FlowGuard detects unsafe content during diffusion image generation via linear latent decoding and curriculum learning, outperforming prior methods by over 30% F1 while reducing GPU memory by 97% and projection time to 0.2 seconds.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
WSTypist is a new RL-based simulation model that reproduces human-like word suggestion strategies, individual differences, and adaptation to design changes in mobile text entry.
REC RL improves LLM code generation by automatically assessing and optimizing requirement difficulty with adaptive curriculum sampling, yielding 1.23-5.62% Pass@1 gains over baselines.
BehaviorLM applies progressive fine-tuning in two stages to let LLMs predict both frequent anchor and rare tail user behaviors more robustly on real-world datasets.
CurEvo integrates curriculum guidance into self-evolution to structure autonomous improvement of video understanding models, yielding gains on VideoQA benchmarks.
citing papers explorer
-
FlowGuard: Towards Lightweight In-Generation Safety Detection for Diffusion Models via Linear Latent Decoding
FlowGuard detects unsafe content during diffusion image generation via linear latent decoding and curriculum learning, outperforming prior methods by over 30% F1 while reducing GPU memory by 97% and projection time to 0.2 seconds.
-
Simulating Word Suggestion Usage in Mobile Typing to Guide Intelligent Text Entry Design
WSTypist is a new RL-based simulation model that reproduces human-like word suggestion strategies, individual differences, and adaptation to design changes in mobile text entry.
-
Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning
REC RL improves LLM code generation by automatically assessing and optimizing requirement difficulty with adaptive curriculum sampling, yielding 1.23-5.62% Pass@1 gains over baselines.
-
Tuning Language Models for Robust Prediction of Diverse User Behaviors
BehaviorLM applies progressive fine-tuning in two stages to let LLMs predict both frequent anchor and rare tail user behaviors more robustly on real-world datasets.
-
CurEvo: Curriculum-Guided Self-Evolution for Video Understanding
CurEvo integrates curriculum guidance into self-evolution to structure autonomous improvement of video understanding models, yielding gains on VideoQA benchmarks.