1 citations · 1 across the 13 of their papers we have counts for
13 papers
DemoPSD: Disagreement-Modulated Policy Self-Distillation
Yunhe Li, Hao Shi, Wenhao Liu +5
On-policy self-distillation (OPSD) has emerged as a practical method for training large language models (LLMs) to reason, where a single model acts as both the teacher and the stud…
ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models
Wenhao Liu, Hao Shi, Yunhe Li +7
Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth. Current decoding-time…
Learning to Reason with Insight for Informal Theorem Proving
Yunhe Li, Hao Shi, Bowen Deng +8
Although most of the automated theorem-proving approaches depend on formal proof systems, informal theorem proving can align better with large language models' (LLMs) strength in n…
Reasoning Meets Personalization: Unleashing the Potential of Large Reasoning Model for Personalized Generation
Sichun Luo, Guanzhi Deng, Jian Xu +4
Personalization is a critical task in modern intelligent systems, with applications spanning diverse domains, including interactions with large language models (LLMs). Recent advan…
RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning
Sichun Luo, Jian Xu, Xiaojie Zhang +4
Large Language Models (LLMs) have been integrated into recommender systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further inc…
RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learning
Jian Xu, Sichun Luo, Xiangyu Chen +3
Large Language Models (LLMs) have been integrated into recommendation systems to enhance user behavior comprehension. The Retrieval Augmented Generation (RAG) technique is further…
Privacy in LLM-based Recommendation: Recent Advances and Future Directions
Sichun Luo, Wei Shao, Yuxuan Yao +9
Nowadays, large language models (LLMs) have been integrated with conventional recommendation models to improve recommendation performance. However, while most of the existing works…
Reed-Solomon Codes over Cyclic Polynomial Ring with Lower Encoding/Decoding Complexity
Wenhao Liu, Zhengyi Jiang, Zhongyi Huang +2
Reed-Solomon (RS) codes are constructed over a finite field that have been widely employed in storage and communication systems. Many fast encoding/decoding algorithms such as fast…
Learning From Correctness Without Prompting Makes LLM Efficient Reasoner
Yuxuan Yao, Han Wu, Zhijiang Guo +6
Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and tox…
Improved Quantization Strategies for Managing Heavy-tailed Gradients in Distributed Learning
Guangfeng Yan, Tan Li, Yuanzhang Xiao +2
Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is obse…
Truncated Non-Uniform Quantization for Distributed SGD
Guangfeng Yan, Tan Li, Yuanzhang Xiao +2
To address the communication bottleneck challenge in distributed learning, our work introduces a novel two-stage quantization strategy designed to enhance the communication efficie…
Towards Quantum-Safe Federated Learning via Homomorphic Encryption: Learning with Gradients
Guangfeng Yan, Shanxiang Lyu, Hanxu Hou +2
This paper introduces a privacy-preserving distributed learning framework via private-key homomorphic encryption. Thanks to the randomness of the quantization of gradients, our lea…
Generalized Simple Regenerating Codes: Trading Sub-packetization and Fault Tolerance
Zhengyi Jiang, Hao Shi, Zhongyi Huang +3
Maximum distance separable (MDS) codes have the optimal trade-off between storage efficiency and fault tolerance, which are widely used in distributed storage systems. As typical n…