HyperAI
Command Palette
Search for a command to run...
Papers
Daily updated cutting-edge AI research papers to help you keep up with the latest AI trends
3,011 papers
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Agent
LLM
Yuhao Wu, Jingyuan Zhang, Jiajun Shi, et al.
Language Models Can Control Their Own Attention
LLM
Text Generation
Namgyu Ho, Huzama Ahmad, Woosung Koh, et al.
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
LLM
Supervised Fine-Tuning
Runpeng Dai, Kaili Huang, Changsung Kang, et al.
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
LLM
Agent
Yuling Shi, Zhensu Sun, Junsen Dong, et al.
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
World Models
Video Generation
Junchao Huang, Guian Fang, Shengju Qian, et al.
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Agent
LLM
Jianlyu Chen, Yuyang Hu, Hongjin Qian, et al.
H3-World: Turning Language Understanding into World Control
World Models
Video Generation
Danze Chen, Zeqing Wang, Ziyue Lin, et al.
ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training
World Models
Xionghao Wu, Yijun Yang, Shiyang Zhou, et al.
UI-Venus-2: A Large Language Model for GUI Agents
LLM
Agent
SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
Transformer
LLM
Shaowen Wang, Ge Zhang, Kairong Luo, et al.
Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving
Autonomous Driving
Qwen
Xin Zhou, Zongchuang Zhao, Zhibo Yang, et al.
StudentSim: Training LLM-based Student Simulators
LLM
Model Training
Ke Yang, Chenglong Wang, Michel Galley, et al.
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
Multimodal
Any-to-Any
Dahua Lin, Lei Yang, Lewei Lu, et al.
Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase
Code Generation
LLM
Daegyu Sung, Yukyeong Lee, Geon Park, et al.
CogEvol: Towards Efficient and Reliable Learning Environment Generation
Code Generation
Supervised Fine-Tuning
Shangqing Tu, Daniel Zhang-Li, Yucheng Wang, et al.
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Multimodal
Agent
Qianli Ma, Ran Mei, Jia Wei, et al.
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
Image Generation
Text-to-Image
Guangting Zheng, Yiyuan Zhang, Tao Yang, et al.
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
3D Generation
3D Machine Vision
Minghan Qin, Yuang Wang, Xiuyu Yang, et al.
DreamX-Creator 1.0: Democratizing Native Audio-Video Generation at 2K Resolution
Video Generation
Diffusion Model
Jiashu Zhu, Yanhao Zheng, Ruitian Tian, et al.
SLIDING-WINDOW BEATS LINEAR ATTENTION
Transformer
Deep Learning
Alexia Jolicoeur-Martineau, Pashmina Cameron, Rhea Sanjay Sukthanker, et al.
Fast Weight Attention for Continual Learning
Deep Learning
Model Training
Yifan Zhang, Steve Ta, Jasper Zhang, et al.
SKILL.state: Scalable Long-Horizon Agent Skills
LLM
Agent
Sanket Badhe, Priyanka Tiwari, Jonghyun Chung
Hydra-0: Action Flow for Generalist World Modeling and Control
World Models
Video Generation
Hongyu Li, Bowen Wen, Xinghao Zhu, et al.
J-ZERO: UNIFIED CHALLENGER–SOLVER–JUDGE CO-EVOLUTION FROM ZERO DATA
LLM
Model Training
Gyouk Chu, Myeongho Jeon, Eunho Yang
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
World Models
Agent
Hanyang Wang, Yimo Cai, Weiliang Chen, et al.
Agentic Artifact Creation: Systems, Evaluation, Principles, and Opportunities
Agent
Tianfu Wang, Zhezheng Hao, Xilin Xia, et al.
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Multimodal
Multimodal Representation
Senqiao Yang, Chengyao Wang, Pengguang Chen, et al.
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents
Agent
LLM
Hangrui Xu, Jiarui Wang, Yang Yang, et al.
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
Benchmarks
Code Generation
Yi Wang, Haopeng Zhang, Chengxiang Huang, et al.
On the Design of Qwen3.8-Next Architecture: Evaluation, Eficiency, and Training Stability
Qwen
Transformer
Zihan Qiu, Zekun Wang, Xiao Li, et al.
What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents
Agent
LLM
Xingshan Zeng, Zishan Xu, Boju Zhang, et al.
Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher
Diffusion Model
Reinforcement Learning
Shiyi Zhang, Mushui Liu, Yunze Tong, et al.