4 citations · 5 across the 22 of their papers we have counts for
23 papers
VisualClaw: A Real-Time, Personalized Agent for the Physical World
Haoqin Tu, Jianwen Chen, Zijun Wang +14
Vision language models are serving as general-purpose interfaces for complex multimodal tasks. However, deployment still faces three gaps: VLMs typically incur high latency and cos…
Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
Minhua Lin, Juncheng Wu, Zijun Wang +14
LLM agents are increasingly deployed as systems built around editable external harnesses, including prompts, skills, memories and tools, that shape task execution without changing…
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
Juncheng Wu, Letian Zhang, Yuhan Wang +9
Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has already been curated and hand…
InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition
Fengze Liu, Weidong Zhou, Binbin Liu +7
Upweighting high-quality data in LLM pretraining often improves performance, but in datalimited regimes, especially under overtraining, stronger upweighting increases repetition an…
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
Qijun Han, Haoqin Tu, Zijun Wang +11
Autonomous GUI agents face two fundamental challenges: early stopping, where agents prematurely declare success without verifiable evidence, and repetitive loops, where agents cycl…
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
Hardy Chen, Nancy Lau, Haoqin Tu +8
Frontier coding agents are increasingly used in workflows where users supervise progress primarily through repeated improvement of a public score, namely the reported score on a pu…
Target-Oriented Pretraining Data Selection via Neuron-Activated Graph
Zijun Wang, Haoqin Tu, Weidong Zhou +7
Everyday tasks come with a target, and pretraining models around this target is what turns them into experts. In this paper, we study target-oriented language model (LM) pretrainin…
Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
Zijun Wang, Haoqin Tu, Letian Zhang +11
OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services such as Gmail, Stripe, and the fil…
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
Chendong Xiang, Jiajun Liu, Jintao Zhang +7
Predictive world models that simulate future observations under explicit camera control are fundamental to interactive AI. Despite rapid advances, current systems lack spatial pers…
Efficient Mixture-of-Agents Serving via Tree-Structured Routing, Adaptive Pruning, and Dependency-Aware Prefill-Decode Overlap
Zijun Wang, Yijiahao Qi, Hanqiu Chen +5
Mixture-of-Agents (MoA) inference can suffer from dense inter-agent communication and low hardware utilization, which jointly inflate serving latency. We present a serving design t…
OnePiece: The Great Route to Generative Recommendation -- A Case Study from Tencent Algorithm Competition
Jiangxia Cao, Shuo Yang, Zijun Wang +1
In past years, the OpenAI's Scaling-Laws shows the amazing intelligence with the next-token prediction paradigm in neural language modeling, which pointing out a free-lunch way to…
ProPhy: Progressive Physical Alignment for Dynamic World Simulation
Zijun Wang, Panwen Hu, Jing Wang +7
Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent resul…
When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought
Yiyang Zhou, Haoqin Tu, Zijun Wang +11
We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT…
Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
Zhaofang Qian, Hardy Chen, Zeyu Wang +9
Vision-language models (VLMs) have advanced rapidly, yet their capacity for image-grounded geolocation in open-world conditions, a task that is challenging and of demand in real li…
When Images Speak Louder: Mitigating Language Bias-induced Hallucinations in VLMs through Cross-Modal Guidance
Jinjin Cao, Zhiyang Chen, Zijun Wang +3
Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hal…
C-Evolve: Consensus-based Evolution for Prompt Groups
Tiancheng Li, Yuhang Wang, Zhiyang Chen +3
Prompt evolution algorithms offer a powerful paradigm for enhancing AI systems based on closed-source models, while few work explores whether aggregating results from multiple prom…
AHELM: A Holistic Evaluation of Audio-Language Models
Tony Lee, Haoqin Tu, Chi Heem Wong +6
Evaluations of audio-language models (ALMs) -- multimodal models that take interleaved audio and text as input and output text -- are hindered by the lack of standardized benchmark…
Mimicking the Physicist's Eye:A VLM-centric Approach for Physics Formula Discovery
Jiaqi Liu, Songning Lai, Pengze Li +12
Automated discovery of physical laws from observational data in the real world is a grand challenge in AI. Current methods, relying on symbolic regression or LLMs, are limited to u…
Robust and Efficient AI-Based Attack Recovery in Autonomous Drones
Diego Ortiz Barbosa, Luis Burbano, Siwei Yang +4
We introduce an autonomous attack recovery architecture to add common sense reasoning to plan a recovery action after an attack is detected. We outline use-cases of our architectur…
Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models
Zemin Huang, Zhiyang Chen, Zijun Wang +2
We introduce the Diffusion Chain of Lateral Thought (DCoLT), a reasoning framework for diffusion language models. DCoLT treats each intermediate step in the reverse diffusion proce…
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
Zijun Wang, Haoqin Tu, Yuhan Wang +6
This paper introduces STAR-1, a high-quality, just-1k-scale safety dataset specifically designed for large reasoning models (LRMs) like DeepSeek-R1. Built on three core principles…
AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation
Zijun Wang, Haoqin Tu, Jieru Mei +3
This paper studies the vulnerabilities of transformer-based Large Language Models (LLMs) to jailbreaking attacks, focusing specifically on the optimization-based Greedy Coordinate…
How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs
Haoqin Tu, Chenhang Cui, Zijun Wang +6
This work focuses on the potential of Vision LLMs (VLLMs) in visual reasoning. Different from prior studies, we shift our focus from evaluating standard performance to introducing…