Publications (40)
Unsupervised Wildfire Change Detection based on Contrastive Learning
Beichen Zhang, Huiqi Wang, Amani Alabri +4
The accurate characterization of the severity of the wildfire event strongly contributes to the characterization of the fuel conditions in fire-prone areas, and provides valuable i…
Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos
Yufan Zhou, Zhaobo Qi, Lingshuai Lin +5
In this paper, we address the challenge of procedure planning in instructional videos, aiming to generate coherent and task-aligned action sequences from start and end visual obser…
Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
Beichen Zhang, Kun Zhou, Xilin Wei +4
Chain-of-thought prompting~(CoT) and tool augmentation have been validated in recent work as effective practices for improving large language models~(LLMs) to perform step-by-step…
START: Self-taught Reasoner with Tools
Chengpeng Li, Mingfeng Xue, Zhenru Zhang +7
Large reasoning models (LRMs) like OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable capabilities in complex reasoning tasks through the utilization of long Chain-of-thought (…
Reinforcement Learning for Sociohydrology
Tirthankar Roy, Shivendra Srivastava, Beichen Zhang
In this study, we discuss how reinforcement learning (RL) provides an effective and efficient framework for solving sociohydrology problems. The efficacy of RL for these types of p…
TweetDrought: A Deep-Learning Drought Impacts Recognizer based on Twitter Data
Beichen Zhang, Frank Schilder, Kelly Helm Smith +3
Acquiring a better understanding of drought impacts becomes increasingly vital under a warming climate. Traditional drought indices describe mainly biophysical variables and not im…
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…
Slow Thinking for Sequential Recommendation
Junjie Zhang, Beichen Zhang, Wenqi Sun +4
To develop effective sequential recommender systems, numerous methods have been proposed to model historical user behaviors. Despite the effectiveness, these methods share the same…
ETCHR: Editing To Clarify and Harness Reasoning
Beichen Zhang, Yuhong Liu, Jinsong Li +3
Multimodal Large Language Models have advanced visual reasoning, yet a purely textual chain of thought remains a bottleneck for questions that require fine-grained focus or view tr…
SinkRouter: Sink-Aware Routing for Efficient Long-Context Decoding in Large Language and Multimodal Models
Junnan Liu, Xinyan Liu, Peifeng Gao +4
In long-context decoding for LLMs and LMMs, attention becomes increasingly memory-bound because each decoding step must load a large amount of KV-cache data from GPU memory. Existi…
Long-CLIP: Unlocking the Long-Text Capability of CLIP
Beichen Zhang, Pan Zhang, Xiaoyi Dong +2
Contrastive Language-Image Pre-training (CLIP) has been the cornerstone for zero-shot classification, text-image retrieval, and text-image generation by aligning image and text mod…
YuLan: An Open-source Large Language Model
Yutao Zhu, Kun Zhou, Kelong Mao +35
Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many o…
Think Visually, Reason Textually: Vision-Language Synergy in ARC
Beichen Zhang, Yuhang Zang, Xiaoyi Dong +4
Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transf…
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…
SEE: Structure-aware Exploring \& Exploiting for Long-horizon GUI Agent Trajectory Synthesis
Zhuohang Fan, Beichen Zhang, Yuanfa Li +4
Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-covera…
A Survey of Large Language Models
Wayne Xin Zhao, Kun Zhou, Junyi Li +19
Language is essentially a complex, intricate system of human expressions governed by grammatical rules. It poses a significant challenge to develop capable AI algorithms for compre…
Rethinking Graph Neural Architecture Search from Message-passing
Shaofei Cai, Liang Li, Jincan Deng +4
Graph neural networks (GNNs) emerged recently as a standard toolkit for learning from data on graphs. Current GNN designing works depend on immense human expertise to explore diffe…
From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR
Jia Deng, Jie Chen, Zhipeng Chen +7
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditiona…
Debiased Contrastive Learning of Unsupervised Sentence Representations
Kun Zhou, Beichen Zhang, Wayne Xin Zhao +1
Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close…
AIFIND: Artifact-Aware Interpreting Fine-Grained Alignment for Incremental Face Forgery Detection
Hao Wang, Beichen Zhang, Yanpei Gong +5
As forgery types continue to emerge consistently, Incremental Face Forgery Detection (IFFD) has become a crucial paradigm. However, existing methods typically rely on data replay o…
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
Beichen Zhang, Yuhong Liu, Xiaoyi Dong +6
Large language models (LLMs) have demonstrated impressive ability in solving complex mathematical problems with multi-step reasoning and can be further enhanced with well-designed…
