← Search

Jianguo Zhang

44 accepted papers

2026

EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization

ICML 2026poster

Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantly rely on stochastic, hand-crafted operators that overlook the underlying performance landscape of the coefficient space…

Cited by 0SourceScholar
2026

Position: Vector Prompt Interfaces Should Be Exposed to Enable Customization of Large Language Models

ICML 2026poster

As large language models (LLMs) transition from research prototypes to real-world systems, customization has emerged as a central bottleneck. While text prompts can already customize LLM behavior, we argue that text-only prompting does not constitute a suitable control interface for scalable, stable…

Cited by 0SourceScholar
2026

Test-Time Adaptation for LLM Agents via Environment Interaction

ICLR 2026poster

Large language model (LLM)-based agents struggle to generalize to novel and complex environments, such as unseen websites or new sets of functions, due to a fundamental mismatch between their pre-training and test-time conditions. This challenge stems from two distinct failure modes: a syntactic mis…

Cited by 0SourcecodeScholar
2026

TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing

AAAI 2026technical

Scene Text Editing (STE) aims to naturally modify text in images while preserving visual consistency, the decisive factors of which can be divided into three parts, i.e., text style, text content, and background. Previous methods have struggled with incomplete disentanglement of editable attributes,

Cited by 0SourcePDFScholar
2025

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

NeurIPS 2025poster

Training effective AI agents for multi-turn interactions requires high-quality data that captures realistic human-agent dynamics, yet such data is scarce and expensive to collect manually. We introduce APIGen-MT, a two-phase framework that generates verifiable and diverse multi-turn agent data. In t…

Cited by 0SourceScholar
2025

ActionStudio: A Lightweight Framework for Data and Training of Large Action Models

EMNLP 2025

Large Action models are essential for enabling autonomous agents to perform complex tasks. However, training such models remains challenging due to the diversity of agent environments and the complexity of noisy agentic data. Existing infrastructure offers limited support for scalable, agent-specifi

2025

Bridging the Data Provenance Gap Across Text, Speech, and Video

ICLR 2025poster

Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities --- pop…

Cited by 1SourcePDFScholar
2025

Enhancing Low-Light Images: A Synthetic Data Perspective on Practical and Generalizable Solutions

AAAI 2025technical

Recently, deep neural networks (DNNs) have emerged as the leading approach for low-light image enhancement (LLIE). However, training these models generally requires large-scale paired datasets, which are challenging to obtain due to the labor-intensive and time-consuming nature of real-world data co…

2025

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback

ACL 2025finding

Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. To address these issues, we present LAM SIMULATOR, a compr…

Cited by 0SourcePDFScholar
2025

LATTE: Learning to Think with Vision Specialists

EMNLP 2025

While open-source vision-language models perform well on simple question-answering, they still struggle with complex questions that require both perceptual and reasoning capabilities. We propose LATTE, a family of vision-language models that have LeArned to Think wiTh vision spEcialists. By offloadi

2025

Open-Det: An Efficient Learning Framework for Open-Ended Detection

ICML 2025poster

Open-Ended object Detection (OED) is a novel and challenging task that detects objects and generates their category names in a free-form manner, without requiring additional vocabularies during inference. However, the existing OED models, such as GenerateU, require large-scale datasets for training,…

2025

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data

ACL 2025finding

Personalization is essential for AI assistants, especially in private AI settings where models are expected to interpret users’ personal data (e.g., conversations, app usage) to understand their background, preferences, and social context. However, due to privacy concerns, existing academic research…

Cited by 23SourcePDFScholar
2025

ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations

ICCV 2025poster

Referring video object segmentation (RVOS) aims to segment target objects throughout a video based on a text description. This is challenging as it involves deep vision-language understanding, pixel-level dense prediction and spatiotemporal reasoning. Despite notable progress in recent years, existi…

Cited by 0SourcePDFScholar
2025

SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models

AAAI 2025technical

Known as low energy consumption networks, spiking neural networks (SNNs) have gained a lot of attention within the past decades. While SNNs are increasing competitive with artificial neural networks (ANNs) for vision tasks, they are rarely used for long sequence tasks, despite their intrinsic tempor…

2025

Underwater Motions Analysis and Control of a Coupling-Tiltable Unmanned Aerial-Aquatic Vehicle

