Picture for Yoon Kim

Yoon Kim

Richard

The Surprising Effectiveness of Test-Time Training for Abstract Reasoning

Add code
Nov 11, 2024
Viaarxiv icon

The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities

Add code
Nov 07, 2024
Figure 1 for The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities
Figure 2 for The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities
Figure 3 for The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities
Figure 4 for The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities
Viaarxiv icon

Training-Free Activation Sparsity in Large Language Models

Add code
Aug 26, 2024
Viaarxiv icon

LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theory

Add code
Aug 05, 2024
Viaarxiv icon

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

Add code
Jul 15, 2024
Viaarxiv icon

Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps

Add code
Jul 09, 2024
Viaarxiv icon

MDCR: A Dataset for Multi-Document Conditional Reasoning

Add code
Jun 17, 2024
Viaarxiv icon

Parallelizing Linear Transformers with the Delta Rule over Sequence Length

Add code
Jun 10, 2024
Viaarxiv icon

Value Augmented Sampling for Language Model Alignment and Personalization

Add code
May 10, 2024
Viaarxiv icon

Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment

Add code
Apr 18, 2024
Viaarxiv icon