研究成果

联系我们

「智能始于记忆，张量链接未来」

研究成果

UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions

2025-06-04

研究成果

Adversarial Preference Learning for Robust LLM Alignment

2025-05-30

研究成果

GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning

2025-05-28

研究成果

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models

2025-05-27

研究成果

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval Augmented Generation

2025-05-26

研究成果

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems

2025-05-26

研究成果

MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System

2025-05-26

研究成果

XFINDER: LARGE LANGUAGE MODELS AS AUTOMATED EVALUATORS FOR RELIABLE EVALUATION

2025-02-25

研究成果

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model

2025-02-23

研究成果

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models

2024-10-04

研究成果

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

2024-07-15

研究成果

Memory3 : Language Modeling with Explicit Memory

2024-07-01

研究成果

NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism

2024-06-04

研究成果

Grimoire is All You Need for Enhancing Large Language Models

2024-01-10

研究成果

HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning

2023-12-29

研究成果

Time-interval Aware Share Recommendation via Bi-directional Continuous Time Dynamic Graphs

2023-07-18

研究成果

电话：021-60299607

邮箱：MemTensor@memtensor.cn

地址：上海市徐汇区乐山路33号上海交通大学科技园

互联网建设模板

UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions

Adversarial Preference Learning for Robust LLM Alignment

GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning

Token-level Accept or Reject: A Micro Alignment Approach for Large Language Models

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval Augmented Generation

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems

MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System

XFINDER: LARGE LANGUAGE MODELS AS AUTOMATED EVALUATORS FOR RELIABLE EVALUATION

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

Memory3 : Language Modeling with Explicit Memory

NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism

Grimoire is All You Need for Enhancing Large Language Models

HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning

Time-interval Aware Share Recommendation via Bi-directional Continuous Time Dynamic Graphs