الباحثون

Jian Xu

المنشورات 7

نسخة أولية وصول مفتوح

EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs

Leizhen Wang, Peibo Duan, Zhenlin Qin وآخرون · 2026

Effective traffic signal control (TSC) requires policies that respond to changing traffic demand and network conditions while meeting different control objectives. However, adapting existing strategies often involves repeated manual design and adjustment, making it difficult to systematically explore better control rul …

نسخة أولية وصول مفتوح

Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning

Jinghan Zhao, Yiman Hu, Liang Wu وآخرون · 2026

E-commerce videos are information-dense and frequently compared by consumers evaluating products and merchants assessing marketing strategies. However, existing multimodal models mainly focus on single-video understanding and have limited ability to compare information across videos. We introduce AdsCVR, the first e-co …

نسخة أولية وصول مفتوح

No Task Vector Is an Island: A Comprehensive Study on the Composability of Task Vectors from On-Policy Distillation

Jingang Zhou, Feiyu Han, Han Zhu وآخرون · 2026

Task vectors provide a simple mechanism for composing learned capabilities through model merging. However, the composability of task vectors produced by on-policy distillation (OPD) remains largely unexplored. OPD trains a student using teacher feedback on student-generated trajectories, yielding parameter updates that …

نسخة أولية وصول مفتوح

What Does a Stream Model Buy You in Flow Matching?

Jian Xu · 2026

Stream-level flow matching replaces the linear interpolant of conditional flow matching (CFM) by a Gaussian-process (GP) stream connecting each source--target pair, and reports lower sample error than \icfm{} on 2-Gaussian, MNIST and CIFAR-10 benchmarks. We ask what such a stream model actually contributes. Three resul …

نسخة أولية وصول مفتوح

Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents

Jian Xu · 2026

Agentic video-generation systems close a loop between a generator and a verifier: an LLM plans shots, calls a text-to-video model, and a multimodal judge decides whether the result satisfies the request. To diagnose where a long workflow fails, recent harnesses deliberately show the judge more than the video-the agent' …

نسخة أولية وصول مفتوح

RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents

Fanyu Zhao, Ruike Cao, Liang Dong وآخرون · 2026

Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at every query, making long-horizon performance increasingly dependent on retrieval quality and contextual reasoning as histories grow. Parametric memory encodes experience di …

نسخة أولية وصول مفتوح

Behavior2Value: Benchmarking and Empowering LLMs for Consumer Value Measurement from E-commerce Behaviors

Peixuan Hou, Bin Chen, Li He وآخرون · 2026

Human values are deep motivational orientations that shape human behaviors. In e-commerce, they reveal the stable drivers behind users' purchase decisions. Compared with short-term interests, consumer values better explain how users evaluate products before purchase. However, consumer values are often implicit in compl …

المؤلفون المشاركون