ICRA 2025

Coupling-Tiltable Unmanned Aerial-Aquatic Vehicles (UAAVs) have gained increasing importance, yet lack comprehensive analysis and suitable controllers. This paper analyzes the underwater motion characteristics of a self-designed UAAV, Mirs-Alioth, and designs a controller for it. The effectiveness o

Cited by 1SourceScholar
2025

Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints

ICCV 2025poster

Part-level features are crucial for image understanding, but few studies focus on them because of the lack of fine-grained labels. Although unsupervised part discovery can eliminate the reliance on labels, most of them cannot maintain robustness across various categories and scenarios, which restric…

2025

xLAM: A Family of Large Action Models to Empower AI Agent Systems

NAACL 2025long

Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protoco…

2024

APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets

NeurIPS 2024poster

The advancement of function-calling agent models requires diverse, reliable, and high-quality datasets. This paper presents APIGen, an automated data generation pipeline designed to synthesize high-quality datasets for function-calling applications. We leverage APIGen and collect 3,673 executable AP…

2024

Consent in Crisis: The Rapid Decline of the AI Data Commons

NeurIPS 2024poster

General-purpose artificial intelligence (AI) systems are built on massive swathes of public web data, assembled into corpora such as C4, RefinedWeb, and Dolma. To our knowledge, we conduct the first, large-scale, longitudinal audit of the consent protocols for the web domains underlying AI training…

Cited by 36SourceScholar
2024

Gradient-Guided Modality Decoupling for Missing-Modality Robustness

AAAI 2024technical

Multimodal learning with incomplete input data (missing modality) is very practical and challenging. In this work, we conduct an in-depth analysis of this challenge and find that modality dominance has a significant negative impact on the model training, greatly degrading the missing modality perfor…

2024

MLP-DINO: Category Modeling and Query Graphing with Deep MLP for Object Detection

IJCAI 2024poster

Popular transformer-based detectors detect objects in a one-to-one manner, where both the bounding box and category of each object are predicted only by the single query, leading to the box-sensitive category predictions. Additionally, the initialization of positional queries solely based on the pre…

2024

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

ICLR 2024spotlight

Recent months have seen the emergence of a powerful new trend in which large language models (LLMs) are augmented to become autonomous language agents capable of performing objective oriented multi-step tasks on their own, rather than merely responding to queries from human users. Most existing lang…

2024

Using Left and Right Brains Together: Towards Vision and Language Planning

ICML 2024poster

Large Language Models (LLMs) and Large Multi-modality Models (LMMs) have demonstrated remarkable decision masking capabilities on a variety of tasks. However, they inherently operate planning within the language space, lacking the vision and spatial imagination ability. In contrast, humans utilize b…

Cited by 5SourcePDFScholar
2023

Cross Contrasting Feature Perturbation for Domain Generalization

ICCV 2023poster

Domain generalization (DG) aims to learn a robust model from source domains that generalize well on unseen target domains. Recent studies focus on generating novel domain samples or features to diversify distributions complementary to source domains. Yet, these approaches can hardly deal with the re…

Cited by 26PDFcodeScholar
2023

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems

ICLR 2023poster

When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward functio…

2023

Feature Alignment and Uniformity for Test Time Adaptation

CVPR 2023poster

Test time adaptation (TTA) aims to adapt deep neural networks when receiving out of distribution test domain samples. In this setting, the model can only access online unlabeled test samples and pre-trained models on the training domains. We first address TTA as a feature revision problem due to the…

2023

Rethinking Alignment and Uniformity in Unsupervised Image Semantic Segmentation

AAAI 2023technical

Unsupervised image segmentation aims to match low-level visual features with semantic-level representations without outer supervision. In this paper, we address the critical properties from the view of feature alignments and feature uniformity for UISS models. We also make a comparison between UISS…

Cited by 22SourcePDFScholar
2023

Strip-MLP: Efficient Token Interaction for Vision MLP

ICCV 2023poster

Token interaction operation is one of the core modules in MLP-based models to exchange and aggregate information between different spatial locations. However, the power of token interaction on the spatial dimension is highly dependent on the spatial resolution of the feature maps, which limits the m…

Cited by 13PDFcodeScholar
2022

Density-driven Regularization for Out-of-distribution Detection

NeurIPS 2022accept

Detecting out-of-distribution (OOD) samples is essential for reliably deploying deep learning classifiers in open-world applications. However, existing detectors relying on discriminative probability suffer from the overconfident posterior estimate for OOD data. Other reported approaches either impo…

