Picture for Pang Wei Koh

Pang Wei Koh

MoSH: Modeling Multi-Objective Tradeoffs with Soft and Hard Bounds

Add code
Dec 09, 2024
Viaarxiv icon

Establishing Task Scaling Laws via Compute-Efficient Model Ladders

Add code
Dec 05, 2024
Viaarxiv icon

Negative Token Merging: Image-based Adversarial Feature Guidance

Add code
Dec 02, 2024
Viaarxiv icon

OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs

Add code
Nov 21, 2024
Viaarxiv icon

On Erroneous Agreements of CLIP Image Embeddings

Add code
Nov 07, 2024
Viaarxiv icon

Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging

Add code
Oct 16, 2024
Figure 1 for Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
Figure 2 for Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
Figure 3 for Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
Figure 4 for Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
Viaarxiv icon

OLMoE: Open Mixture-of-Experts Language Models

Add code
Sep 03, 2024
Figure 1 for OLMoE: Open Mixture-of-Experts Language Models
Figure 2 for OLMoE: Open Mixture-of-Experts Language Models
Figure 3 for OLMoE: Open Mixture-of-Experts Language Models
Figure 4 for OLMoE: Open Mixture-of-Experts Language Models
Viaarxiv icon

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

Add code
Aug 15, 2024
Viaarxiv icon

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation

Add code
Jul 09, 2024
Viaarxiv icon

PLeaS -- Merging Models with Permutations and Least Squares

Add code
Jul 02, 2024
Viaarxiv icon