Kai Wang
9 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Salami Slicing Risk, a novel multi-turn jailbreak technique that accumulates harmful intent through numerous low-risk inputs, achieving state-of-the-art attack success rates against major LLMs.
The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rather than just malicious user prompts.
The paper proposes Hydra, a framework to stabilize and control the injection of multiple, conflicting backdoor triggers into text-to-image diffusion models, ensuring high attack reliability while maintaining clean generation quality.
The paper introduces EASE, a method that enhances multimodal Reinforcement Learning with Verifiable Rewards (RLVR) by providing spatial attention supervision anchored to visual evidence, significantly improving visual grounding and reasoning capabilities in VLMs.
The paper introduces EASE, a method that enhances multimodal Reinforcement Learning with Verifiable Rewards (RLVR) by providing spatial attention supervision anchored to visual evidence, significantly improving visual grounding and reasoning capabilities in VLMs.
HumanNOVA introduces a photorealistic, universal, and rapid model capable of generating high-quality 3D human avatars from a single input RGB image.
HumanNOVA introduces a photorealistic, universal, and rapid model capable of generating high-quality 3D human avatars from a single input RGB image.
This paper proposes a four-layer technical architecture for large model inference optimization, including Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion.
This paper investigates the use of synthetic facial images to supplement training data for recognizing genetic syndromes.