SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation
Paper • 2608.21500 • Published • 39
Tianyu Fu
fuvty
AI & ML interests
efficient-llm
large-language-models
sparse-attention
token-routing
latent-iterations
kv-cache
multi-llm
reasoning
inference
systems
Recent Activity
upvoted a paper 4 days ago
SecOPD: Mitigating Adaptive Prompt Injections by On-Policy Distillation upvoted a paper about 2 months ago
DOPD: Dual On-policy Distillation upvoted a paper 3 months ago
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMsOrganizations
upvoted a paper 4 days ago
upvoted a paper about 2 months ago
upvoted a paper 3 months ago
liked a
dataset 3 months ago
updated a
dataset 5 months ago
published a
dataset 5 months ago
updated a
dataset 5 months ago
published a
dataset 5 months ago
upvoted 3
papers 5 months ago
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
Paper • 2604.02029 • Published • 153
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Paper • 2603.20278 • Published • 102
Step-DeepResearch Technical Report
Paper • 2512.20491 • Published • 89
upvoted 2
papers 6 months ago
liked a
dataset 7 months ago
upvoted 3
papers 7 months ago
RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
Paper • 2602.07837 • Published • 57
DFlash: Block Diffusion for Flash Speculative Decoding
Paper • 2602.06036 • Published • 95
WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement Learning
Paper • 2602.04634 • Published • 100
liked a
model 7 months ago
upvoted a paper 9 months ago
liked a
model 9 months ago