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

Jun 27

Submitted by

kimingng

MMSearch-R1: Incentivizing LMMs to Search

·
8 authors

Submitted by

apryc1

MADrive: Memory-Augmented Driving Scene Modeling

·
6 authors

1

Submitted by

JacobYuan

WorldVLA: Towards Autoregressive Action World Model

·
12 authors

Submitted by

BoyuNLP

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

·
26 authors

Submitted by

zhoutianyi

FaSTA^*: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing

·
4 authors

Submitted by

zhoutianyi

Where to find Grokking in LLM Pretraining? Monitor Memorization-to-Generalization without Test

·
3 authors

1

Submitted by

songw-zju

SAM4D: Segment Anything in Camera and LiDAR Streams

·
7 authors

Submitted by

parachas

Arch-Router: Aligning LLM Routing with Human Preferences

·
4 authors

Submitted by

Emma02

Whole-Body Conditioned Egocentric Video Prediction

·
6 authors

1

Submitted by

Angelakeke

An Agentic System for Rare Disease Diagnosis with Traceable Reasoning

·
12 authors

Submitted by

vinthony

FairyGen: Storied Cartoon Video from a Single Child-Drawn Character

·
2 authors

Submitted by

haoz19

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

·
5 authors

Submitted by

ArthurDouillard

DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster

·
9 authors

Submitted by

tim-lawson

Learning to Skip the Middle Layers of Transformers

·
2 authors

Submitted by

fundwotsai2001

MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners

·
7 authors

Submitted by

VictorYXL

HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges

·
5 authors

Submitted by

wuyhthu

DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning

·
5 authors