Picture for Shuming Shi

Shuming Shi

TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild

Add code
Sep 19, 2023
Viaarxiv icon

A Benchmark for Text Expansion: Datasets, Metrics, and Baselines

Add code
Sep 17, 2023
Viaarxiv icon

TeGit: Generating High-Quality Instruction-Tuning Data with Text-Grounded Task Design

Add code
Sep 11, 2023
Viaarxiv icon

Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models

Add code
Sep 03, 2023
Figure 1 for Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Figure 2 for Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Figure 3 for Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Figure 4 for Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Viaarxiv icon

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

Add code
Aug 12, 2023
Figure 1 for GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Figure 2 for GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Figure 3 for GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Figure 4 for GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
Viaarxiv icon

Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling

Add code
Jul 22, 2023
Figure 1 for Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Figure 2 for Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Figure 3 for Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Figure 4 for Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Viaarxiv icon

On the Cultural Gap in Text-to-Image Generation

Add code
Jul 06, 2023
Figure 1 for On the Cultural Gap in Text-to-Image Generation
Figure 2 for On the Cultural Gap in Text-to-Image Generation
Figure 3 for On the Cultural Gap in Text-to-Image Generation
Figure 4 for On the Cultural Gap in Text-to-Image Generation
Viaarxiv icon

SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills

Add code
Jun 28, 2023
Viaarxiv icon

Explicit Syntactic Guidance for Neural Text Generation

Add code
Jun 25, 2023
Figure 1 for Explicit Syntactic Guidance for Neural Text Generation
Figure 2 for Explicit Syntactic Guidance for Neural Text Generation
Figure 3 for Explicit Syntactic Guidance for Neural Text Generation
Figure 4 for Explicit Syntactic Guidance for Neural Text Generation
Viaarxiv icon

Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration

Add code
Jun 15, 2023
Viaarxiv icon