7 citations · 17 across the 31 of their papers we have counts for
36 papers
Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization
Bizhe Bai, Jiakang Yuan, Hongming Wu +8
GUI agents increasingly operate across websites, mobile apps, and desktop environments, yet the field still reports progress primarily through task success. We argue that practical…
AeroGround: A Comprehensive Benchmark for Aerial-Ground Collaborative Reasoning
Shenghong Yi, Lin Zhang, Muzian Li +6
Vision-language models (VLMs) have been widely employed in understanding and reasoning tasks for unmanned aerial vehicles (UAVs). Existing UAV benchmarks primarily focus on aerial-…
Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System
Haoyu Zhang, Shuoxun Zhang, Peng Ye +5
Multimodal Large Language Model (MLLM)-based UAV aerial image understanding and reasoning is essential for aerial intelligence yet poses distinct challenges arising from extreme sc…
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Lei Bai, Zongsheng Cao, Yang Chen +50
We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling…
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
Siyao Chen, Jiakang Yuan, Jiaxin Wang +1
Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning. However, existing RL methods typically requi…
From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator
Xiaohua Wang, Jiakang Yuan, Zisu Huang +5
A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline log…
Segment-Aligned Policy Optimization for Multi-Modal Reasoning
Lei Gao, Zhuoming Li, Mengxi Jia +4
Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or entire response sequences. How…
MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancement
Haoyu Zhang, Jingyi Zhou, Peng Ye +4
With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot ability. However, due to th…
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models…
Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale
Yicheng Zou, Dongsheng Zhu, Lin Zhu +174
We introduce Intern-S1-Pro, the first one-trillion-parameter scientific multimodal foundation model. Scaling to this unprecedented size, the model delivers a comprehensive enhancem…
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
Shiyang Feng, Runmin Ma, Xiangchao Yan +53
We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architec…
SciEvalKit: An Open-source Evaluation Toolkit for Scientific General Intelligence
Yiheng Wang, Yixin Chen, Shuo Li +33
We introduce SciEvalKit, a unified benchmarking toolkit designed to evaluate AI models for science across a broad range of scientific disciplines and task capabilities. Unlike gene…
LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding
Yichen Jiang, Jiakang Yuan, Chongjun Tu +2
Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context w…
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
Muzhao Tian, Zisu Huang, Xiaohua Wang +8
As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most…
OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment
Yiting Lu, Fengbin Guan, Yixin Gao +8
Current visual evaluation approaches are typically constrained to a single task. To address this, we propose OmniQuality-R, a unified reward modeling framework that transforms mult…
AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
Shangheng Du, Xiangchao Yan, Dengyang Jiang +6
Large language models (LLMs) have shown impressive performance in general programming tasks. However, in Machine Learning Engineering (MLE) scenarios such as AutoML and Kaggle comp…
FlowSearch: Advancing deep research with dynamic structured knowledge flow
Yusong Hu, Runmin Ma, Yue Fan +11
Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-s…
Sequential Token Merging: Revisiting Hidden States
Yan Wen, Peng Ye, Lin Zhang +4
Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution. While exis…
OmniCaptioner: One Captioner to Rule Them All
Yiting Lu, Jiakang Yuan, Zhen Li +17
We propose OmniCaptioner, a versatile visual captioning framework for generating fine-grained textual descriptions across a wide variety of visual domains. Unlike prior methods lim…
MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs
Jiakang Yuan, Tianshuo Peng, Yilei Jiang +8
Logical reasoning is a fundamental aspect of human intelligence and an essential capability for multimodal large language models (MLLMs). Despite the significant advancement in mul…
InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification
InternAgent Team, Bo Zhang, Shiyang Feng +23
Artificial Intelligence (AI) is accelerating the transformation of scientific research paradigms, not only enhancing research efficiency but also driving innovation. We introduce I…
Consistency-aware Self-Training for Iterative-based Stereo Matching
Jingyi Zhou, Peng Ye, Haoyu Zhang +6
Iterative-based methods have become mainstream in stereo matching due to their high performance. However, these methods heavily rely on labeled data and face challenges with unlabe…
Lumina-Image 2.0: A Unified and Efficient Image Generative Framework
Qi Qin, Le Zhuo, Yi Xin +20
We introduce Lumina-Image 2.0, an advanced text-to-image generation framework that achieves significant progress compared to previous work, Lumina-Next. Lumina-Image 2.0 is built u…
SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing
Xiangchao Yan, Shiyang Feng, Jiakang Yuan +4
Survey paper plays a crucial role in scientific research, especially given the rapid growth of research publications. Recently, researchers have begun using LLMs to automate survey…