Papers5

#KL Regularization

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

Xiaoxuan Wang, Han Zhang et al.Feb 25arXiv

This paper tackles why training AI agents that act over many steps (like browsing the web or moving in a house) often becomes unstable and collapses.

#Agentic Reinforcement Learning#Policy Gradient#Sequence-level Clipping

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

Beginner

Yiju Guo, Tianyi Hu et al.Jan 29arXiv

This paper shows that many reasoning failures in AI are caused by just a few distracting words in the prompt, not because the problems are too hard.

#LENS#Interference Tokens#Reinforcement Learning with Verifiable Rewards

Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization

Intermediate

Mizanur Rahman, Mohammed Saidul Islam et al.Jan 8arXiv

This paper teaches a model to turn a question about a table into both a short answer and a clear, correct chart.

#Text-to-Visualization#Reinforcement Learning#GRPO

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Beginner

Shilong Zhang, He Zhang et al.Dec 19arXiv

This paper shows that great image understanding features alone are not enough for making great images; you also need strong pixel-level detail.

#Pixel–Semantic VAE#Semantic Regularization#Off-Manifold Generation

RecTok: Reconstruction Distillation along Rectified Flow

Intermediate

Qingyu Shi, Size Wu et al.Dec 15arXiv

RecTok is a new visual tokenizer that teaches the whole training path of a diffusion model (the forward flow) to be smart about image meaning, not just the starting latent features.

#Rectified Flow#Flow Matching#Visual Tokenizer