Publications (32)
CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings
Shanghaoran Quan, Jiaxi Yang, Bowen Yu +14
With the increasing code reasoning capabilities of existing large language models (LLMs) and breakthroughs in reasoning models like OpenAI o1 and o3, there is a growing need to dev…
Multi-branch Attentive Transformer
Yang Fan, Shufang Xie, Yingce Xia +4
While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especia…
Learning to Teach with Dynamic Loss Functions
Lijun Wu, Fei Tian, Yingce Xia +4
Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only prov…
Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs
Shiyu Xiang, Ansen Zhang, Yanfei Cao +2
Although Aligned Large Language Models (LLMs) are trained to refuse harmful requests, they remain vulnerable to jailbreak attacks. Unfortunately, existing methods often focus on su…
Qwen Technical Report
Jinze Bai, Shuai Bai, Yunfei Chu +45
Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to hu…
Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Peng Wang, Shuai Bai, Sinan Tan +16
We present the Qwen2-VL Series, an advanced upgrade of the previous Qwen-VL models that redefines the conventional predetermined-resolution approach in visual processing. Qwen2-VL…
Qwen-AgentWorld: Language World Models for General Agents
Yuxin Zuo, Zikai Xiao, Li Sheng +30
A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investigat…
Structure-Unified M-Tree Coding Solver for MathWord Problem
Bin Wang, Jiangzhou Ju, Yang Fan +3
As one of the challenging NLP tasks, designing math word problem (MWP) solvers has attracted increasing research attention for the past few years. In previous work, models designed…
Center of the Yangian double in type A
Yang Fan, Naihuan Jing
We prove the R-matrix and Drinfeld presentations of the Yangian double in type A are isomorphic. The central elements of the completed Yangian double in type A at the critical leve…
Online Merging Optimizers for Boosting Rewards and Mitigating Tax in Alignment
Keming Lu, Bowen Yu, Fei Huang +3
Effectively aligning Large Language Models (LLMs) with human-centric values while preventing the degradation of abilities acquired through Pre-training and Supervised Fine-tuning (…
Research on Graph-Retrieval Augmented Generation Based on Historical Text Knowledge Graphs
Yang Fan, Zhang Qi, Xing Wenqian +2
This article addresses domain knowledge gaps in general large language models for historical text analysis in the context of computational humanities and AIGC technology. We propos…
CrossFormer: Cross-Segment Semantic Fusion for Document Segmentation
Tongke Ni, Yang Fan, Junru Zhou +2
Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document str…
WorldPM: Scaling Human Preference Modeling
Binghai Wang, Runji Lin, Keming Lu +17
Motivated by scaling laws in language modeling that demonstrate how test loss scales as a power law with model and dataset sizes, we find that similar laws exist in preference mode…
Qwen3 Technical Report
An Yang, Anfeng Li, Baosong Yang +57
In this work, we present Qwen3, the latest version of the Qwen model family. Qwen3 comprises a series of large language models (LLMs) designed to advance performance, efficiency, a…
AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
Bin Kang, Shaoguo Wen, Yang Fan +6
While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the structural mismatch between…
FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts
Yunan Zhang, Yang Fan, Heng Li +2
Continual Learning for Named Entity Recognition (CLNER) enable models to incrementally learn new entity types without forgetting previously acquired ones. However, existing methods…
BrainPilot: Automating Brain Discovery with Agentic Research
Haoxuan Li, Tianci Gao, Jianhe Li +13
BrainPilot is an open‑source multi‑agent framework that automates brain‑science research by coordinating specialist agents with a curated knowledge base and a traceable workflow, w…
Qwen2.5-Coder Technical Report
Binyuan Hui, Jian Yang, Zeyu Cui +21
In this report, we introduce the Qwen2.5-Coder series, a significant upgrade from its predecessor, CodeQwen1.5. This series includes six models: Qwen2.5-Coder-(0.5B/1.5B/3B/7B/14B/…
Social Network De-anonymization: More Adversarial Knowledge, More Users Re-Identified?
Jianwei Qian, Xiang-Yang Li, Yu Wang +3
Following the trend of data trading and data publishing, many online social networks have enabled potentially sensitive data to be exchanged or shared on the web. As a result, user…
Qwen2.5-Omni Technical Report
Jin Xu, Zhifang Guo, Jinzheng He +11
In this report, we present Qwen2.5-Omni, an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously gene…
TDeLTA: A Light-weight and Robust Table Detection Method based on Learning Text Arrangement
Yang Fan, Xiangping Wu, Qingcai Chen +4
The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfi…
Qwen2.5 Technical Report
Qwen, :, An Yang +41
In this report, we introduce Qwen2.5, a comprehensive series of large language models (LLMs) designed to meet diverse needs. Compared to previous iterations, Qwen 2.5 has been sign…
Discovering Drug-Target Interaction Knowledge from Biomedical Literature
Yutai Hou, Yingce Xia, Lijun Wu +6
The Interaction between Drugs and Targets (DTI) in human body plays a crucial role in biomedical science and applications. As millions of papers come out every year in the biomedic…
Microsoft Research Asia's Systems for WMT19
Yingce Xia, Xu Tan, Fei Tian +11
We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks. We won the first place for 8 of the 11 directions and the second place fo…
Learning to Reweight with Deep Interactions
Yang Fan, Yingce Xia, Lijun Wu +5
Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real t…
AdEval: Alignment-based Dynamic Evaluation to Mitigate Data Contamination in Large Language Models
Yang Fan
As Large Language Models (LLMs) are pre-trained on ultra-large-scale corpora, the problem of data contamination is becoming increasingly serious, and there is a risk that static ev…
GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay
Yunan Zhang, Shuoran Jiang, Mengchen Zhao +4
The continual learning capability of large language models (LLMs) is crucial for advancing artificial general intelligence. However, continual fine-tuning LLMs across various domai…
Qwen-Image-2.0 Technical Report
Bing Zhao, Chenfei Wu, Deqing Li +72
We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite rece…
Tailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design
Kehan Wu, Yingce Xia, Yang Fan +7
Structure-based drug design is drawing growing attentions in computer-aided drug discovery. Compared with the virtual screening approach where a pre-defined library of compounds ar…
Learning to Teach
Yang Fan, Fei Tian, Tao Qin +2
Teaching plays a very important role in our society, by spreading human knowledge and educating our next generations. A good teacher will select appropriate teaching materials, imp…
Learning What Data to Learn
Yang Fan, Fei Tian, Tao Qin +2
Machine learning is essentially the sciences of playing with data. An adaptive data selection strategy, enabling to dynamically choose different data at various training stages, ca…
Qwen2 Technical Report
An Yang, Baosong Yang, Binyuan Hui +59
This report introduces the Qwen2 series, the latest addition to our large language models and large multimodal models. We release a comprehensive suite of foundational and instruct…