Picture for Chris Biemann

Chris Biemann

Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark

Add code
Mar 13, 2025
Viaarxiv icon

Self-Taught Self-Correction for Small Language Models

Add code
Mar 11, 2025
Viaarxiv icon

Argument-Based Comparative Question Answering Evaluation Benchmark

Add code
Feb 20, 2025
Viaarxiv icon

GIMMICK -- Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarking

Add code
Feb 19, 2025
Viaarxiv icon

MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching

Add code
Feb 18, 2025
Viaarxiv icon

Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model

Add code
Jan 09, 2025
Figure 1 for Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Figure 2 for Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Figure 3 for Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Figure 4 for Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Viaarxiv icon

CogSteer: Cognition-Inspired Selective Layer Intervention for Efficient Semantic Steering in Large Language Models

Add code
Oct 23, 2024
Figure 1 for CogSteer: Cognition-Inspired Selective Layer Intervention for Efficient Semantic Steering in Large Language Models
Figure 2 for CogSteer: Cognition-Inspired Selective Layer Intervention for Efficient Semantic Steering in Large Language Models
Figure 3 for CogSteer: Cognition-Inspired Selective Layer Intervention for Efficient Semantic Steering in Large Language Models
Figure 4 for CogSteer: Cognition-Inspired Selective Layer Intervention for Efficient Semantic Steering in Large Language Models
Viaarxiv icon

Large Language Models Are Overparameterized Text Encoders

Add code
Oct 18, 2024
Figure 1 for Large Language Models Are Overparameterized Text Encoders
Figure 2 for Large Language Models Are Overparameterized Text Encoders
Figure 3 for Large Language Models Are Overparameterized Text Encoders
Figure 4 for Large Language Models Are Overparameterized Text Encoders
Viaarxiv icon

Demarked: A Strategy for Enhanced Abusive Speech Moderation through Counterspeech, Detoxification, and Message Management

Add code
Jun 27, 2024
Viaarxiv icon

Low-Resource Machine Translation through the Lens of Personalized Federated Learning

Add code
Jun 18, 2024
Figure 1 for Low-Resource Machine Translation through the Lens of Personalized Federated Learning
Figure 2 for Low-Resource Machine Translation through the Lens of Personalized Federated Learning
Figure 3 for Low-Resource Machine Translation through the Lens of Personalized Federated Learning
Figure 4 for Low-Resource Machine Translation through the Lens of Personalized Federated Learning
Viaarxiv icon