Search Results for author: Jialong Wu

Found 29 papers, 20 papers with code

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement

1 code implementation4 Apr 2025 Runnan Fang, Xiaobin Wang, Yuan Liang, Shuofei Qiao, Jialong Wu, Zekun Xi, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions.

Navigate

LocAgent: Graph-Guided LLM Agents for Code Localization

1 code implementation12 Mar 2025 Zhaoling Chen, Xiangru Tang, Gangda Deng, Fang Wu, Jialong Wu, Zhiwei Jiang, Viktor Prasanna, Arman Cohan, Xingyao Wang

By parsing codebases into directed heterogeneous graphs, LocAgent creates a lightweight representation that captures code structures (files, classes, functions) and their dependencies (imports, invocations, inheritance), enabling LLM agents to effectively search and locate relevant entities through powerful multi-hop reasoning.

GitHub issue resolution Navigate

Benchmarking Temporal Reasoning and Alignment Across Chinese Dynasties

1 code implementation24 Feb 2025 Zhenglin Wang, Jialong Wu, Pengfei Li, Yong Jiang, Deyu Zhou

Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications.

Benchmarking

WebWalker: Benchmarking LLMs in Web Traversal

1 code implementation13 Jan 2025 Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, Fei Huang

Extensive experimental results show that WebWalkerQA is challenging and demonstrates the effectiveness of RAG combined with WebWalker, through the horizontal and vertical integration in real-world scenarios.

Benchmarking Open-Domain Question Answering +2

A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

1 code implementation17 Oct 2024 Siwei Wu, Zhongyuan Peng, Xinrun Du, Tuney Zheng, Minghao Liu, Jialong Wu, Jiachen Ma, Yizhi Li, Jian Yang, Wangchunshu Zhou, Qunshu Lin, Junbo Zhao, Zhaoxiang Zhang, Wenhao Huang, Ge Zhang, Chenghua Lin, J. H. Liu

In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i. e., math, coding, commonsense reasoning).

Math

Long-Sequence Recommendation Models Need Decoupled Embeddings

1 code implementation3 Oct 2024 Ningya Feng, Junwei Pan, Jialong Wu, Baixu Chen, Ximei Wang, Qian Li, Xian Hu, Jie Jiang, Mingsheng Long

In this work, we identify and characterize, for the first time, a neglected deficiency in existing long-sequence recommendation models: a single set of embeddings struggles with learning both attention and representation, leading to interference between these two processes.

Recommendation Systems

AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment

1 code implementation2 Jul 2024 Yilong Lai, Jialong Wu, Congzhi Zhang, Haowen Sun, Deyu Zhou

Conversational Query Reformulation (CQR) has significantly advanced in addressing the challenges of conversational search, particularly those stemming from the latent user intent and the need for historical context.

Context Query Reformulation Conversational Search +1

Symbolic Learning Enables Self-Evolving Agents

1 code implementation26 Jun 2024 Wangchunshu Zhou, Yixin Ou, Shengwei Ding, Long Li, Jialong Wu, Tiannan Wang, Jiamin Chen, Shuai Wang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang

In this work, we introduce agent symbolic learning, a systematic framework that enables language agents to optimize themselves on their own in a data-centric way using symbolic optimizers.

SEED: Accelerating Reasoning Tree Construction via Scheduled Speculative Decoding

1 code implementation26 Jun 2024 Zhenglin Wang, Jialong Wu, Yilong Lai, Congzhi Zhang, Deyu Zhou

However, such methods introduce significant inference latency due to the systematic exploration and evaluation of multiple thought paths.

Management

SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Data

no code implementations15 Jun 2024 Jialong Wu, Mirko Meuter, Markus Schoeler, Matthias Rottmann

Radar-based perception has gained increasing attention in autonomous driving, yet the inherent sparsity of radars poses challenges.

Autonomous Driving object-detection +1

iVideoGPT: Interactive VideoGPTs are Scalable World Models

1 code implementation24 May 2024 Jialong Wu, Shaofeng Yin, Ningya Feng, Xu He, Dong Li, Jianye Hao, Mingsheng Long

This work introduces Interactive VideoGPT (iVideoGPT), a scalable autoregressive transformer framework that integrates multimodal signals--visual observations, actions, and rewards--into a sequence of tokens, facilitating an interactive experience of agents via next-token prediction.