Quantitative Assessment of Drought Impacts Using XGBoost based on the Drought Impact Reporter
Beichen Zhang, Fatima K. Abu Salem, Michael J. Hayes +1
Under climate change, the increasing frequency, intensity, and spatial extent of drought events lead to higher socio-economic costs. However, the relationships between the hydro-me…
Downstream-Pretext Domain Knowledge Traceback for Active Learning
Beichen Zhang, Liang Li, Zheng-Jun Zha +2
Active learning (AL) is designed to construct a high-quality labeled dataset by iteratively selecting the most informative samples. Such sampling heavily relies on data representat…
ChatCoT: Tool-Augmented Chain-of-Thought Reasoning on Chat-based Large Language Models
Zhipeng Chen, Kun Zhou, Beichen Zhang +3
Although large language models (LLMs) have achieved excellent performance in a variety of evaluation benchmarks, they still struggle in complex reasoning tasks which require specif…
JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding
Wayne Xin Zhao, Kun Zhou, Zheng Gong +7
This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model~(PLM) for effectively understanding and…
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Zhenru Zhang, Chujie Zheng, Yangzhen Wu +6
Process Reward Models (PRMs) emerge as a promising approach for process supervision in mathematical reasoning of Large Language Models (LLMs), which aim to identify and mitigate in…
Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach
Beichen Zhang, Xiaoxing Wang, Xiaohan Qin +1
Supernet is a core component in many recent Neural Architecture Search (NAS) methods. It not only helps embody the search space but also provides a (relative) estimation of the fin…
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Kun Zhou, Beichen Zhang, Jiapeng Wang +6
Mathematical reasoning is an important capability of large language models~(LLMs) for real-world applications. To enhance this capability, existing work either collects large-scale…
Coupling Agent-based Modeling and Life Cycle Assessment to Analyze Trade-offs in Resilient Energy Transitions
Beichen Zhang, Mohammed T. Zaki, Hanna Breunig +1
Transitioning to sustainable and resilient energy systems requires navigating complex and interdependent trade-offs across environmental, social, and resource dimensions. Neglectin…
EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models
Xuanlang Dai, Yujie Zhou, Long Xing +6
Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusion frameworks primarily as text encoders to tackle complex tasks such as spatial reasonin…
State-Relabeling Adversarial Active Learning
Beichen Zhang, Liang Li, Shijie Yang +3
Active learning is to design label-efficient algorithms by sampling the most representative samples to be labeled by an oracle. In this paper, we propose a state relabeling adversa…
STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning
Yanpei Gong, Beichen Zhang, Hao Wang +5
Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored video modeling, they largely ov…
An Empirical Study on Eliciting and Improving R1-like Reasoning Models
Zhipeng Chen, Yingqian Min, Beichen Zhang +10
In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL…
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning
Yuhong Liu, Beichen Zhang, Yuhang Zang +6
Spatial understanding remains a weakness of Large Vision-Language Models (LVLMs). Existing supervised fine-tuning (SFT) and recent reinforcement learning with verifiable rewards (R…
JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving
Wayne Xin Zhao, Kun Zhou, Beichen Zhang +8
Although pre-trained language models~(PLMs) have recently advanced the research progress in mathematical reasoning, they are not specially designed as a capable multi-task solver,…
Contributions to the cross shock electric field at supercritical perpendicular shocks: Impact of the pickup ions
Zhongwei Yang, Desheng Han, Huigen Yang +4
A particle-in-cell code is used to examine contributions of the pickup ions (PIs) and the solar wind ions (SWs) to the cross shock electric field at the supercritical, perpendicula…
Designing the Haystack: Programmable Chemical Space for Generative Molecular Discovery
Yuchen Zhu, Donghai Zhao, Yangyang Zhang +10
Chemical space exploration underlies drug discovery, yet most generative models treat chemical space as a fixed, implicitly learned distribution, focusing on sampling molecules rat…
Towards Effective Code-Integrated Reasoning
Fei Bai, Yingqian Min, Beichen Zhang +6
In this paper, we investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter. To acquire thi…
Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
An Yang, Beichen Zhang, Binyuan Hui +13
In this report, we present a series of math-specific large language models: Qwen2.5-Math and Qwen2.5-Math-Instruct-1.5B/7B/72B. The core innovation of the Qwen2.5 series lies in in…
ProcessBench: Identifying Process Errors in Mathematical Reasoning
Chujie Zheng, Zhenru Zhang, Beichen Zhang +6
As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalab…