13 citations · 33 across the 14 of their papers we have counts for
14 papers
Cosmos 3: Omnimodal World Models for Physical AI
NVIDIA, :, Aditi +293
We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-t…
Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges
Qin Liu, Wenjie Mo, Terry Tong +4
The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models sca…
Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
Terry Tong, Jiashu Xu, Qin Liu +1
Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single uttera…
Instructional Fingerprinting of Large Language Models
Jiashu Xu, Fei Wang, Mingyu Derek Ma +3
The exorbitant cost of training Large language models (LLMs) from scratch makes it essential to fingerprint the models to protect intellectual property via ownership authentication…
DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
Brian Nlong Zhao, Yuhang Xiao, Jiashu Xu +6
The popularization of Text-to-Image (T2I) diffusion models enables the generation of high-quality images from text descriptions. However, generating diverse customized images with…
Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
Wenjie Mo, Jiashu Xu, Qin Liu +5
Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the c…
Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +3
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.).…
Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
Jiashu Xu, Mingyu Derek Ma, Fei Wang +2
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performanc…
EM-Paste: EM-guided Cut-Paste with DALL-E Augmentation for Image-level Weakly Supervised Instance Segmentation
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +2
We propose EM-PASTE: an Expectation Maximization(EM) guided Cut-Paste compositional dataset augmentation approach for weakly-supervised instance segmentation using only image-level…
Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?
Jiashu Xu, Mingyu Derek Ma, Muhao Chen
Two key obstacles in biomedical relation extraction (RE) are the scarcity of annotations and the prevalence of instances without explicitly pre-defined labels due to low annotation…
Neural-Sim: Learning to Generate Training Data with NeRF
Yunhao Ge, Harkirat Behl, Jiashu Xu +6
Training computer vision models usually requires collecting and labeling vast amounts of imagery under a diverse set of scene configurations and properties. This process is incredi…
DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection
Yunhao Ge, Jiashu Xu, Brian Nlong Zhao +3
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-toimage synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.).…
Unified Semantic Typing with Meaningful Label Inference
James Y. Huang, Bangzheng Li, Jiashu Xu +1
Semantic typing aims at classifying tokens or spans of interest in a textual context into semantic categories such as relations, entity types, and event types. The inferred labels…
SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning
Aaron Chan, Jiashu Xu, Boyuan Long +3
Augmenting pre-trained language models with knowledge graphs (KGs) has achieved success on various commonsense reasoning tasks. However, for a given task instance, the KG, or certa…