OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
arXiv 2026
Internal Safety Collapse in Frontier Large Language Models
arXiv 2026
A Survey of Large Audio Language Models: Generalization, Trustworthiness, and Outlook
arXiv 2026
OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
arXiv 2026
FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions
arXiv 2026
SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents
arXiv 2026
PixelSmile: Toward Fine-Grained Facial Expression Editing
arXiv 2026
A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Doubao 1.8, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
arXiv 2026
OmniSVG: A Unified Scalable Vector Graphics Generation Model
arXiv 2025
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
arXiv 2025
X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
arXiv 2025
WithAnyone: Towards Controllable and ID Consistent Image Generation
arXiv 2025
BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
arXiv 2025
Safety at Scale: A Comprehensive Survey of Large Model Safety
arXiv 2025
Detecting Backdoor Samples in Contrastive Language Image Pretraining
arXiv 2025
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
arXiv 2025
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
arXiv 2024
Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks
arXiv 2024
LDReg: Local Dimensionality Regularized Self-Supervised Learning
arXiv 2024
Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
arXiv 2024
Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
CVPR 2025 1
AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models
CVPR 2025 1
Fake Alignment: Are LLMs Really Aligned Well?
arXiv 2023
Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models
arXiv 2023
Reconstructive Neuron Pruning for Backdoor Defense
arXiv 2023
Distilling Cognitive Backdoor Patterns within an Image
arXiv 2023
Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples
CVPR 2023 1
Few-Shot Backdoor Attacks on Visual Object Tracking
few-shot-backdoor-attacks-on-visual-object
WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
arXiv 2021
Unlearnable Examples: Making Personal Data Unexploitable
unlearnable-examples-making-personal-data
Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks
NeurIPS 2021 12
Normalized Loss Functions for Deep Learning with Noisy Labels
ICML 2020 1
Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness
arXiv 2020
Affiliations
Frequent co-authors
10from 33 papers