Author name cluster

Jiaming Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAMAS Conference 2026 Conference Paper

Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning

Yihong Wu
Liheng Ma
Muzhi Li
Jiaming Zhou
Lei Ding
Jianye Hao
Ho-fung Leung
Irwin King

Large Language Models (LLMs) equipped with modern Retrieval- Augmented Generation (RAG) systems often employ multi-turn interaction pipelines to interface with search engines for complex reasoning tasks. However, such multi-turn interactions inevitably produce long intermediate contexts, as context length grows exponentially with exploration depth. This leads to a well-known limitation of LLMs: their difficulty in effectively leveraging informationfromlongcontexts. ThisproblemisfurtheramplifiedinRAG systemsthatdependonin-contextlearning, wherefew-shotdemonstrations must also be included in the prompt, compounding the context-length bottleneck. To address these challenges, we propose Mujica-MyGo, a unified framework for efficient multi-turn reasoning in RAG. Inspired by the divide-and-conquer principle, we introduce Mujica (Multi-hop Joint Intelligence for Complex Question Answering), a multi-agent RAG workflow that decomposes multiturn interactions into cooperative sub-interactions, thereby mitigating long-context issues. To eliminate the dependency on in-context learning, we further develop MyGO (Minimalist Policy Gradient Optimization), a lightweight and efficient reinforcement learning algorithm that enables effective post-training of LLMs within complex RAG pipelines. We provide theoretical guarantees for MyGO’s convergence to the optimal policy. Empirical evaluations across diverse question-answering benchmarks—covering both text corpora and knowledge graphs—show that Mujica-MyGO achieves †qually contributed. This work is licensed under a Creative Commons Attribution International 4. 0 License. Proc. of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026), C. Amato, L. Dennis, V. Mascardi, J. Thangarajah (eds.), May 25 – 29, 2026, Paphos, Cyprus. © 2026 International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). https: //doi. org/10. 65109/QCQC1144 superior performance. Proofs, implementation details, and prompt templates are available in the extended version 1.

PDF

AAAI Conference 2026 Conference Paper

DIFFA: Large Language Diffusion Models Can Listen and Understand

Jiaming Zhou
Hongjie Chen
Shiwan Zhao
Jian Kang
Jie Li
Enzhi Wang
Yujie Guo
Haoqin Sun

Recent advances in large language models (LLMs) have shown remarkable capabilities across textual and multimodal domains. In parallel, large language diffusion models have emerged as a promising alternative to the autoregressive paradigm, offering improved controllability, bidirectional context modeling, and robust generation. However, their application to the audio modality remains underexplored. In this work, we introduce DIFFA, the first diffusion-based large audio-language model designed to perform spoken language understanding. DIFFA integrates a frozen diffusion language model with a lightweight dual-adapter architecture that bridges speech understanding and natural language reasoning. We employ a two-stage training pipeline: first, aligning semantic representations via an ASR objective; then, learning instruction-following abilities through synthetic audio-caption pairs automatically generated by prompting LLMs. Despite being trained on only 960 hours of ASR and 127 hours of synthetic instruction data, DIFFA demonstrates competitive performance on major benchmarks, including MMSU, MMAU, and VoiceBench, outperforming several autoregressive open-source baselines. Our results reveal the potential of large language diffusion models for efficient and scalable audio understanding, opening a new direction for speech-driven AI.

PDF Details DOI

TMLR Journal 2026 Journal Article

Extracting and Following Paths for Robust Relational Reasoning with Large Language Models

Ge Zhang
Mohammad Ali Alomrani
Hongjian Gu
Jiaming Zhou
Yaochen Hu
Bin Wang
Qun Liu
Mark Coates

Large language models (LLMs) possess vast semantic knowledge but often struggle with complex reasoning tasks, particularly in relational reasoning problems such as kinship or spatial reasoning. In this paper, we present Path-of-Thoughts (PoT), a novel framework for solving relation reasoning that decomposes the task into three key stages: graph extraction, path identification, and reasoning. Unlike previous approaches, PoT efficiently extracts a reasoning graph that identifies crucial entities, relations, and attributes within the context. Subsequently, PoT identifies query-relevant reasoning paths within the graph, facilitating downstream reasoning of potential answers. Experimental evaluations across four datasets of relational reasoning demonstrate that PoT surpasses state-of-the-art baselines by a significant margin (up to 21.3%) without requiring fine-tuning or extensive LLM calls. Furthermore, unlike prior neuro-symbolic methods, PoT exhibits improved resilience against LLM extraction errors and input ambiguity by leveraging the compositional nature of graphs.

