Papers7

#preference alignment

The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

This paper teaches AI to turn simple dialogue into full movie scenes by first writing a detailed script and then filming it step by step.

#dialogue-to-video#cinematic script generation#ScripterAgent

Solar Open Technical Report

Intermediate

Sungrae Park, Sanghoon Kim et al.Jan 11arXiv

Solar Open is a giant bilingual AI (102 billion parameters) that focuses on helping underserved languages like Korean catch up with English-level AI quality.

#Solar Open#Mixture-of-Experts#bilingual LLM

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

Beginner

Muzhao Tian, Zisu Huang et al.Jan 8arXiv

Long-term AI helpers remember past chats, but using all memories can trap them in old ideas (Memory Anchoring).

#steerable memory#memory anchoring#long-term agents

TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning

Intermediate

Yinuo Wang, Mining Tan et al.Jan 8arXiv

TourPlanner is a travel-planning system that first gathers the right places, then lets multiple expert ‘voices’ debate plans, and finally polishes the winner with a learning method that follows rules before style.

#travel planning#multi-agent reasoning#chain-of-thought

VIBE: Visual Instruction Based Editor

Intermediate

Grigorii Alekseenko, Aleksandr Gordeev et al.Jan 5arXiv

VIBE is a tiny but mighty image editor that listens to your words and changes pictures while keeping the original photo intact unless you ask otherwise.

#instruction-based image editing#vision-language model#diffusion model

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

Intermediate

Yuanhao Cai, Kunpeng Li et al.Dec 31arXiv

This paper teaches text-to-video models to follow real-world physics, so people, balls, water, glass, and fire act the way they should.

#text-to-video generation#physical consistency#direct preference optimization

TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models

Intermediate

Zheng Ding, Weirui YeDec 9arXiv

TreeGRPO teaches image generators using a smart branching tree so each training run produces many useful learning signals instead of just one.

#TreeGRPO#reinforcement learning#diffusion models