41 citations · 227 across the 55 of their papers we have counts for
57 papers
LIBERO-VPro: Benchmarking Closed-Loop Visual Robustness of Robotic Foundation Models
Huiqiong Li, Zhiting Mei, Anirudha Majumdar +3
Robotic foundation models achieve impressive performance on standard manipulation benchmarks, yet these evaluations typically assume clean, timely, and consistent visual observatio…
Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement
Jiarui Yang, Jiajin Zhang, Bin Zhu +2
Online post-training of vision-language-action (VLA) models requires efficient use of robot interaction and reliable policy improvement from continually collected experience. We pr…
StructRL: Structured Action-Space Exploration for Flow-Based VLAs
Jiarui Yang, Bin Zhu, Jingjing Chen +4
Flow-based Vision-Language-Action (VLA) models are now widely used for continuous robotic manipulation, and online reinforcement learning (RL) is emerging as a key technique for ad…
SphereVideo: Prototype-anchored Hyperspherical Boundary for Continual AI-generated Video Detection
Fei Li, Yue Yu, Yuran Wang +3
AI-generated video (AIGV) detection aims to distinguish real videos from AI-generated ones. In practice, detectors trained on existing data often fail to generalize to newly emergi…
Disentangling Semantic Attention from Structural Bias in the Attention Manifold
Pengkun Jiao, Bin Zhu, Jingjing Chen +1
The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws. Specifically, MLLMs consistently exhibit disprop…
Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models
Ziyao Tang, Pengkun Jiao, Bin Zhu +3
Video Large Language Models (Vid-LLMs) have demonstrated remarkable performance in video understanding tasks, yet their robustness under conversational interaction remains largely…
SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning
Yian Li, Yang Jiao, Bin Zhu +4
Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language…
RC-NF: Robot-Conditioned Normalizing Flow for Real-Time Anomaly Detection in Robotic Manipulation
Shijie Zhou, Bin Zhu, Jiarui Yang +3
Recent advances in Vision-Language-Action (VLA) models have enabled robots to execute increasingly complex tasks. However, VLA models trained through imitation learning struggle to…
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Hui Zhang, Juntao Liu, Zongkai Liu +4
Instruction-based image editing aims to modify specific content within existing images according to user-provided instructions while preserving non-target regions. Beyond tradition…
VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation
Feng Han, Chao Gong, Zhipeng Wei +2
Recently, autoregressive image generation models have wowed audiences with their remarkable capability in creating surprisingly realistic images. Models such as GPT-4o and LlamaGen…
Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
Jiarui Yang, Bin Zhu, Jingjing Chen +1
Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promisin…
Benchmarking Gaslighting Negation Attacks Against Reasoning Models
Bin Zhu, Hailong Yin, Jingjing Chen +1
Recent advances in reasoning-centric models promise improved robustness through mechanisms such as chain-of-thought prompting and test-time scaling. However, their ability to withs…
ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning
Feng Han, Yang Jiao, Shaoxiang Chen +3
The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, cont…
OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks
Jiayu Wang, Yang Jiao, Yue Yu +4
Recent breakthroughs in large multimodal models (LMMs), such as the impressive GPT-4o-Native, have demonstrated remarkable proficiency in following general-purpose instructions for…
Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs
Pengkun Jiao, Bin Zhu, Jingjing Chen +2
Large Multimodal Models (LMMs) have demonstrated remarkable capabilities across a wide range of tasks. However, their vulnerability to user gaslighting-the deliberate use of mislea…
UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding
Yang Jiao, Haibo Qiu, Zequn Jie +4
We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integratio…
Mirror Descent Linearized Augmented Lagrangian Methods for Nonconvex Constrained Stochastic Zeroth-Order Optimization
Qiankun Shi, Han Yuan, Xiao Wang +1
In this paper, we study nonconvex constrained stochastic zeroth-order optimization problems with exact constraints and stochastic objective evaluations. To solve this class of prob…
Revealing the Implicit Noise-based Imprint of Generative Models
Xinghan Li, Yue Yu, Xue Song +2
With the rapid advancement of vision generation models, the potential security risks stemming from synthetic visual content have garnered increasing attention, posing significant c…
Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics
Georgii Gotin, Ekaterina Shumitskaya, Anastasia Antsiferova +1
Recent studies have revealed that modern image and video quality assessment (IQA/VQA) metrics are vulnerable to adversarial attacks. An attacker can manipulate a video through prep…
DuMo: Dual Encoder Modulation Network for Precise Concept Erasure
Feng Han, Kai Chen, Chao Gong +3
The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copy…
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
Xue Song, Jiequan Cui, Hanwang Zhang +4
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient s…
Retrieval Augmented Recipe Generation
Guoshan Liu, Hailong Yin, Bin Zhu +3
Given the potential applications of generating recipes from food images, this area has garnered significant attention from researchers in recent years. Existing works for recipe ge…
From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning
Pengkun Jiao, Bin Zhu, Jingjing Chen +2
Efficient Visual Instruction Fine-Tuning (EVIT) seeks to adapt Multimodal Large Language Models (MLLMs) to downstream tasks with minimal computational overhead. However, as task di…
EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models
Jiacheng Zhang, Yang Jiao, Shaoxiang Chen +2
Recently, Multimodal Large Language Models (MLLMs) have sparked great research interests owing to their exceptional content-reasoning and instruction-following capabilities. To eff…