Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models
Paper • 2509.01909 • Published • 6
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
TokenCast: Forecasting Token Consumption During LLM Agent Execution
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
RosyCheng
authored 2
papers 13 days ago
RosyCheng
authored 6
papers 14 days ago
Deep Search in Real-World Web Environments
Paper • 2610.30181 • Published • 108
EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment
Paper • 2511.11301 • Published
Search-G1: Co-Evolving Representation-Based Rewards for Selective Grounded Search
Paper • 2608.07531 • Published
Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
Paper • 2605.25377 • Published
Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
Paper • 2610.21569 • Published
HABIT-Bench: Evaluating Habit Induction from Longitudinal Weak Evidence in Agent Memory
Paper • 2610.24520 • Published • 32
LeoYML
submitted a
paper to Daily Papers about 1 month ago
LeoYML
submitted a
paper to Daily Papers 3 months ago
RosyCheng
authored 6
papers over 1 year ago
Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
Paper • 2503.18991 • Published
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization
Paper • 2412.05892 • Published
Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining
Paper • 2410.18371 • Published
TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
Paper • 2405.14517 • Published
AGR: Age Group fairness Reward for Bias Mitigation in LLMs
Paper • 2409.04340 • Published
Reinforcement Learning from Multi-role Debates as Feedback for Bias Mitigation in LLMs
Paper • 2404.10160 • Published
