PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs
Paper
•
2410.05265
•
Published
•
30
essay
-
-
MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents
Paper • 2410.03450 • Published • 36 -
MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code
Paper • 2410.08196 • Published • 45 -
Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
Paper • 2410.07303 • Published • 18 -
Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
Paper • 2410.05210 • Published • 10 -
Attention Heads of Large Language Models: A Survey
Paper • 2409.03752 • Published • 89 -
CLEAR: Character Unlearning in Textual and Visual Modalities
Paper • 2410.18057 • Published • 200