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
3,087 papers
ScienceIDE: Turning World’s Scientific Codebase into Agent Learnable Environments
AI for Science
Agent
Hejia Geng, Zesen Huang, Haoyang Li, et al.
ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks
Agent
LLM
Jeonghye Kim, Minseon Kim, Young Jin Kim, et al.
Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening
Reinforcement Learning
Model Training
Yizhuo Li, Jianhao Yan, Yun Luo, et al.
Agora: Git as Shared Memory for Collective AutoResearch
Agent
LLM
Yifan Zhang, Yunheng Zou, Shaokun Zhang, et al.
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents
Retrieval-Augmented Generation
Agent
Caiqi Zhang, Xiaochen Zhu, Chengzu Li, et al.
LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
Deep Learning
Transformer
Xingxuan Zhang, Peng Cui, Gang Ren, et al.
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
AI for Science
Agent
Shuhan Xue, Jianyuan Zhong, Ziyuan Nan, et al.
AI for Games in the Foundation Model Era
World Models
Agent
Meng Luo, Yanlin Li, Hao Li, et al.
StepAudio 3 Music Technical Report
Text-to-Audio
Diffusion Model
Chengli Feng, Zhiyue Wu, Jiahao Song, et al.
StepAudio 3 Realtime Technical Report
Audio and Speech Processing
Multimodal
Bin Lin, Bo Zhao, Boyang Zhang, et al.
Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement
Agent
Reinforcement Learning
Hongyao Tang, Yi Ma, Pengyi Li, et al.
Continual Learning Mechanisms Compose for Long-Horizon Memorization
Supervised Fine-Tuning
LLM
Zheyuan Zhang, Alvin Zhang, Daniel Khashabi, et al.
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
LLM
DeepSeek
Anyi Xu, B. Li, Bangcai Lin, et al.
Atria Dawn: The Dawn of Agentic Superintelligence On the Evolving Roles of Human–AI Collaboration
Agent
AI for Science
Honglin Guo, Tao Gui, Yicheng Chen, et al.
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
World Models
Multimodal
Yu Bin, Haipeng Cao, Zheng Chang, et al.
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Reinforcement Learning
Agent
Tong Zheng, Xidong Wu, Zheng Zhang, et al.
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search
LLM
Model Training
Jiyan He, Guang Liang, Hao Liu, et al.
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Video Generation
Video Processing
Jintao Zhang, Kai Jiang, Jintao Chen, et al.
AI in Science: Early Insights
AI for Science
LLM
Mihai Codreanu, Evalyne Muiruri, Ana Trišović, et al.
Exact Feasibility Certification and Optimal Responsibility Allocation for Multi-Robot CBF Safety Filters
Robotics
Chandan Kumar Sah, Jishnu Keshavan
CROSS-BLOCK CONDITIONING IN DEEP BOLTZMANN MACHINES FOR STATISTICAL DATA FUSION
Deep Learning
Multi-Task Learning
Junichiro Niimi
The Complexity of Weak Partition Connectivity in Hedgegraphs
Image Segmentation
Mask Generation
Yuanhao Wang, Wei Wang
Accelerated Local Algorithms for Personalized and Regularized PageRank
vLLM
Supervised Fine-Tuning
Baojian Zhou
Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions
Deep Learning
Transformer
Dimitris Ntounis, Ariel Schwartzman, Chris Chafe, et al.
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Agent
LLM
Sibo Zhu, Shicheng Fan, Xinyue Wang, et al.
Breaking the Token Ceiling: Distilling Smaller, Stronger Byte Models
Transformer
Model Training
Kalyani Marathe, Artidoro Pagnoni, Tomasz Limisiewicz, et al.
COBRA-SKILLS: CONTEXTUAL BANDIT-GUIDED EVOLUTION FOR AGENT SKILL OPTIMIZATION
Agent
Reinforcement Learning
Pingchen Lu, Xiangyi Wang, Xiang Li, et al.
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
Transformer
Model Training
Zhiwei Li, Lei Zhu, Hao Gu, et al.
Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation
Benchmarks
LLM
Koutian Wu, Junjie Zhou, Ergan Shang, et al.
DataFlex-RL: An Evaluation Platform for RLVR Data Policies
Reinforcement Learning
Model Training
Hao Liang, Mingrui Chen, Hengyi Feng, et al.
Breaking the Vision–Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models
World Models
Multimodal
Jianman Lin, Shailesh Shailesh, Zhongyi Luo, et al.
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Supervised Fine-Tuning
Agent
Zongjie Li, Alan Z. W John, Nicolas J, et al.