new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

May 29

Submitted by

akhaliq

Break-A-Scene: Extracting Multiple Concepts from a Single Image

·
5 authors

Submitted by

akhaliq

Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer

·
4 authors

Submitted by

akhaliq

Large Language Models as Tool Makers

·
5 authors

Submitted by

akhaliq

ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing

·
5 authors

Submitted by

akhaliq

Mindstorms in Natural Language-Based Societies of Mind

·
26 authors

Submitted by

akhaliq

Training Socially Aligned Language Models in Simulated Human Society

·
8 authors

Submitted by

akhaliq

DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

·
10 authors

Submitted by

akhaliq

Role-Play with Large Language Models

·
3 authors

Submitted by

akhaliq

PandaGPT: One Model To Instruction-Follow Them All

·
6 authors

Submitted by

akhaliq

Think Before You Act: Decision Transformers with Internal Working Memory

·
6 authors

Submitted by

akhaliq

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

·
10 authors

Submitted by

akhaliq

Playing repeated games with Large Language Models

·
6 authors

Submitted by

akhaliq

Randomized Positional Encodings Boost Length Generalization of Transformers

·
8 authors

Submitted by

akhaliq

MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies

·
7 authors

Submitted by

akhaliq

Do GPTs Produce Less Literal Translations?

·
4 authors

Submitted by

akhaliq

Backpack Language Models

·
4 authors

1

Submitted by

akhaliq

A Closer Look at In-Context Learning under Distribution Shifts

·
2 authors

Submitted by

akhaliq

Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing

·
8 authors

Submitted by

akhaliq

ZeroAvatar: Zero-shot 3D Avatar Generation from a Single Image

·
3 authors

Submitted by

akhaliq

Lexinvariant Language Models

·
6 authors

Submitted by

akhaliq

OlaGPT: Empowering LLMs With Human-like Problem-Solving Abilities

·
10 authors