Cited by 17SourcePDFScholar
2022

Differentiable hierarchical and surrogate gradient search for spiking neural networks

NeurIPS 2022accept

Spiking neural network (SNN) has been viewed as a potential candidate for the next generation of artificial intelligence with appealing characteristics such as sparse computation and inherent temporal dynamics. By adopting architectures of deep artificial neural networks (ANNs), SNNs are achieving c…

2022

Discrete Time Convolution for Fast Event-Based Stereo

CVPR 2022poster

Inspired by biological retina, dynamical vision sensor transmits events of instantaneous changes of pixel intensity, giving it a series of advantages over traditional frame-based camera, such as high dynamical range, high temporal resolution and low power consumption. However, extracting information…

Cited by 32PDFcodeScholar
2022

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning

CVPR 2022poster

Heatmap regression methods have dominated face alignment area in recent years while they ignore the inherent relation between different landmarks. In this paper, we propose a Sparse Local Patch Transformer (SLPT) for learning the inherent relation. The SLPT generates the representation of each singl…

Cited by 62PDFcodeScholar
2022

TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning

ECCV 2022poster

"This paper presents a transformer framework for few-shot learning, termed TransVLAD, with one focus showing the power of locally aggregated descriptors for few-shot learning. Our TransVLAD model is simple: a standard transformer encoder following a NeXtVLAD aggregation module to output the locally…

Cited by 10SourcePDFScholar
2021

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning

EMNLP 2021main

In this work, we focus on a more challenging few-shot intent detection scenario where many intents are fine-grained and semantically similar. We present a simple yet effective few-shot intent detection schema via contrastive pre-training and fine-tuning. Specifically, we first conduct self-supervise…

2021

HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive Summarization

EMNLP 2021main

To capture the semantic graph structure from raw text, most existing summarization approaches are built on GNNs with a pre-trained model. However, these methods suffer from cumbersome procedures and inefficient computations for long-text documents. To mitigate these issues, this paper proposes HetFo…

2021

Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction From Raw Point Clouds

CVPR 2021poster

Shape modeling and reconstruction from raw point clouds of objects stand as a fundamental challenge in vision and graphics research. Classical methods consider analytic shape priors; however, their performance is degraded when the scanned points deviate from the ideal conditions of cleanness and com…

Cited by 39PDFScholar
2020

TEA: Temporal Excitation and Aggregation for Action Recognition

CVPR 2020poster

Temporal modeling is key for action recognition in videos. It normally considers both short-range motions and long-range aggregations. In this paper, we propose a Temporal Excitation and Aggregation (TEA) block, including a motion excitation (ME) module and a multiple temporal aggregation (MTA) modu…

Cited by 638PDFScholar
2019

Progressive Teacher-Student Learning for Early Action Prediction

CVPR 2019poster

The goal of early action prediction is to recognize actions from partially observed videos with incomplete action executions, which is quite different from action recognition. Predicting early actions is very challenging since the partially observed videos do not contain enough action information fo…

Cited by 166PDFcodeScholar
2018

Deep Bilinear Learning for RGB-D Action Recognition

ECCV 2018poster

In this paper, we focus on exploring modality-temporal mutual information for RGB-D action recognition. In order to learn time-varying information and multi-modal features jointly, we propose a novel deep bilinear learning framework. In the framework, we propose bilinear blocks that consist of two l…

Cited by 116SourcePDFScholar
2018

Discriminative Learning of Latent Features for Zero-Shot Recognition

CVPR 2018poster

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the proper mapping matrices aligning the visual and semantic space, whilst the importanc…

Cited by 196SourcePDFScholar
2017

Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-Identification

CVPR 2017spotlight

Person re-identification (ReID) is an important task in wide area video surveillance which focuses on identifying people across different cameras. Recently, deep learning networks with a triplet loss become a common framework for person ReID. However, the triplet loss pays main attentions on obtaini…

Cited by 1545PDFScholar
2015

Jointly Learning Heterogeneous Features for RGB-D Activity Recognition

CVPR 2015poster

In this paper, we focus on heterogeneous feature learning for RGB-D activity recognition. Considering that features from different channels could share some similar hidden structures, we propose a joint learning model to simultaneously explore the shared and feature-specific components as an instanc…

Cited by 687SourcePDFScholar