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

Jul 29

Submitted by

dongguanting

Agentic Reinforced Policy Optimization

·
14 authors

Submitted by

jiahaoq

A Survey of Self-Evolving Agents: On Path to Artificial Super Intelligence

·
27 authors

Submitted by

tttoaster

ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts

·
18 authors

Submitted by

yixinsong

SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment

·
14 authors

2

Submitted by

ZedongWangAI

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning

·
3 authors

Submitted by

yukangcao

Reconstructing 4D Spatial Intelligence: A Survey

·
11 authors

Submitted by

jeepliu

Geometric-Mean Policy Optimization

·
12 authors

Submitted by

Zhiyuan-Fan

Diversity-Enhanced Reasoning for Subjective Questions

·
4 authors

2

Submitted by

xiangan

Region-based Cluster Discrimination for Visual Representation Learning

·
12 authors

Submitted by

cihangxie

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

·
7 authors

Submitted by

forestliutc

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities

·
5 authors

2

Submitted by

Lupin1998

Met^2Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems

·
4 authors

Submitted by

Kaichengalex

ForCenNet: Foreground-Centric Network for Document Image Rectification

·
9 authors

Submitted by

xiac24

ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment

·
6 authors

Submitted by

soujanyaporia

JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment

·
8 authors

Submitted by

chrisdonahue

Music Arena: Live Evaluation for Text-to-Music

·
8 authors

2

Submitted by

Zhang199

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

·
4 authors

1

Submitted by

mehuldamani

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty

·
7 authors

1

Submitted by

shuhaibmehri

Goal Alignment in LLM-Based User Simulators for Conversational AI

·
6 authors

Submitted by

Prakamya

SAND-Math: Using LLMs to Generate Novel, Difficult and Useful Mathematics Questions and Answers

·
5 authors

2

Submitted by

Liu-Hy

GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis

·
3 authors

Submitted by

gabrielchua

Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security

·
1 authors

2