Tianyi Zhou

34

Papers

459

Total Citations

Papers (34)

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models

Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free

DataGen: Unified Synthetic Dataset Generation via Large Language Models

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding

Transformers Learn Low Sensitivity Functions: Investigations and Implications

Many-Objective Multi-Solution Transport

Learning To Collaborate in Decentralized Learning of Personalized Models

Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering

Subclass-balancing Contrastive Learning for Long-tailed Recognition

When to Learn What: Model-Adaptive Data Augmentation Curriculum

Diffusion Curriculum: Synthetic-to-Real Data Curriculum via Image-Guided Diffusion

Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld

InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models

One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts

ODIN: Disentangled Reward Mitigates Hacking in RLHF

Position: TrustLLM: Trustworthiness in Large Language Models

Diverse Ensemble Evolution: Curriculum Data-Model Marriage

Learning to Propagate for Graph Meta-Learning

Curriculum-guided Hindsight Experience Replay

Curriculum Learning by Dynamic Instance Hardness

Constrained Robust Submodular Partitioning

CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum

Class-Disentanglement and Applications in Adversarial Detection and Defense

Federated Learning from Pre-Trained Models: A Contrastive Learning Approach

Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach

Retrospective Adversarial Replay for Continual Learning

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Structured Federated Learning through Clustered Additive Modeling

Module-wise Adaptive Distillation for Multimodality Foundation Models

Bias Also Matters: Bias Attribution for Deep Neural Network Explanation

Jumpout : Improved Dropout for Deep Neural Networks with ReLUs