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

Jul 25

Submitted by

akhaliq

OpenDevin: An Open Platform for AI Software Developers as Generalist Agents

·
24 authors

Submitted by

Seerkfang

$VILA^2$: VILA Augmented VILA

·
9 authors

Submitted by

akhaliq

HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation

·
11 authors

Submitted by

xxzcc

DDK: Distilling Domain Knowledge for Efficient Large Language Models

·
16 authors

Submitted by

akhaliq

PERSONA: A Reproducible Testbed for Pluralistic Alignment

·
5 authors

Submitted by

klight

Longhorn: State Space Models are Amortized Online Learners

·
6 authors

Submitted by

akhaliq

SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency

·
5 authors

Submitted by

gemcollector

Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning

·
6 authors

Submitted by

akhaliq

Scalify: scale propagation for efficient low-precision LLM training

·
4 authors

Submitted by

akhaliq

DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection

·
4 authors

Submitted by

ffelten

MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning

·
13 authors

Submitted by

akhaliq

ViPer: Visual Personalization of Generative Models via Individual Preference Learning

·
5 authors

Submitted by

xiaobiaodu

DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction

·
5 authors