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
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Reinforcement Learning
LLM
Minseo Kim, Minjae Lee, Seunghyuk Oh, et al.
Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding
Multimodal
Jingyuan Huang, Zuming Huang, Yucheng Shi, et al.
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
Multimodal
3D Machine Vision
Yatai Ji, An-Chieh Cheng, Yang Fu, et al.
SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior
LLM
Deep Learning
Mingyue Cui, Linghui Shen, Xingyi Yang
Kairos: A Native World Model Stack for Physical AI
Agent
Multimodal
Kairos Team, Fei Wang, Shan You, et al.
Guava: An Effective and Universal Harness for Embodied Manipulation
Embodied Intelligence
Agent
Haowen Liu, Xirui Li, Shaoxiong Yao, et al.
Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games
Multimodal
LLM
Shengyuan Ding, Xilin Wei, Xinyu Fang, et al.
LifeSciBench: Evaluating Language Models on Realistic, Expert-Level Tasks in the Life Sciences
Benchmarks
LLM
Amelia Liu, Andrew Ho, Anne Marie Droste, et al.
TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs
LLM
Model Training
Hyeongwon Jang, Gyouk Chu, Changhun Kim, et al.
LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching
Agent
Embodied Intelligence
Jaward Sesay, Yue Yu, Siwei Dong, et al.
GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
Code Generation
Agent
Tongxu Luo, Rongsheng Wang, Jiaxi Bi, et al.
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Reinforcement Learning
LLM
Byung-Kwan Lee, Ximing Lu, Shizhe Diao, et al.
ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
Multimodal
Supervised Fine-Tuning
Hao Li, Ganlong Zhao, Yufei Liu, et al.
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Transformer
Code Generation
Jian Yang, Shawn Guo, Wei Zhang, et al.
Predicting LLM Safety Before Release by Simulating Deployment
LLM
Text Generation
Marcus Williams, Hannah Sheahan, Cameron Raymond, et al.
FastContext: Training Efficient Repository Explorer for Coding Agents
LLM
Code Generation
Shaoqiu Zhang, Maoquan Wang, Yuling Shi, et al.
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models
Reasoning
Supervised Fine-Tuning
Sen Xu, Shixi Liu, Wei Wang, et al.
DreamX-World 1.0: A General-Purpose Interactive World Model
Diffusion Model
Text-to-Video
DreamX Team, Yancheng Bai, Rui Chen, et al.
Geometric Action Model for Robot Policy Learning
Multimodal
Multimodal Representation
Jisang Han, Seonghu Jeon, Jaewoo Jung, et al.
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Multimodal
LLM
Kevin Qinghong Lin, Batu EI, Yuhong Shi, et al.
JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
Multimodal
Video Understanding
Dingyu Yao, Junhao Zhou, Chenxu Yang, et al.
dots.tts Technical Report
Text-to-Speech
Deterministic Video Depth Estimation with Generative Priors
Depth Estimation
Diffusion Model
Hongfei Zhang, Harold Haodong Chen, Chenfei Liao, et al.
Galaxy Image Deconvolution for Weak Gravitational Lensing with Unrolled Plug-and-Play ADMM
Deep Learning
AI for Science
Tianao Li, Emma Alexander
AI Must Embrace Specialization via Superhuman Adaptable Intelligence
Artificial Intelligence
Judah Goldfeder, Philippe Wyder, Yann LeCun, et al.
Sycophantic Chatbots Cause Delusional Spiraling, Even in Ideal Bayesians
LLM
Text Generation
Kartik Chandra, Max Kleiman-Weiner, Jonathan Ragan-Kelley, et al.
Agents of Chaos
Agent
LLM
Natalie Shapira, Chris Wendler, Avery Yen, et al.
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Agent
LLM
Darwin Agent Team
Orchestra-o1: Omnimodal Agent Orchestration
Multimodal
Agent
Fan Zhang, Vireo Zhang, Shengju Qian, et al.
From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI
LLM
Agent
Yongheng Zhang, Ziang Liu, Jiaxuan Zhu, et al.
Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
Agent
LLM
Shuo Ji, Yibo Li, Bryan Hooi
APPO: Agentic Procedural Policy Optimization
Reinforcement Learning
Agent
Xucong Wang, Ziyu Ma, Yong Wang, et al.