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
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
LLM
Agent
Akter et al., Xiao et al., Liu et al., et al.
Qwen-Image-Flash: Beyond Objective Design
Text-to-Image
Image Generation
Tianhe Wu, Kun Yan, Zikai Zhou, et al.
OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
Multimodal
Video Understanding
Yifei Li, Pengyiang Liu, Yuhang Zang, et al.
Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning
Reinforcement Learning
LLM
Xuekang Wang, Zhuoyuan Hao, Shuo Hou, et al.
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories
Agent
LLM
Jiaming Wang, Ziteng Feng, Jiangtao Wu, et al.
Audio Interaction Model
LLM
Audio and Speech Processing
Zhifei Xie, Zihang Liu, Ze An, et al.
Cosmos 3: Omnimodal World Models for Physical AI
Multimodal
Any-to-Any
Aditi, Niket Agarwal, Arslan Ali, et al.
Learning, Fast and Slow: Towards LLMs That Adapt Continually
Supervised Fine-Tuning
Model Training
Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal, et al.
LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
LLM
Text Generation
Po-Nien Kung, Linfeng Song, Dawsen Hwang, et al.
World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning
Multimodal
Visual Question Answering
Yucheng Zhou, Wei Tao, Yiwen Guo, et al.
From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain
Image Generation
Multimodal Representation
Yuval Golbari, Navve Wasserman, Matias Cosarinsky, et al.
A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
Reinforcement Learning
LLM
Lei Yang, Siyu Ding, Deyi Xiong
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
LLM
Object Tracking
Zekun Qi, Xuchuan Chen, Dairu Liu, et al.
Trust Region On-Policy Distillation
LLM
Text Generation
Xingrun Xing, Haoqing Wang, Boyan Gao, et al.
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering
Retrieval-Augmented Generation
Intelligent Question Answering
Maksim Savkin, Mikhail Goncharov, Alexander Gambashidze, et al.
MAI-Thinking-1: Building a Hill-Climbing Machine
Model Training
LLM
VLM3: Vision Language Models Are Native 3D Learners
3D Generation
Depth Estimation
Zhipeng Cai, Zhuang Liu, Yunyang Xiong, et al.
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Retrieval-Augmented Generation
Agent
Pengcheng Jiang, Zhiyi Shi, Kelly Hong, et al.
DeepCrack: A deep hierarchical feature learning architecture for crack segmentation
Semantic Segmentation
Image Segmentation
Yahui Liu, Lian Yao, Xiaohu Lu, et al.
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
Video Generation
Diffusion Model
Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral, et al.
Draft-OPD: On-Policy Distillation for Speculative Draft Models
Text Generation
LLM
Haodi Lei, Yafy Li, Haoran Zhang, et al.
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
Benchmarks
Agent
Nahyun Lee, Dongkeun Yoon, Guijin Son, et al.
A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
Benchmarks
Agent
Tomer Keren, Nitay Calderon, Asaf Yehudai, et al.
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
LLM
Model Training
Mind Lab, Song Cao, Vic Cao, et al.
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
Image Generation
AI for Science
Haozhe Zhao, Shuzheng Si, Zhenhailong Wang, et al.
TACK: A statistical evaluation of degradation activity on a novel TArgeting Chimeras Knowledge dataset
AI for Science
Deep Learning
Stefano Ribes, Nils Dunlop, Rocío Mercado
Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning
Video Generation
Multimodal
Zhengjian Yao, Yongzhi Li, Xinyuan Gao, et al.
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
LLM
Agent
Minhua Lin, Juncheng Wu, Zijun Wang, et al.
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Reinforcement Learning
LLM
Nianyi Lin, Jiajie Zhang, Lei Hou, et al.
Trust-Region Behavior Blending for On-Policy Distillation
Reinforcement Learning
LLM
Daniil Plyusov, Alexey Gorbatovski, Alexey Malakhov, et al.
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue
Text-to-Speech
Ruiqi Li, Yu Zhang, Changhao Pan, et al.
Representation Forcing for Bottleneck-Free Unified Multimodal Models
Any-to-Any
Image Generation
Yuqing Wang, Zhijie Lin, Ceyuan Yang, et al.