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 1

Submitted by

YannQi

R-4B: Incentivizing General-Purpose Auto-Thinking Capability in MLLMs via Bi-Mode Annealing and Reinforce Learning

·
6 authors

Submitted by

CoCoOne

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

·
103 authors

Submitted by

delinqu

EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

·
15 authors

Submitted by

lixiaochuan

Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation

·
14 authors

Submitted by

wanng

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

·
21 authors

Submitted by

Shunian

TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

·
13 authors

Submitted by

taesiri

Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models

·
8 authors

Submitted by

XiaohuanZhou

TiKMiX: Take Data Influence into Dynamic Mixture for Language Model Pre-training

·
9 authors

Submitted by

taesiri

UItron: Foundational GUI Agent with Advanced Perception and Planning

·
10 authors

Submitted by

taesiri

AHELM: A Holistic Evaluation of Audio-Language Models

·
9 authors

Submitted by

hanxiao

Efficient Code Embeddings from Code Generation Models

·
5 authors

Submitted by

LLucass

Model-Task Alignment Drives Distinct RL Outcomes

·
4 authors

Submitted by

taesiri

Morae: Proactively Pausing UI Agents for User Choices

·
4 authors

Submitted by

ashiq24

CLIPSym: Delving into Symmetry Detection with CLIP

·
3 authors

Submitted by

JiaaqiLiu

Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery

·
15 authors

Submitted by

gemcollector

HERMES: Human-to-Robot Embodied Learning from Multi-Source Motion Data for Mobile Dexterous Manipulation

·
7 authors

Submitted by

nennomp

Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks

·
3 authors

Submitted by

AllanK24

Quantization Robustness to Input Degradations for Object Detection

·
3 authors

2

Submitted by

yhua219

EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks

·
4 authors