3 citations · 12 across the 47 of their papers we have counts for
30 papers · 1 filter
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…
Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs
Zhenyu Liu, Xuanyu Zhang, Yunxin Li +10
Developing seamless, high-performance, native intelligent full-duplex Spoken Language Models (SLMs) remains a critical challenge and long-standing goal for the speech and NLP commu…
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
Yunxin Li, Jinchao Li, Shibo Su +7
OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a well-built self-evolution mech…
Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking
Xinping Zhao, Jiaxin Xu, Ziqi Dai +10
As retrieval systems scale, effective and efficient reranking becomes increasingly important. However, most existing encoder- and decoder-based rerankers jointly process every quer…
Less Languages, Less Tokens: An Efficient Unified Logic Cross-lingual Chain-of-Thought Reasoning Framework
Chenyuan Zhang, Qiguang Chen, Xie Chen +6
Cross-lingual chain-of-thought (XCoT) with self-consistency markedly enhances multilingual reasoning, yet existing methods remain costly due to extensive sampling of full trajector…
CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks
Peiqin Lin, Chenyang Lyu, Wenjiang Luo +22
Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prio…
ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution
Shouzheng Huang, Meishan Zhang, Baotian Hu +1
Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evolving tool repositories, exi…
LMEB: Long-horizon Memory Embedding Benchmark
Xinping Zhao, Xinshuo Hu, Jiaxin Xu +9
Embedding models are increasingly used as retrievers in memory-augmented systems, but are typically evaluated on traditional passage retrieval benchmarks. It remains unclear whethe…
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…
A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation
Ziyang Chen, Erxue Min, Xiang Zhao +7
We introduce ChronoQA, a large-scale benchmark dataset for Chinese question answering, specifically designed to evaluate temporal reasoning in Retrieval-Augmented Generation (RAG)…
On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey
Meishan Zhang, Xin Zhang, Xinping Zhao +3
Text embeddings have attracted growing interest due to their effectiveness across a wide range of natural language processing (NLP) tasks, including retrieval, classification, clus…
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
Xinping Zhao, Shouzheng Huang, Yan Zhong +4
Retrieval-Augmented Generation (RAG) effectively improves the accuracy of Large Language Models (LLMs). However, retrieval noises significantly undermine the quality of LLMs' gener…
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
Zhenran Xu, Yiyu Wang, Xue Yang +5
AI-generated content has evolved from monolithic models to modular workflows, particularly on platforms like ComfyUI, enabling customization in creative pipelines. However, craftin…
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development
Zhenran Xu, Xue Yang, Yiyu Wang +7
We introduce ComfyUI-Copilot, a large language model-powered plugin designed to enhance the usability and efficiency of ComfyUI, an open-source platform for AI-driven art creation.…
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…
VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization
Yunxin Li, Xinyu Chen, Zitao Li +5
Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning. However, popular Reinforcement Fine-Tuning (…
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…
Picking the Cream of the Crop: Visual-Centric Data Selection with Collaborative Agents
Zhenyu Liu, Yunxin Li, Baotian Hu +3
To improve Multimodal Large Language Models' (MLLMs) ability to process images and complex instructions, researchers predominantly curate large-scale visual instruction tuning data…
FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces
Zhenran Xu, Longyue Wang, Jifang Wang +7
Virtual film production requires intricate decision-making processes, including scriptwriting, virtual cinematography, and precise actor positioning and actions. Motivated by recen…
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…