PDF Details

AAAI Conference 2026 Conference Paper

TTA-Bench: A Comprehensive Benchmark for Evaluating Text-to-Audio Models

Hui Wang
Cheng Liu
Junyang Chen
Haoze Liu
Yuhang Jia
Shiwan Zhao
Jiaming Zhou
Haoqin Sun

Text-to-Audio (TTA) generation has made rapid progress, but current evaluation methods remain narrow, focusing mainly on perceptual quality while overlooking robustness, generalization, and ethical concerns. We present TTA-Bench, a comprehensive benchmark for evaluating TTA models across functional performance, reliability, and social responsibility. It covers seven dimensions including accuracy, robustness, fairness, and toxicity, and includes 2,999 diverse prompts generated through automated and manual methods. We introduce a unified evaluation protocol that combines objective metrics with over 118,000 human annotations from both experts and general users. Ten state-of-the-art models are benchmarked under this framework, offering detailed insights into their strengths and limitations. TTA-Bench establishes a new standard for holistic evaluation of TTA systems.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization

Jiaming Zhou
Ke Ye
Jiayi Liu
Teli Ma
Zifan Wang
Ronghe QIU
Kun-Yu Lin
Zhilin Zhao

The generalization capabilities of vision-language-action (VLA) models to unseen tasks are crucial to achieving general-purpose robotic manipulation in open-world settings. However, the cross-task generalization capabilities of existing VLA models remain significantly underexplored. To address this gap, we introduce **AGNOSTOS**, a novel simulation benchmark designed to rigorously evaluate cross-task zero-shot generalization in manipulation. AGNOSTOS comprises 23 unseen manipulation tasks for test—distinct from common training task distributions—and incorporates two levels of generalization difficulty to assess robustness. Our systematic evaluation reveals that current VLA models, despite being trained on diverse datasets, struggle to generalize effectively to these unseen tasks. To overcome this limitation, we propose **Cross-Task In-Context Manipulation (X-ICM)**, a method that conditions large language models (LLMs) on in-context demonstrations from seen tasks to predict action sequences for unseen tasks. Additionally, we introduce a **dynamics-guided sample selection** strategy that identifies relevant demonstrations by capturing cross-task dynamics. On AGNOSTOS, X-ICM significantly improves cross-task zero-shot generalization performance over leading VLAs, achieving improvements of 6. 0\% over $\pi_0$ and 7. 9\% over VoxPoser. We believe AGNOSTOS and X-ICM will serve as valuable tools for advancing general-purpose robotic manipulation.

PDF Details

NeurIPS Conference 2025 Conference Paper

SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors

Chen Yang
Hui Wang
Shiyao Wang
Junyang Chen
Jiabei He
Jiaming Zhou
Xi Yang
Yequan Wang

While voice technologies increasingly serve aging populations, current systems exhibit significant performance gaps due to inadequate training data capturing elderly-specific vocal characteristics like presbyphonia and dialectal variations. The limited data available on super-aged individuals in existing elderly speech datasets, coupled with overly simple recording styles and annotation dimensions, exacerbates this issue. To address the critical scarcity of speech data from individuals aged 75 and above, we introduce SeniorTalk, a carefully annotated Chinese spoken dialogue dataset. This dataset contains 55. 53 hours of speech from 101 natural conversations involving 202 participants, ensuring a strategic balance across gender, region, and age. Through detailed annotation across multiple dimensions, it can support a wide range of speech tasks. We perform extensive experiments on speaker verification, speaker diarization, speech recognition, and speech editing tasks, offering crucial insights for the development of speech technologies targeting this age group. Code is available at https: //github. com/flageval-baai/SeniorTalk and data at https: //huggingface. co/datasets/evan0617/seniortalk.

PDF Details

ICML Conference 2024 Conference Paper

CKGConv: General Graph Convolution with Continuous Kernels

Liheng Ma
Soumyasundar Pal
Yitian Zhang
Jiaming Zhou
Yingxue Zhang 0001
Mark Coates

The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel and general graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKGConv). Theoretically, we demonstrate that CKGConv is flexible and expressive. CKGConv encompasses many existing graph convolutions, and exhibits a stronger expressiveness, as powerful as graph transformers in terms of distinguishing non-isomorphic graphs. Empirically, we show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets. The code and models are publicly available at https: //github. com/networkslab/CKGConv.

Details

NeurIPS Conference 2023 Conference Paper

Diversifying Spatial-Temporal Perception for Video Domain Generalization

Kun-Yu Lin
Jia-Run Du
Yipeng Gao
Jiaming Zhou
Wei-Shi Zheng

Video domain generalization aims to learn generalizable video classification models for unseen target domains by training in a source domain. A critical challenge of video domain generalization is to defend against the heavy reliance on domain-specific cues extracted from the source domain when recognizing target videos. To this end, we propose to perceive diverse spatial-temporal cues in videos, aiming to discover potential domain-invariant cues in addition to domain-specific cues. We contribute a novel model named Spatial-Temporal Diversification Network (STDN), which improves the diversity from both space and time dimensions of video data. First, our STDN proposes to discover various types of spatial cues within individual frames by spatial grouping. Then, our STDN proposes to explicitly model spatial-temporal dependencies between video contents at multiple space-time scales by spatial-temporal relation modeling. Extensive experiments on three benchmarks of different types demonstrate the effectiveness and versatility of our approach.

PDF Details