Publications (21)
SeisGPT: A Physics-Informed Data-Driven Large Model for Real-Time Seismic Response Prediction
Shiqiao Meng, Ying Zhou, Qinghua Zheng +4
Accurately predicting the dynamic responses of building structures under seismic loads is essential for ensuring structural safety and minimizing potential damage. This critical as…
GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
V Team, Wenyi Hong, Wenmeng Yu +90
We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this…
Bootstrapping a User-Centered Task-Oriented Dialogue System
Shijie Chen, Ziru Chen, Xiang Deng +8
We present TacoBot, a task-oriented dialogue system built for the inaugural Alexa Prize TaskBot Challenge, which assists users in completing multi-step cooking and home improvement…
SciNav: A General Agent Framework for Scientific Coding Tasks
Tianshu Zhang, Huan Sun
Autonomous science agents built on large language models (LLMs) are increasingly used to generate hypotheses, design experiments, and produce reports. However, prior work mainly ta…
TableLlama: Towards Open Large Generalist Models for Tables
Tianshu Zhang, Xiang Yue, Yifei Li +1
Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically interpret, augment, and query tables. Current methods often require pretraining o…
Nonreciprocal subdiffraction imaging with staggered gyromagnetic photonic crystals
Rui Ding, Tianshu Zhang, Jiarui Yu +4
Subdiffraction imaging serves as a novel technique to enhance the optical imaging resolution, where a backscattering-free approach remains so far unavailable. Here, we theoreticall…
Exploring Chain-of-Thought Style Prompting for Text-to-SQL
Chang-You Tai, Ziru Chen, Tianshu Zhang +2
In-context learning with large language models (LLMs) has recently caught increasing attention due to its superior few-shot performance on various tasks. However, its performance o…
Roll Up Your Sleeves: Working with a Collaborative and Engaging Task-Oriented Dialogue System
Lingbo Mo, Shijie Chen, Ziru Chen +10
We introduce TacoBot, a user-centered task-oriented digital assistant designed to guide users through complex real-world tasks with multiple steps. Covering a wide range of cooking…
Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification
Tianshu Zhang, Yan Wang, Ji Qi +1
Spatio-temporal grounding in long videos requires precise temporal localization and robust object tracking conditioned on natural-language queries. While recent vision-language mod…
ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
Junzhe Chen, Tianshu Zhang, Shiyu Huang +4
Despite the recent breakthroughs achieved by Large Vision Language Models (LVLMs) in understanding and responding to complex visual-textual contexts, their inherent hallucination t…
D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery
Hanane Nour Moussa, Yifei Li, Zhuoyang Li +7
Despite recent progress in language models and agents for scientific data-driven discovery, further advancing their capabilities is held back by the absence of verifiable environme…
EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution
Tianshu Zhang, Kun Qian, Siddhartha Sahai +4
Neural text-to-SQL models, which translate natural language questions (NLQs) into SQL queries given a database schema, have achieved remarkable performance. However, database schem…
Few-shot Adaptation of Multi-modal Foundation Models: A Survey
Fan Liu, Tianshu Zhang, Wenwen Dai +3
Multi-modal (vision-language) models, such as CLIP, are replacing traditional supervised pre-training models (e.g., ImageNet-based pre-training) as the new generation of visual fou…
Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
Tian Qin, Junzhe Chen, Yuqing Shi +3
Large vision-language models (LVLMs) often hallucinate when language priors dominate weak or ambiguous visual evidence. Existing contrastive decoding methods mitigate this problem…
S4DL: Shift-sensitive Spatial-Spectral Disentangling Learning for Hyperspectral Image Unsupervised Domain Adaptation
Jie Feng, Tianshu Zhang, Junpeng Zhang +4
Unsupervised domain adaptation techniques, extensively studied in hyperspectral image (HSI) classification, aim to use labeled source domain data and unlabeled target domain data t…
Ambient Backscatter Communication in LTE Uplink Sounding Reference Signal
Jingyi Liao, Tianshu Zhang, Kalle Ruttik +2
Ambient Internet of Things (AIoT), recently standardized by the 3rd Generation Partnership Project (3GPP), demands a low-power wide-area communication solution that operates severa…
OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination
Junzhe Chen, Tianshu Zhang, Shiyu Huang +6
Recently, Omni-modal large language models (OLLMs) have sparked a new wave of research, achieving impressive results in tasks such as audio-video understanding and real-time enviro…
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
Boyu Gou, Zanming Huang, Yuting Ning +23
Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major s…
Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras
Buzhen Huang, Yuan Shu, Tianshu Zhang +1
Dynamic multi-person mesh recovery has been a hot topic in 3D vision recently. However, few works focus on the multi-person motion capture from uncalibrated cameras, which mainly f…
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
V Team, Wenyi Hong, Xiaotao Gu +94
We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depen…
Federated Learning for Semantic Parsing: Task Formulation, Evaluation Setup, New Algorithms
Tianshu Zhang, Changchang Liu, Wei-Han Lee +2
This paper studies a new task of federated learning (FL) for semantic parsing, where multiple clients collaboratively train one global model without sharing their semantic parsing…