3 citations · 13 across the 27 of their papers we have counts for
27 papers
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Dongfang Li, Xiaodong Luo, Ruoyu Sun +62
Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pre…
LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
Dongfang Li, Zixuan Liu, Junmai Wang +6
Long-horizon LLM agents must preserve information from past interactions to support future tasks. Existing memory systems typically rely on eager consolidation, invoking LLMs after…
LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing
Dongfang Li, Zixuan Liu, Gang Lin +2
The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large La…
SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference
Luchang Li, Dongfang Li, Bozhao Gong +1
Prefill-Decode (P/D) disaggregation has emerged as a widely adopted optimization strategy for Large Language Model (LLM) inference. However, there currently exists no well-establis…
Structured Episodic Event Memory
Zhengxuan Lu, Dongfang Li, Yukun Shi +3
Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails…
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
Zhuoen Chen, Dongfang Li, Meishan Zhang +2
Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation…
LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding
Gang Lin, Dongfang Li, Zhuoen Chen +4
The proliferation of long-context large language models (LLMs) exposes a key bottleneck: the rapidly expanding key-value cache during decoding, which imposes heavy memory and laten…
Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
Zetian Sun, Dongfang Li, Zhuoen Chen +2
Reward sparsity in long-horizon reinforcement learning (RL) tasks remains a significant challenge, while existing outcome-based reward shaping struggles to define meaningful immedi…
Improving Value-based Process Verifier via Low-Cost Variance Reduction
Zetian Sun, Dongfang Li, Baotian Hu +1
Large language models (LLMs) have achieved remarkable success in a wide range of tasks. However, their reasoning capabilities, particularly in complex domains like mathematics, rem…
Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?
Zetian Sun, Dongfang Li, Xuhui Chen +2
The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize t…
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Xinping Zhao, Xinshuo Hu, Zifei Shan +14
Recent advancements in Large Language Models (LLMs)-based text embedding models primarily focus on data scaling or synthesis, yet limited exploration of training techniques and dat…
Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment
Zhenyu Liu, Dongfang Li, Xinshuo Hu +4
Recent studies have explored the working mechanisms of In-Context Learning (ICL). However, they mainly focus on classification and simple generation tasks, limiting their broader a…
Improving Value-based Process Verifier via Structural Prior Injection
Zetian Sun, Dongfang Li, Baotian Hu +2
In the Large Language Model(LLM) reasoning scenario, people often estimate state value via Monte Carlo sampling. Though Monte Carlo estimation is an elegant method with less induct…
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
Xinshuo Hu, Zifei Shan, Xinping Zhao +10
As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, pri…
CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
Dongfang Li, Zetian Sun, Xinshuo Hu +2
Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LL…
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
Xinping Zhao, Dongfang Li, Yan Zhong +4
Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG perform…
Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Xinping Zhao, Jindi Yu, Zhenyu Liu +5
As we all know, hallucinations prevail in Large Language Models (LLMs), where the generated content is coherent but factually incorrect, which inflicts a heavy blow on the widespre…
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
Xinping Zhao, Yan Zhong, Zetian Sun +5
Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful…
In-Context Learning State Vector with Inner and Momentum Optimization
Dongfang Li, Zhenyu Liu, Xinshuo Hu +3
Large Language Models (LLMs) have exhibited an impressive ability to perform In-Context Learning (ICL) from only a few examples. Recent works have indicated that the functions lear…
Improving Attributed Text Generation of Large Language Models via Preference Learning
Dongfang Li, Zetian Sun, Baotian Hu +4
Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformati…
Does the Generator Mind its Contexts? An Analysis of Generative Model Faithfulness under Context Transfer
Xinshuo Hu, Baotian Hu, Dongfang Li +2
The present study introduces the knowledge-augmented generator, which is specifically designed to produce information that remains grounded in contextual knowledge, regardless of a…
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
Liangxin Liu, Xuebo Liu, Derek F. Wong +4
Instruction tuning (IT) is crucial to tailoring large language models (LLMs) towards human-centric interactions. Recent advancements have shown that the careful selection of a smal…
Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration
Zhenran Xu, Senbao Shi, Baotian Hu +4
Large Language Models (LLMs) have shown remarkable capabilities in general natural language processing tasks but often fall short in complex reasoning tasks. Recent studies have ex…
Temporal Knowledge Question Answering via Abstract Reasoning Induction
Ziyang Chen, Dongfang Li, Xiang Zhao +2
In this study, we address the challenge of enhancing temporal knowledge reasoning in Large Language Models (LLMs). LLMs often struggle with this task, leading to the generation of…