Decision Making Model-based Reinforcement Learning +3

Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment

no code implementations5 Mar 2024 Congzhi Zhang, Linhai Zhang, Jialong Wu, Yulan He, Deyu Zhou

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases.

Contrastive Learning Data Augmentation +4

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models

1 code implementation2 Mar 2024 Linhai Zhang, Jialong Wu, Deyu Zhou, Guoqiang Xu

For poor model calibration, we incorporate the regularization method during LoRA training to keep the model from being over-confident, and the Monte-Carlo dropout mechanism is employed to enhance the uncertainty estimation.

Active Learning Few-Shot Learning +1

DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference

1 code implementation2 Mar 2024 Jialong Wu, Linhai Zhang, Deyu Zhou, Guoqiang Xu

However, most of the present debiasing methods focus on single-variable causal inference, which is not suitable for ABSA with two input variables (the target aspect and the review).

Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +3

Constituency Parsing using LLMs

no code implementations30 Oct 2023 Xuefeng Bai, Jialong Wu, Yulong Chen, Zhongqing Wang, Yue Zhang

Constituency parsing is a fundamental yet unsolved natural language processing task.

Constituency Parsing

HarmonyDream: Task Harmonization Inside World Models

1 code implementation30 Sep 2023 Haoyu Ma, Jialong Wu, Ningya Feng, Chenjun Xiao, Dong Li, Jianye Hao, Jianmin Wang, Mingsheng Long

Model-based reinforcement learning (MBRL) holds the promise of sample-efficient learning by utilizing a world model, which models how the environment works and typically encompasses components for two tasks: observation modeling and reward modeling.

Atari Games 100k Model-based Reinforcement Learning +1

Agents: An Open-source Framework for Autonomous Language Agents

1 code implementation14 Sep 2023 Wangchunshu Zhou, Yuchen Eleanor Jiang, Long Li, Jialong Wu, Tiannan Wang, Shi Qiu, Jintian Zhang, Jing Chen, Ruipu Wu, Shuai Wang, Shiding Zhu, Jiyu Chen, Wentao Zhang, Xiangru Tang, Ningyu Zhang, Huajun Chen, Peng Cui, Mrinmaya Sachan

Recent advances on large language models (LLMs) enable researchers and developers to build autonomous language agents that can automatically solve various tasks and interact with environments, humans, and other agents using natural language interfaces.

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

1 code implementation NeurIPS 2023 Jialong Wu, Haoyu Ma, Chaoyi Deng, Mingsheng Long

To tackle this issue, we introduce Contextualized World Models (ContextWM) that explicitly separate context and dynamics modeling to overcome the complexity and diversity of in-the-wild videos and facilitate knowledge transfer between distinct scenes.

Autonomous Driving Decoder +4

CLIPood: Generalizing CLIP to Out-of-Distributions

1 code implementation2 Feb 2023 Yang Shu, Xingzhuo Guo, Jialong Wu, Ximei Wang, Jianmin Wang, Mingsheng Long

This paper aims at generalizing CLIP to out-of-distribution test data on downstream tasks.

Out-of-Dynamics Imitation Learning from Multimodal Demonstrations

1 code implementation13 Nov 2022 Yiwen Qiu, Jialong Wu, Zhangjie Cao, Mingsheng Long

Existing imitation learning works mainly assume that the demonstrator who collects demonstrations shares the same dynamics as the imitator.

Imitation Learning MuJoCo

Real-Time And Robust 3D Object Detection with Roadside LiDARs

no code implementations11 Jul 2022 Walter Zimmer, Jialong Wu, Xingcheng Zhou, Alois C. Knoll

This work aims to address the challenges in autonomous driving by focusing on the 3D perception of the environment using roadside LiDARs.

Autonomous Driving Domain Adaptation +3

Flowformer: Linearizing Transformers with Conservation Flows

1 code implementation13 Feb 2022 Haixu Wu, Jialong Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long

By respectively conserving the incoming flow of sinks for source competition and the outgoing flow of sources for sink allocation, Flow-Attention inherently generates informative attentions without using specific inductive biases.

Ranked #4 on D4RL on D4RL

D4RL Offline RL +2

Supported Policy Optimization for Offline Reinforcement Learning

3 code implementations13 Feb 2022 Jialong Wu, Haixu Wu, Zihan Qiu, Jianmin Wang, Mingsheng Long

Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy.

Offline RL reinforcement-learning +2

Cannot find the paper you are looking for? You can Submit a new open access paper.