Read AI papers faster
with ChatPaper

Yi Wang, Haopeng Zhang, Chengxiang Huang, Rui Dai et al. · AMAP-ML

Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitioners design loops that monitor…

Hangrui Xu, Jiarui Wang, Yang Yang, Chuanbo Zhu et al. · ByteDance

Equipping Large Language Models (LLMs) with multi-turn tool-calling capabilities is essential for building autonomous agents. However, progress is fundamentally limited by the…

Senqiao Yang, Chengyao Wang, Yuxin Chen, Zixuan Wang et al. · Star Vision Language Action Models

Scaling robot data is crucial for building generalist Vision-Language-Action (VLA) models, yet robot trajectories are harder to scale than web-scale image-text data because…

Tianfu Wang, Zhezheng Hao, Xilin Xia, Lixin Liu et al. · Hong Kong University of Science and Technology(GuangZhou)

Generative models can turn natural-language prompts into images, text, code, and other content, lowering the cost of producing drafts and components. Their practical impact…

Hanyang Wang, Yimo Cai, Weiliang Chen, Jiawei Chi et al. · MirroS

Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can recognize and explain…

Gyouk Chu, Myeongho Jeon, Eunho Yang · KAIST AI

Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. While considerable…

Esakkivel Esakkiraja, Denis Akhiyarov, Vikas Yadav, Sai Rajeswar et al. · ServiceNow-AI

We present StarHarness, a framework for evolving environment-specific agent harnesses while keeping model weights fixed. The evolved harness can include prompt and task framing,…

Kairong Luo, Jiarui Cui, Yaorui Yin, Shengqi Chen et al. · PACMAN Group, Tsinghua University

Language model pretraining has become almost synonymous with prohibitive cost, placing it out of reach for much of the academic and open-source communities. Although strong…

Jiarong Han, Jincheng Xiong, Yuzhou Liu, Linzhe Shi et al. · Alibaba AMAP CV Lab

Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation. Early streaming models…

Sangoh Lee, Sangwoo Mo, Wook-Shin Han · Pohang University of Science and Technology

Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which…

Yixuan Ding, Jiahao Kong, Wei Huang, Ruijie Quan et al. · Zhejiang University

Autoregressive video diffusion enables scalable long-video generation by producing chunks from a bounded recent context. While recency-based caching preserves local continuity, it…

Yifan Zhang, Steve Ta, Jasper Zhang, Jichen Feng et al.

Recurrent fast-weight memories and selective state-space models compress an expanding context into a fixed-size recurrent state, making the state transition an online learning…