Tianlong Chen

56

Papers

92

Total Citations

Papers (56)

DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis

Facial Affective Behavior Analysis with Instruction Tuning

Graph Sparsification via Mixture of Graphs

PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches

Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints

Mapping from Meaning: Addressing the Miscalibration of Prompt-Sensitive Language Models

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts

Evolution-Inspired Loss Functions for Protein Representation Learning

Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness

Position: TrustLLM: Trustworthiness in Large Language Models

Adversarial Robustness: From Self-Supervised Pre-Training to Fine-Tuning

L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks

Troubleshooting Blind Image Quality Models in the Wild

Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free

The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy

CADTransformer: Panoptic Symbol Spotting Transformer for CAD Drawings

Aug-NeRF: Training Stronger Neural Radiance Fields With Triple-Level Physically-Grounded Augmentations

ABD-Net: Attentive but Diverse Person Re-Identification

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts

Robust Mixture-of-Expert Training for Convolutional Neural Networks

AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts

HALO: Hardware-Aware Learning to Optimize

Point Cloud Domain Adaptation via Masked Local 3D Structure Prediction

DNA: Improving Few-Shot Transfer Learning with Low-Rank Decomposition and Alignment

Scalable Learning to Optimize: A Learned Optimizer Can Train Big Models

The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective

Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study

Tuning-Free Accountable Intervention for LLM Deployment – a Metacognitive Approach

TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models

Molecular Data Programming: Towards Molecule Pseudo-labeling with Systematic Weak Supervision

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

Learning to Optimize in Swarms

Graph Contrastive Learning with Augmentations

Training Stronger Baselines for Learning to Optimize

Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free

The Lottery Ticket Hypothesis for Pre-trained BERT Networks

Robust Pre-Training by Adversarial Contrastive Learning

You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership

Improving Contrastive Learning on Imbalanced Data via Open-World Sampling

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?

Chasing Sparsity in Vision Transformers: An End-to-End Exploration

Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective

Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative

Sparse Winning Tickets are Data-Efficient Image Recognizers

A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking

Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again

Advancing Model Pruning via Bi-level Optimization

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets

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

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter