11 papers
S2-MoE: Enabling Efficient Self-Speculative Decoding for Mixture-of-Experts on Edge Devices
Haochen Huang, Shengxuan Qiu, Meng Li
Deploying large language models (LLMs) for inference on edge devices is challenging due to severe memory and bandwidth constraints. While speculative decoding and Mixture-of-Expert…
Cachemir: Fully Homomorphic Encrypted Inference of Generative Large Language Model with KV Cache
Ye Yu, Yifan Zhou, Yi Chen +3
Generative large language models (LLMs) have revolutionized multiple domains. Modern LLMs predominantly rely on an autoregressive decoding strategy, which generates output tokens s…
IntraSlice: Towards High-Performance Structural Pruning with Block-Intra PCA for LLMs
Meng Li, Peisong Wang, Yuantian Shao +5
Large Language Models (LLMs) achieve strong performance across diverse tasks but face deployment challenges due to their massive size. Structured pruning offers acceleration benefi…
HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
Shengxuan Qiu, Haochen Huang, Shuzhang Zhong +2
Scaling test-time compute with multi-path chain-of-thought improves reasoning accuracy, but its effectiveness depends critically on the exploration-exploitation trade-off. Existing…
What Gets Activated: Uncovering Domain and Driver Experts in MoE Language Models
Guimin Hu, Meng Li, Qiwei Peng +3
Most interpretability work focuses on layer- or neuron-level mechanisms in Transformers, leaving expert-level behavior in MoE LLMs underexplored. Motivated by functional specializa…
Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model
Ling Team, Anqi Shen, Baihui Li +101
We present Ring-1T, the first open-source, state-of-the-art thinking model with a trillion-scale parameter. It features 1 trillion total parameters and activates approximately 50 b…
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning
Ling Team, Bin Han, Caizhi Tang +25
In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B paramet…
EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
Zebin Yang, Sunjian Zheng, Tong Xie +6
Object-goal navigation (ObjNav) tasks an agent with navigating to the location of a specific object in an unseen environment. Embodied agents equipped with large language models (L…
MAPF-World: Action World Model for Multi-Agent Path Finding
Zhanjiang Yang, Yang Shen, Yueming Li +2
Multi-agent path finding (MAPF) studies the problem of planning conflict-free paths for multiple agents from given start locations to designated goals, with applications in robot-a…
Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes
Meng Li, Michael Vrazitulis, David Schlangen
Rational speakers are supposed to know what they know and what they do not know, and to generate expressions matching the strength of evidence. In contrast, it is still a challenge…
Holistic Capability Preservation: Towards Compact Yet Comprehensive Reasoning Models
Ling Team, Caizhi Tang, Chilin Fu +15
This technical report presents Ring-Lite-Distill, a lightweight reasoning model derived from our open-source Mixture-of-Experts (MoE) Large Language Models (LLMs) Ling-Lite. This s…