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 25

Submitted by

LiuXR

Thus Spake Long-Context Large Language Model

·
13 authors

Submitted by

akhaliq

VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing

·
4 authors

Submitted by

gallilmaimon

Slamming: Training a Speech Language Model on One GPU in a Day

·
3 authors

Submitted by

Canyu

DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks

·
8 authors

Submitted by

a43992899

Audio-FLAN: A Preliminary Release

·
22 authors

Submitted by

yulunliu

GCC: Generative Color Constancy via Diffusing a Color Checker

·
7 authors

Submitted by

CheeryLJH

CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models

·
18 authors

Submitted by

Facico

Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

·
7 authors

Submitted by

amphora

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning

·
4 authors

Submitted by

akhaliq

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers

·
6 authors

Submitted by

xw-eric

Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models

·
8 authors

Submitted by

TianjinHuang

Stable-SPAM: How to Train in 4-Bit More Stably than 16-Bit Adam

·
11 authors

Submitted by

xhyandwyy

Mobile-Agent-V: Learning Mobile Device Operation Through Video-Guided Multi-Agent Collaboration

·
7 authors

Submitted by

ProKil

Grounded Persuasive Language Generation for Automated Marketing

·
7 authors

Submitted by

jianlanluo

Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation

·
6 authors

Submitted by

clem

Forecasting Open-Weight AI Model Growth on Hugging Face

·
3 authors

Submitted by

akhaliq

X-Dancer: Expressive Music to Human Dance Video Generation

·
9 authors

Submitted by

irenesolaiman

Beyond Release: Access Considerations for Generative AI Systems

·
7 authors

Submitted by

callanwu

Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties

·
5 authors

Submitted by

wenyueH

InductionBench: LLMs Fail in the Simplest Complexity Class

·
6 authors

Submitted by

dalime

Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models

·
6 authors

Submitted by

GPaolo

TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning

·
5 authors

Submitted by

Nadav

Can Community Notes Replace Professional Fact-Checkers?

·
4 authors

Submitted by

peterji

Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation

·
10 authors

Submitted by

zouharvi

Early-Exit and Instant Confidence Translation Quality Estimation

·
5 authors

Submitted by

angus924

MONSTER: Monash Scalable Time Series Evaluation Repository

·
9 authors

Submitted by

codezakh

MutaGReP: Execution-Free Repository-Grounded Plan Search for Code-Use

·
6 authors

Submitted by

WillHeld

Mind the Gap! Static and Interactive Evaluations of Large Audio Models

·
7 authors

Submitted by

yzhuang

Self-Taught Agentic Long Context Understanding

·
10 authors

Submitted by

ludolara

Diagnosing COVID-19 Severity from Chest X-Ray Images Using ViT and CNN Architectures

·
4 authors

Submitted by

nielsr

M3-AGIQA: Multimodal, Multi-Round, Multi-Aspect AI-Generated Image Quality Assessment

·
6 authors

Submitted by

gberton

MegaLoc: One Retrieval to Place Them All

·
2 authors

Submitted by

ZarkLngeW

The snake in the Brownian sphere

·
4 authors