Papers5

#GSM8K

Thinking with Comics: Enhancing Multimodal Reasoning through Structured Visual Storytelling

Andong Chen, Wenxin Zhu et al.Feb 2arXiv

This paper shows that comics (multi-panel pictures with words) can help AI think through problems step by step, just like a student explains their work.

#multimodal reasoning#visual storytelling#comics

Residual Context Diffusion Language Models

Intermediate

Yuezhou Hu, Harman Singh et al.Jan 30arXiv

Diffusion language models (dLLMs) generate several tokens at once but usually throw away lots of helpful clues each step—RCD keeps and reuses those clues.

#diffusion language models#residual context diffusion#soft tokens

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

Intermediate

Zhuochun Li, Yong Zhang et al.Jan 30arXiv

Big models are often used to grade AI answers, but they are expensive, slow, and depend too much on tricky prompts.

#Representation-as-a-Judge#Semantic Capacity Asymmetry#LLM-as-a-Judge

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection

Beginner

Tao Liu, Taiqiang Wu et al.Jan 14arXiv

Traditional supervised fine-tuning (SFT) makes a model copy one answer too exactly, which can cause overfitting to the exact wording instead of the real idea.

#ProFit#Supervised Fine-Tuning#Token Probability

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

Intermediate

Linhao Zhong, Linyu Wu et al.Jan 12arXiv

Diffusion Language Models (DLMs) write by polishing whole sentences in several passes instead of one token at a time.

#Diffusion Language Models#Masked Diffusion#Soft Token Distributions