10 papers
Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
Han Zhang, Zihao Tang, Xin Yu +8
In existing memory benchmarks for Large Language Models (LLMs), the evaluated dialogue sessions often lack long-term semantic consistency, and the underlying personas tend to be fl…
An Efficient Streaming Video Understanding Framework with Agentic Control
Jinming Liu, Jianguo Huang, Zhaoyang Jia +7
Streaming video requires handling dynamic information density under strict latency budgets. Yet, existing methods typically employ static strategies, such as fixed memory compressi…
From Patches to Trajectories: Privileged Process Supervision for Software-Engineering Agents
Murong Ma, Tianyu Chen, Yun Lin +7
Supervised fine-tuning (SFT) on long teacher trajectories is the dominant way to instill investigation and reasoning in open software-engineering (SWE) agents. Since every retained…
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Dong Chen, Fangyun Wei, Ziyu Wan +18
We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with more than 6B parameters acro…
Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory
Runxi Cheng, Yuchen Guan, Yongxian Wei +7
Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables from scratch during pre-trainin…
RoboForge: Physically Optimized Text-guided Whole-Body Locomotion for Humanoids
Xichen Yuan, Zhe Li, Bofan Lyu +4
While generative models have become effective at producing human-like motions from text, transferring these motions to humanoid robots for physical execution remains challenging. E…
From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation
Zezhou Wang, Ziyun Zhang, Xiaoyi Zhang +2
Vision-language models are increasingly deployed as computer-use agents (CUAs) that operate desktops and browsers. Top-performing CUAs are framework-based systems that decompose pl…
InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training
Ziyun Zhang, Zezhou Wang, Xiaoyi Zhang +4
GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the…
UI-Evol: Automatic Knowledge Evolving for Computer Use Agents
Ziyun Zhang, Xinyi Liu, Xiaoyi Zhang +3
External knowledge has played a crucial role in the recent development of computer use agents. We identify a critical knowledge-execution gap: retrieved knowledge often fails to tr…
UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis
Xinyi Liu, Xiaoyi Zhang, Ziyun Zhang +1
Recent advancements in Large Vision-Language Models are accelerating the development of Graphical User Interface (GUI) agents that utilize human-like vision perception capabilities…