Picture for Marjan Ghazvininejad

Marjan Ghazvininejad

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs

Add code
Mar 14, 2025
Viaarxiv icon

Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models

Add code
Feb 20, 2025
Viaarxiv icon

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge

Add code
Jan 30, 2025
Figure 1 for Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
Figure 2 for Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
Figure 3 for Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
Figure 4 for Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
Viaarxiv icon

ALMA: Alignment with Minimal Annotation

Add code
Dec 05, 2024
Figure 1 for ALMA: Alignment with Minimal Annotation
Figure 2 for ALMA: Alignment with Minimal Annotation
Figure 3 for ALMA: Alignment with Minimal Annotation
Figure 4 for ALMA: Alignment with Minimal Annotation
Viaarxiv icon

JPEG-LM: LLMs as Image Generators with Canonical Codec Representations

Add code
Aug 15, 2024
Viaarxiv icon

SSD-2: Scaling and Inference-time Fusion of Diffusion Language Models

Add code
May 24, 2023
Viaarxiv icon

Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation

Add code
Feb 15, 2023
Figure 1 for Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation
Figure 2 for Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation
Figure 3 for Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation
Figure 4 for Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation
Viaarxiv icon

Representation Deficiency in Masked Language Modeling

Add code
Feb 04, 2023
Figure 1 for Representation Deficiency in Masked Language Modeling
Figure 2 for Representation Deficiency in Masked Language Modeling
Figure 3 for Representation Deficiency in Masked Language Modeling
Figure 4 for Representation Deficiency in Masked Language Modeling
Viaarxiv icon

XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models

Add code
Jan 25, 2023
Figure 1 for XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Figure 2 for XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Figure 3 for XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Figure 4 for XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Viaarxiv icon

In-context Examples Selection for Machine Translation

Add code
Dec 05, 2022
Viaarxiv icon