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

Sep 9

Submitted by

taesiri

Reverse-Engineered Reasoning for Open-Ended Generation

·
12 authors

Submitted by

Junteng

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents

·
15 authors

Submitted by

Lingaaaaaaa

Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

·
6 authors

Submitted by

che111

Does DINOv3 Set a New Medical Vision Standard?

·
19 authors

Submitted by

shuaishuaicdp

Reinforced Visual Perception with Tools

·
9 authors

Submitted by

wenjun-li

Reinforcement Learning Foundations for Deep Research Systems: A Survey

·
11 authors

Submitted by

glecorve

DivMerge: A divergence-based model merging method for multi-tasking

·
4 authors

Submitted by

taesiri

Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents

·
4 authors

Submitted by

YuyaoGe

Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning

·
9 authors

2

Submitted by

dorni

UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

·
10 authors

Submitted by

Osilly

Interleaving Reasoning for Better Text-to-Image Generation

·
18 authors

Submitted by

lioooox

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

·
9 authors

Submitted by

taesiri

Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers

·
5 authors

Submitted by

cxiong

SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents

·
7 authors

Submitted by

JamesXZ

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet

·
3 authors

Submitted by

UVSKKR

D-HUMOR: Dark Humor Understanding via Multimodal Open-ended Reasoning

·
6 authors

Submitted by

MElHuseyni

Guided Decoding and Its Critical Role in Retrieval-Augmented Generation

·
7 authors

2

Submitted by

stefan-it

Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavarian

·
8 authors

2

Submitted by

Youbang

R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World

·
5 authors

Submitted by

LuJingyi

Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping

·
2 authors

Submitted by

bearhaon

Mechanistic interpretability for steering vision-language-action models

·
4 authors

2

Submitted by

lgy0404

MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

·
11 authors

Submitted by

TahaKoleilat

Singular Value Few-shot Adaptation of Vision-Language Models

·
3 authors

Submitted by

sileod

Saturation-Driven Dataset Generation for LLM Mathematical Reasoning in the TPTP Ecosystem

·
2 authors

Submitted by

xchu123

DCReg: Decoupled Characterization for Efficient Degenerate LiDAR Registration

·
6 authors