Picture for Simeng Sun

Simeng Sun

SWAN-GPT: An Efficient and Scalable Approach for Long-Context Language Modeling

Add code
Apr 11, 2025
Viaarxiv icon

L0-Reasoning Bench: Evaluating Procedural Correctness in Language Models via Simple Program Execution

Add code
Mar 28, 2025
Viaarxiv icon

How much do contextualized representations encode long-range context?

Add code
Oct 16, 2024
Figure 1 for How much do contextualized representations encode long-range context?
Figure 2 for How much do contextualized representations encode long-range context?
Figure 3 for How much do contextualized representations encode long-range context?
Figure 4 for How much do contextualized representations encode long-range context?
Viaarxiv icon

nGPT: Normalized Transformer with Representation Learning on the Hypersphere

Add code
Oct 01, 2024
Viaarxiv icon

Suri: Multi-constraint Instruction Following for Long-form Text Generation

Add code
Jun 27, 2024
Viaarxiv icon

RULER: What's the Real Context Size of Your Long-Context Language Models?

Add code
Apr 11, 2024
Viaarxiv icon

TopicGPT: A Prompt-based Topic Modeling Framework

Add code
Nov 02, 2023
Figure 1 for TopicGPT: A Prompt-based Topic Modeling Framework
Figure 2 for TopicGPT: A Prompt-based Topic Modeling Framework
Figure 3 for TopicGPT: A Prompt-based Topic Modeling Framework
Figure 4 for TopicGPT: A Prompt-based Topic Modeling Framework
Viaarxiv icon

Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF

Add code
Sep 16, 2023
Figure 1 for Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
Figure 2 for Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
Figure 3 for Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
Figure 4 for Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
Viaarxiv icon

PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents

Add code
May 23, 2023
Figure 1 for PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
Figure 2 for PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
Figure 3 for PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
Figure 4 for PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents
Viaarxiv icon

How Does In-Context Learning Help Prompt Tuning?

Add code
Feb 22, 2023
Figure 1 for How Does In-Context Learning Help Prompt Tuning?
Figure 2 for How Does In-Context Learning Help Prompt Tuning?
Figure 3 for How Does In-Context Learning Help Prompt Tuning?
Figure 4 for How Does In-Context Learning Help Prompt Tuning?
Viaarxiv icon