Youliang Yuan

Youliang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 19 papers 3 months ago

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Paper • 2308.06463 • Published Aug 12, 2023 • 1

CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis

Paper • 2407.13301 • Published Jul 18 • 54

Qwen2 Technical Report

Paper • 2407.10671 • Published Jul 15 • 155

Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning

Paper • 2406.02265 • Published Jun 4 • 6

RRM: Relightable assets using Radiance guided Material extraction

Paper • 2407.06397 • Published Jul 8 • 4

Characterizing Prompt Compression Methods for Long Context Inference

Paper • 2407.08892 • Published Jul 11 • 9

TCAN: Animating Human Images with Temporally Consistent Pose Guidance using Diffusion Models

Paper • 2407.09012 • Published Jul 12 • 8

New Desiderata for Direct Preference Optimization

Paper • 2407.09072 • Published Jul 12 • 9

GAVEL: Generating Games Via Evolution and Language Models

Paper • 2407.09388 • Published Jul 12 • 14

StyleSplat: 3D Object Style Transfer with Gaussian Splatting

Paper • 2407.09473 • Published Jul 12 • 10

Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis

Paper • 2407.09732 • Published Jul 13 • 8

Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing

Paper • 2407.08770 • Published Jul 11 • 19

Transformer Layers as Painters

Paper • 2407.09298 • Published Jul 12 • 13

H2O-Danube3 Technical Report

Paper • 2407.09276 • Published Jul 12 • 18

MUSCLE: A Model Update Strategy for Compatible LLM Evolution

Paper • 2407.09435 • Published Jul 12 • 20

SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers

Paper • 2407.09413 • Published Jul 12 • 9

Toto: Time Series Optimized Transformer for Observability

Paper • 2407.07874 • Published Jul 10 • 29

Human-like Episodic Memory for Infinite Context LLMs

Paper • 2407.09450 • Published Jul 12 • 58

SpreadsheetLLM: Encoding Spreadsheets for Large Language Models

Paper • 2407.09025 • Published Jul 12 • 128

upvoted a paper 4 months ago

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Paper • 2407.09121 • Published Jul 12 • 5