7 citations · 13 across the 18 of their papers we have counts for
19 papers
Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
Yongjiang Liu, Jie Zhang, Haoyue Zhang +3
Equipping VLM agents with world modeling capabilities has shown strong potential for complex reasoning and long-horizon planning, while reducing the dependence of policy learning o…
OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language Models
Xiaocheng Lu, Hualei Zhang, Shuhan Guo +8
Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step distillation accelerates deco…
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
Xuanzhi Feng, Zhengyang Li, Zeyu Liu +6
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instability: uni…
Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations
Zeyu Liu, Xuanzhi Feng, Sing Kwong Lai +6
The financial market is a typical low signal-to-noise ratio (SNR) setting, which often destabilizes off-policy maximum-entropy methods like Soft Actor-Critic (SAC). Specifically, n…
AdaTok: Self-Budgeting Image Tokenization with Quality-Preserving Dynamic Tokens
Xiaocheng Lu, Yuxi Chen, Jie Zhang +5
Image tokenizers, from 2D grids to recent 1D sequences, typically encode every image with the same fixed number of tokens. Yet visual complexity is highly heterogeneous, so a unifo…
READER: Dynamic LLM Provenance from Query-Varying Interactions
Jiaxu Liu, Sunnan Mu, Dong Huang +3
Existing black-box LLM provenance methods achieve comparability by querying every candidate model with the same diagnostic prompts. In deployment, auditors inherit a different evid…
DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
Hongxu Ma, Lin Wang, Chenghou Jin +6
Ordinal Regression (OR) aims to predict target values with inherent order, underpinning critical applications across diverse domains, from recommender systems to computer vision. T…
Laundering AI Authority with Adversarial Examples
Jie Zhang, Pura Peetathawatchai, Florian Tramèr +1
Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly…
What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity
Haoxi Li, Qinglin Hou, Jianfei Ma +6
To navigate partially observable visual environments, recent VLM agents increasingly internalize world modeling capabilities into their policies via explicit CoT reasoning, enablin…
DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning
Sikai Bai, Jie Zhang, Shuaicheng Li +5
Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data, and federated domain generalization further considers the test dataset (target doma…
Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning
Zhijie Rao, Jingcai Guo, Xiaocheng Lu +5
Generalized Zero-shot Learning (GZSL) has yielded remarkable performance by designing a series of unbiased visual-semantics mappings, wherein, the precision relies heavily on the c…
FreePIH: Training-Free Painterly Image Harmonization with Diffusion Model
Ruibin Li, Jingcai Guo, Song Guo +2
This paper provides an efficient training-free painterly image harmonization (PIH) method, dubbed FreePIH, that leverages only a pre-trained diffusion model to achieve state-of-the…
GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning
Ziming Liu, Jingcai Guo, Xiaocheng Lu +3
This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein, the model is trained to recognize multiple unseen classes within a…
Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
Ruibin Li, Qihua Zhou, Song Guo +5
Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content, opening up the opportunity to improve image super-resol…
Exploring Optimal Substructure for Out-of-distribution Generalization via Feature-targeted Model Pruning
Yingchun Wang, Jingcai Guo, Song Guo +2
Recent studies show that even highly biased dense networks contain an unbiased substructure that can achieve better out-of-distribution (OOD) generalization than the original model…
Efficient Stein Variational Inference for Reliable Distribution-lossless Network Pruning
Yingchun Wang, Song Guo, Jingcai Guo +4
Network pruning is a promising way to generate light but accurate models and enable their deployment on resource-limited edge devices. However, the current state-of-the-art assumes…
Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application
Leijie Wu, Song Guo, Yaohong Ding +4
Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However,…
Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations
Tao Guo, Song Guo, Jiewei Zhang +2
Recently, the enactment of privacy regulations has promoted the rise of the machine unlearning paradigm. Existing studies of machine unlearning mainly focus on sample-wise unlearni…
From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization
Feijie Wu, Song Guo, Haozhao Wang +4
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizin…