Papers25

All Beginner Intermediate Advanced

All Sources arXiv

#curriculum learning

MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning

Intermediate

Jiejun Tan, Zhicheng Dou et al.Mar 3arXiv

MemSifter is a smart helper that picks the right memories for a big AI so the big AI doesn’t have to read everything.

#long-term memory#LLM retrieval#proxy model

ArXiv-to-Model: A Practical Study of Scientific LM Training

Intermediate

Anuj GuptaFeb 19arXiv

This paper shows, step by step, how to train a 1.36-billion-parameter science-focused language model directly from raw arXiv LaTeX files using only 2 A100 GPUs.

#scientific language model#arXiv LaTeX#tokenization

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

Intermediate

Chansung Park, Juyong Jiang et al.Feb 17arXiv

TAROT teaches code-writing AI the way good teachers teach kids: start at the right level and raise the bar at the right time.

#TAROT#curriculum learning#reinforcement fine-tuning

P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling

Intermediate

Pinyi Zhang, Ting-En Lin et al.Feb 12arXiv

This paper introduces P-GenRM, a personalized generative reward model that judges AI answers using a custom scorecard built just for each user and situation.

#personalized reward modeling#generative reward model#evaluation chain

Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens

Intermediate

Weihao Liu, Dehai Min et al.Feb 10arXiv

The paper introduces LT-Tuning, a way for AI models to “think silently” using special hidden tokens instead of writing every step out loud.

#latent tokens#chain-of-thought#context-prediction fusion

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

Intermediate

Zehao Chen, Gongxun Li et al.Feb 9arXiv

Big language models can get stuck after fine-tuning because they become too sure of themselves, so normal training stops helping.

#weak-driven learning#logit mixing#weak agents

Dreaming in Code for Curriculum Learning in Open-Ended Worlds

Intermediate

Konstantinos Mitsides, Maxence Faldor et al.Feb 9arXiv

Agents in vast, open-ended games often learn a little and then get stuck because the next good practice steps are missing.

#open-ended learning#unsupervised environment design#curriculum learning

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

Intermediate

Dongyang Chen, Chaoyang Wang et al.Feb 5arXiv

V-Retrver is a new way for AI to search across text and images by double-checking tiny visual details instead of only guessing from words.

#V-Retrver#multimodal retrieval#agentic reasoning

Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation

Intermediate

Zhiqi Yu, Zhangquan Chen et al.Feb 5arXiv

The paper finds a hidden symmetry inside GRPO’s advantage calculation that accidentally stops models from exploring new good answers and from paying the right attention to easy versus hard problems at the right times.

#GRPO#GRAE#A-GRAE

LIVE: Long-horizon Interactive Video World Modeling

Intermediate

Junchao Huang, Ziyang Ye et al.Feb 3arXiv

LIVE is a new way to train video-making AIs so their mistakes don’t snowball over long videos.

#cycle consistency#autoregressive video diffusion#exposure bias

Self-Hinting Language Models Enhance Reinforcement Learning

Intermediate

Baohao Liao, Hanze Dong et al.Feb 3arXiv

When rewards are rare, a popular training method for language models (GRPO) often stops learning because every try in a group gets the same score, so there is nothing to compare.

#reinforcement learning#GRPO#self-hinting

CoDiQ: Test-Time Scaling for Controllable Difficult Question Generation

Intermediate

Zhongyuan Peng, Caijun Xu et al.Feb 2arXiv

CoDiQ is a recipe for making hard-but-solvable math and coding questions on purpose, and it controls how hard they get while you generate them.

#controllable difficulty#test-time scaling#question generation

1 2 3