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

Jan 15

Submitted by

Ryan1122

MiniMax-01: Scaling Foundation Models with Lightning Attention

·
90 authors

Submitted by

Johanan0528

MangaNinja: Line Art Colorization with Precise Reference Following

·
10 authors

Submitted by

sanaka87

3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering

·
4 authors

Submitted by

akhaliq

Diffusion Adversarial Post-Training for One-Step Video Generation

·
6 authors

Submitted by

cmhungsteve

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

·
8 authors

Submitted by

tokeron

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

·
7 authors

Submitted by

Ningyu

A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following

·
8 authors

Submitted by

Yabo

FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors

·
6 authors

Submitted by

s-emanuilov

HALoGEN: Fantastic LLM Hallucinations and Where to Find Them

·
4 authors

Submitted by

turkeyju

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

·
7 authors

Submitted by

akhaliq

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

·
5 authors

Submitted by

akshat57

PokerBench: Training Large Language Models to become Professional Poker Players

·
6 authors

Submitted by

gsarti

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

·
5 authors

Submitted by

yuyijiong

OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training

·
6 authors

Submitted by

stefan-it

AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages

·
27 authors

Submitted by

amanchadha

Potential and Perils of Large Language Models as Judges of Unstructured Textual Data

·
10 authors

Submitted by

nielsr

MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training

·
7 authors

Submitted by

mjbuehler

In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR

·
1 authors