5 papers
When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
Yuchun Miao, Sen Zhang, Yuqi Zhang +4
Reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for advanced reasoning in Large Language Models (LLMs), but rollout samples are expensive to…
JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency
Aichen Cai, Anmeng Zhang, Anyu Li +66
We introduce JoyAI-LLM Flash, an efficient Mixture-of-Experts (MoE) language model designed to redefine the trade-off between strong performance and token efficiency in the sub-50B…
The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking
Yuchun Miao, Sen Zhang, Liang Ding +3
This work identifies the Energy Loss Phenomenon in Reinforcement Learning from Human Feedback (RLHF) and its connection to reward hacking. Specifically, energy loss in the final la…
AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders
Yuqi Zhang, Yuchun Miao, Zuchao Li +1
We introduce AMIA, a lightweight, inference-only defense for Large Vision-Language Models (LVLMs) that (1) Automatically Masks a small set of text-irrelevant image patches to disru…
Intention Analysis Makes LLMs A Good Jailbreak Defender
Yuqi Zhang, Liang Ding, Lefei Zhang +1
Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing m…