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 11

Submitted by

iseesaw

A Survey of Reinforcement Learning for Large Reasoning Models

·
39 authors

Submitted by

taesiri

RewardDance: Reward Scaling in Visual Generation

·
12 authors

Submitted by

taesiri

3D and 4D World Modeling: A Survey

·
23 authors

Submitted by

taesiri

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning

·
23 authors

Submitted by

TongZheng1999

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models

·
11 authors

Submitted by

murcherful

P3-SAM: Native 3D Part Segmentation

·
10 authors

2

Submitted by

Nickyang

Hunyuan-MT Technical Report

·
7 authors

Submitted by

spermwhale

The Majority is not always right: RL training for solution aggregation

·
6 authors

Submitted by

memyprokotow

<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs

·
3 authors

Submitted by

ed13

Statistical Methods in Generative AI

·
1 authors

Submitted by

taesiri

EnvX: Agentize Everything with Agentic AI

·
7 authors

Submitted by

taesiri

HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants

·
4 authors