-
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Paper • 2606.11817 • Published • 18 -
Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
Paper • 2602.00612 • Published • 1 -
Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
Paper • 2509.11250 • Published • 1 -
DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
Paper • 2506.09353 • Published
zhang
yitong42
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Code World Model: Coding Agent as World Brain authored a paper 8 days ago
CoACT: Action-Preserving Observation Compression for Coding Agents upvoted a paper 12 days ago
Environmental Injection Attacks against GUI Agents in Realistic Dynamic EnvironmentsOrganizations
None yet
-
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Paper • 2606.11817 • Published • 18 -
Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
Paper • 2602.00612 • Published • 1 -
Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
Paper • 2509.11250 • Published • 1 -
DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
Paper • 2506.09353 • Published
models 0
None public yet
datasets 0
None public yet