new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Feb 22

Submitted by

akhaliq

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

·
8 authors

Submitted by

akhaliq

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

·
3 authors

Submitted by

akhaliq

Aria Everyday Activities Dataset

·
24 authors

Submitted by

akhaliq

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

·
3 authors

Submitted by

akhaliq

Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis

·
11 authors

Submitted by

akhaliq

User-LLM: Efficient LLM Contextualization with User Embeddings

·
9 authors

Submitted by

akhaliq

In deep reinforcement learning, a pruned network is a good network

·
3 authors

Submitted by

akhaliq

Coercing LLMs to do and reveal (almost) anything

·
6 authors

Submitted by

akhaliq

Music Style Transfer with Time-Varying Inversion of Diffusion Models

·
6 authors

Submitted by

akhaliq

ToDo: Token Downsampling for Efficient Generation of High-Resolution Images

·
3 authors

Submitted by

akhaliq

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models

·
8 authors

Submitted by

akhaliq

D-Flow: Differentiating through Flows for Controlled Generation

·
6 authors

Submitted by

akhaliq

Ouroboros: Speculative Decoding with Large Model Enhanced Drafting

·
6 authors