10 papers
Ecdysis: Efficient and Effective Training of Runtime Harnesses for LLM Agents
Ruiqing Yue, Yu Cui, Zhuoyu Sun +11
Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents and provide a promising paradigm for optimizing agent execution. Exi…
Refusal is Not Safety! Benchmarking Latent Safety Risks of LLM-Driven Content Humorization
Yu Cui, Ruiqing Yue, Tingyu Li +6
Safety defenses for large language models (LLMs) have been extensively studied, with existing approaches focusing on attack detection and refusal mechanisms. Such fixed-form direct…
Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models
Yongqin Zeng, Sicheng Pan, Jiale Wang +4
Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data rem…
An Extensible and Verifiable Language for Query Rewrite Rules
Sicheng Pan, Shuxian Wang, Wesley Zheng +3
Logical query plan rewriting transforms a relational database query into an equivalent but more efficient form and is crucial to the performance of database-backed applications. In…
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
Aili Chen, Aonian Li, Baichuan Zhou +215
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
Spore: Efficient and Training-Free Privacy Extraction Attack on LLMs via Inference-Time Hybrid Probing
Yu Cui, Ruiqing Yue, Hang Fu +6
With the wide adoption of personal AI assistants such as OpenClaw, privacy leakage in user interaction contexts with large language model (LLM) agents has become a critical issue.…
Adaptive Multi-Objective Tiered Storage Configuration for KV Cache in LLM Service
Xianzhe Zheng, Zhengheng Wang, Ruiyan Ma +17
The memory-for-computation paradigm of KV caching is essential for accelerating large language model (LLM) inference service, but limited GPU high-bandwidth memory (HBM) capacity m…
Towards Provably Secure Generative AI: Reliable Consensus Sampling
Yu Cui, Hang Fu, Sicheng Pan +9
Existing research on generative AI security is primarily driven by mutually reinforcing attack and defense methodologies grounded in empirical experience. This dynamic frequently g…
Can LLMs Threaten Human Survival? Benchmarking Potential Existential Threats from LLMs via Prefix Completion
Yu Cui, Yifei Liu, Hang Fu +4
Research on the safety evaluation of large language models (LLMs) has become extensive, driven by jailbreak studies that elicit unsafe responses. Such response involves information…
VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy
Yu Cui, Sicheng Pan, Yifei Liu +2
Large language models (LLMs) have been widely deployed in Conversational AIs (CAIs), while exposing privacy and security threats. Recent research shows that LLM-based CAIs can be m…