Institution profile

JD

Industry researchasia · cn
Official website
Research library245linked papers
Opportunities0open roles
Selected work

Representative Papers

GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion

Sep 21, 2024arXiv.org

To address the scalability bottleneck in multi-agent debate—specifically, the exponential growth in token consumption with increasing agent count and debate rounds—this paper proposes a *grouped multi-agent debate* architecture. Agents are partitioned into disjoint subgroups that conduct parallel internal debates; inter-group information exchange and a dynamic consensus mechanism then aggregate intermediate results efficiently. This approach breaks the traditional linear scaling constraint and represents the first systematic integration of grouping principles into multi-agent debate frameworks. Extensive experiments across multiple logical reasoning benchmarks demonstrate that our method reduces token consumption by up to 51.7% relative to baseline methods, while simultaneously improving accuracy by up to 25%. The architecture thus achieves a significant trade-off improvement between computational efficiency and reasoning performance.

37 citations2 influentialRead paper

Continuous Speculative Decoding for Autoregressive Image Generation

Nov 18, 2024arXiv.org

Continuous autoregressive visual generation models suffer from high inference latency, while existing speculative decoding methods are restricted to discrete token spaces and lack theoretical foundations or practical techniques for continuous-valued outputs. Method: This work pioneers the extension of speculative decoding to continuous visual generation. We propose a diffusion-prior-based continuous acceptance criterion, design a denoising trajectory alignment mechanism and token pre-filling strategy to mitigate distribution mismatch, and establish a continuous accept-reject sampling framework with analytically derived upper bounds on approximation error. Contribution/Results: Our approach achieves a 2.33× inference speedup on standard diffusion-based autoregressive models while provably preserving the exact output distribution of the original model. The implementation is publicly available.

8 citationsRead paper

One Size, Many Fits: Aligning Diverse Group-Wise Click Preferences in Large-Scale Advertising Image Generation

Feb 02, 2026

This work addresses the limitations of existing advertising image generation methods, which adopt a one-size-fits-all strategy and neglect inter-group differences in click preferences, leading to suboptimal performance for certain user segments. To overcome this, the authors propose OSMF, a unified framework that enables personalized ad content generation through product-aware adaptive grouping and preference-conditioned image synthesis. The key contributions include the first introduction of a group-level click preference alignment mechanism, the construction of GAIP—the first large-scale dataset capturing group-specific advertising image preferences—and the development of Group-DPO optimization integrated with a group-aware multimodal large language model (G-MLLM). Both offline evaluations and online experiments demonstrate that the proposed approach significantly improves click-through rates across diverse user groups, achieving state-of-the-art performance.

1 citationsRead paper

ADORE: Autonomous Domain-Oriented Relevance Engine for E-commerce

Jul 13, 2025Annual International ACM SIGIR Conference on Research and Development in Information Retrieval

E-commerce search relevance modeling faces two key challenges: semantic gap between queries and items, and scarcity of domain-specific hard negative samples. To address these, we propose a three-module collaborative framework: (1) a chain-of-thought large language model that automatically generates high-quality training data with intent alignment and behavioral consistency; (2) error-type-aware adversarial sample synthesis to enhance model robustness; and (3) knowledge distillation incorporating hierarchical item critical attributes for lightweight, efficient relevance modeling. Integrating Kahneman–Tversky optimization with neural ranking techniques, our approach establishes a cognitively aligned, resource-efficient, and end-to-end self-sustaining learning system. Extensive offline evaluations and online A/B tests demonstrate significant improvements in search relevance, reduced reliance on manual annotation, and breakthrough performance in industrial deployment—achieving high accuracy, low latency, and strong robustness in ranking.

1 citationsRead paper
Recent publications

Latest Papers