Papers7

#data augmentation

Timer-S1: A Billion-Scale Time Series Foundation Model with Serial Scaling

Timer-S1 is a huge time-series model (8.3B parameters, only 0.75B used per step) that predicts the future by thinking step-by-step inside one forward pass.

#time series forecasting#foundation models#Mixture-of-Experts

Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation

Intermediate

Krzysztof Wróbel, Jan Maria Kowalski et al.Feb 8arXiv

Bielik Guard is a pair of small but strong Polish language safety models that check text for five kinds of risky content: hate/aggression, vulgar language, sexual content, crime, and self-harm.

#Polish NLP#content moderation#safety classifier

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

Intermediate

Yinyi Luo, Yiqiao Jin et al.Feb 3arXiv

AgentArk teaches one language model to think like a whole team of models that debate, so it can solve tough problems quickly without running a long, expensive debate at answer time.

#multi-agent distillation#process reward model#GRPO

RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation

Intermediate

Boyang Wang, Haoran Zhang et al.Jan 8arXiv

RoboVIP is a plug-and-play tool that turns ordinary robot videos into many new, realistic, multi-view training videos without changing the original robot actions.

#robotic manipulation#video diffusion#multi-view generation

Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing

Intermediate

Yuguang Yue, Irakli Salia et al.Jan 8arXiv

The paper teaches a game-playing AI to copy good human players (behavior cloning) and shows that simply scaling up the model and the data makes the AI reason more causally (it pays attention to what truly causes outcomes on screen).

#behavior cloning#causal reasoning#causal confusion

ProGuard: Towards Proactive Multimodal Safeguard

Intermediate

Shaohan Yu, Lijun Li et al.Dec 29arXiv

ProGuard is a safety guard for text and images that doesn’t just spot known problems—it can also recognize and name new, never-seen-before risks.

#proactive safety#multimodal moderation#out-of-distribution detection

Insight Miner: A Time Series Analysis Dataset for Cross-Domain Alignment with Natural Language

Intermediate

Yunkai Zhang, Yawen Zhang et al.Dec 12arXiv

Time-series data are numbers tracked over time, like temperature each hour or traffic each day, and turning them into clear words usually needs experts.

#time series#multimodal model#trend description