Chao Deng

SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks

Latent-Informed Energy-Based Models with collaborative generator training

Go4RL: Improving the Pre-training Data Mixture of Large Language Models for Enhancing Reinforcement Learning

ChildEval: How Large language models meet children’s personalities

TRACE: Coarse-to-Fine Automated Evaluation of Mobile Agents with Safety Considerations in Realistic Environments

Recast Your Input via a Mapping Function for Alignment

DeCodec: Rethinking Audio Codecs as Universal Disentangled Representation Learners

What is an Optimal Growth Schedule for Large Language Models? A Theoretical Study

ASO-LoRA: Attribution Scores-based Soft Orthogonality Low-Rank Adaptation for Large Language Model Continual Learning

DGPO: Mitigating Likelihood Displacement with Bidirectional KL Divergence Gap

LOIRE: LifelOng learning on Incremental data via pre-trained language model gRowth Efficiently

Model Growth Schedule learning via Optimal Path (SLOP) for Efficient LLM Pre-Training