Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
Paper • 2605.10664 • Published • 9
AI & ML interests
We develop data-driven computational methods and intelligent systems to facilitate decision making.
Recent Activity
View all activity
Papers
Uncovering Cross-Objective Interference in Multi-Objective Alignment
A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchain
franciscoliuÂ
submitted a
paper to Daily Papers 9 days ago
hydangÂ
authored 3
papers about 1 month ago
A Quantitative Review on Language Model Efficiency Research
Paper • 2306.01768 • Published • 2
Optimizing Decomposition for Optimal Claim Verification
Paper • 2503.15354 • Published • 18
Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates
Paper • 2509.18076 • Published
franciscoliuÂ
authored a
paper 3 months ago
ylu610Â
authored a
paper 3 months ago
ylu610Â
updated a
Space 3 months ago
ylu610Â
published a
Space 3 months ago
ylu610Â
submitted a
paper to Daily Papers 3 months ago
ylu610Â
authored a
paper 6 months ago
ylu610Â
authored a
paper 8 months ago
ylu610Â
authored a
paper about 1 year ago
mjiang89Â
authored 8
papers over 1 year ago
Traceability Transformed: Generating more Accurate Links with Pre-Trained BERT Models
Paper • 2102.04411 • Published
Enhancing Automated Software Traceability by Transfer Learning from Open-World Data
Paper • 2207.01084 • Published
Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training
Paper • 2404.14604 • Published
Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
Paper • 2406.12050 • Published • 19
LEOPARD : A Vision Language Model For Text-Rich Multi-Image Tasks
Paper • 2410.01744 • Published • 27
Graph Diffusion Transformers for Multi-Conditional Molecular Generation
Paper • 2401.13858 • Published • 1
MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems
Paper • 2410.14179 • Published
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Paper • 2410.22108 • Published • 1