HyperAI

Daily updated cutting-edge AI research papers to help you keep up with the latest AI trends

papers

MOSAIC: Multi-Subject Personalized Generation via Correspondence-Aware Alignment and Disentanglement

Image Generation

Image-to-Image

Dong She, Siming Fu, Mushui Liu, et al.

last year

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation

Diffusion Model

Image Generation

Xuechao Zou, Shun Zhang, Xing Fu, et al.

last year

On the Theoretical Limitations of Embedding-Based Retrieval

Retrieval-Augmented Generation

Benchmarks

Orion Weller, Michael Boratko, Iftekhar Naim, et al.

last year

LMEnt: A Suite for Analyzing Knowledge in Language Models from
Pretraining Data to Representations

LLM

Dataset

Daniela Gottesman, Alon Gilae-Dotan, Ido Cohen, et al.

last year

LLM

Reasoning

Ziyi Xia, Kun Luo, Hongjin Qian, et al.

last year

Robix: A Unified Model for Robot Interaction, Reasoning and Planning

Robotics

Embodied Intelligence

Huang Fang, Mengxi Zhang, Heng Dong, et al.

last year

FusionProt: Fusing Sequence and Structural Information for Unified Protein Representation Learning

Multimodal Representation

Transformer

Dan Kalifa, Uriel Singer, Kira Radinsky

last year

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence

Multi-Task Learning

Any-to-Any

Xingxuan Zhang, Gang Ren, Han Yu, et al.

last year

epiGPTope: A machine learning-based epitope generator and classifier

AI for Science

Deep Learning

Natalia Flechas Manrique, Alberto Martínez, Elena López-Martínez, et al.

last year

GenCompositor: Generative Video Compositing with Diffusion Transformer

Video Generation

Video Processing

Shuzhou Yang, Xiaoyu Li, Xiaodong Cun, et al.

last year

DCPO: Dynamic Clipping Policy Optimization

Reinforcement Learning

Reasoning

Shihui Yang, Chengfeng Dou, Peidong Guo, et al.

last year

LLM

Reasoning

Mohammad Zbeeb, Hasan Abed Al Kader Hammoud, Bernard Ghanem

last year

Baichuan-M2: Scaling Medical Capability with Large Verifier System

LLM

Medicine

Baichuan-M2 Team, Chengfeng Dou, Chong Liu, et al.

last year

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

Benchmarks

Reasoning

Dongfu Jiang, Yi Lu, Zhuofeng Li, et al.

last year

ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding

Benchmarks

Multimodal

Hao Lu, Jiahao Wang, Yaolun Zhang, et al.

last year

AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data

AI for Science

Remote Sensing

Christopher F. Brown, Michal R. Kazmierski, Valerie J. Pasquarella, et al.

last year

AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions

LLM

Code Generation

Zihan Wang, Jiaze Chen, Zhicheng Liu, et al.

last year

TileLang: A Composable Tiled Programming Model for AI Systems

AI Compiler

TVM

Wang Lei, Cheng Yu, Shi Yining, et al.

last year

DeepSeek

LLM

Sara Vera Marjanović, Arkil Patel, Vaibhav Adlakha, et al.

last year

Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation

LLM

Retrieval-Augmented Generation

Mohsen Nayebi Kerdabadi, Arya Hadizadeh Moghaddam, Dongjie Wang, Zijun Yao

last year

LLM

Agent

Yeawon Lee, Xiaoyang Wang, Christopher C. Yang

last year

Document Understanding

Multimodal

Ahmed Nassar, Andres Marafioti, Matteo Omenetti, et al.

last year

olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

Document Understanding

Multimodal

Luca Soldaini, Kyle Lo, Christopher Wilhelm, et al.

last year

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench

Agent

LLM

Venkatesh Mishra, Amir Saeidi, Satyam Raj, et al.

last year

UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via
HUMAIN Chat

LLM

Natural Language Processing

Omer Nacar

last year

From reactive to cognitive: brain-inspired spatial intelligence for
embodied agents

Embodied Intelligence

Reasoning

Shouwei Ruan, Liyuan Wang, Caixin Kang, et al.

last year

No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes

Computer Vision

Object Detection

Blaž Rolih, Matic Fučka, Danijel Skočaj

last year

T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

Benchmarks

LLM

Jie Zhang, Changzai Pan, Kaiwen Wei, et al.

last year

PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning

Reinforcement Learning

Model Training

Wenfeng Feng, Penghong Zhao, Guochao Jiang, et al.

last year

Preference Modeling

Reinforcement Learning

Yuntao Bai, Andy Jones, Kamal Ndousse, et al.

last year

Natural Language Processing

Audio

Multimodality

3D Model

Computer Vision

Other

Command Palette

Papers