JJ
Jiaya Jia
cs.CVcs.AIcs.LGcs.CLAlgorithmsArtificial Intelligencecs.ROcs.MMSubtraction TechniqueColor
On Valency
published · living versionsW_3d4rw8rb·v1 · currentpublished
Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation
with Zheng Zhu, Xiaozhuan Liang, Xi Chen, Bei Yu
1 version
Preprints & journals
216 papers in the corpus · 2004–2026RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control2610.12185v1 · Yuxin Chen, Senqiao Yang, Zixuan Wang et al.2026 · 0 citationsarXiv
WorldLine: Action-Driven Visual Simulation for Robotic Manipulation2609.38059v1 · Shenghe Zheng, Wenbo Li, Jiyao Zhang et al.2026 · 0 citationsarXiv
AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?2609.35025v1 · Haotian Luo, Haoyu Wang, Zeyu Qin et al.2026 · 0 citationsarXiv
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models2608.27550v2 · Senqiao Yang, Chengyao Wang, Yuxin Chen et al.2026 · 0 citationsarXiv
StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding2608.05703v1 · Xichen Zhang, Guankai Li, Yinghao Zhu et al.2026 · 0 citationsarXiv
MemVLN: Episodic and Procedural Memory for Vision-and-Language Navigation2607.23504v1 · Yuqi Liu, Shengju Qian, Tianyuan Qu et al.2026 · 0 citationsarXiv
GKDT: General Keypoint Detection Transformer2607.00752v1 · Changsheng Lu, Yuxin Chen, Haokun Gui et al.2026 · 0 citationsarXiv
PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models2606.26694v2 · Bin Hu, Yanwen Ma, Jiehui Huang et al.2026 · 0 citationsarXiv
CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation2606.21982v1 · Wenhu Zhang, Kun Cheng, Changyuan Wang et al.2026 · 0 citationsarXiv
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating2606.21661v1 · Jiehui Huang, Yuechen Zhang, Bin Xia et al.2026 · 0 citationsarXiv
A Survey of Audio Reasoning in Multimodal Foundation Models2605.21008v1 · Zhihan Guo, Wenqian Cui, Guan-Ting Lin et al.2026 · 0 citationsarXiv
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond2604.22748v3 · Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin et al.2026 · 0 citationsarXiv
StarVLA-: Reducing Complexity in Vision-Language-Action Systems2604.11757v2 · Jinhui Ye, Ning Gao, Senqiao Yang et al.2026 · 0 citationsarXiv
VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models2603.22003v3 · Zixuan Wang, Yuxin Chen, Yuqi Liu et al.2026 · 0 citationsarXiv
Mini-Gemini: Mining the Potential of Multi-Modality Vision Language Models.41296951 · Li, Yanwei, Zhang, Yuechen, Wang, Chengyao et al.2025 · 59 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;PP
SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation2601.14615v1 · Xichen Zhang, Ziyi He, Yinghao Zhu et al.2026 · 0 citationsarXiv
DreamOmni3: Scribble-based Editing and Generation2512.22525v2 · Bin Xia, Bohao Peng, Jiyang Liu et al.2025 · 0 citationsarXiv
VisionDirector: Vision-Language Guided Closed-Loop Refinement for Generative Image Synthesis2512.19243v3 · Meng Chu, Senqiao Yang, Haoxuan Che et al.2025 · 0 citationsarXiv
RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing2512.16864v2 · Tianyuan Qu, Lei Ke, Xiaohang Zhan et al.2025 · 0 citationsarXiv
UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation2512.07831v1 · Jiehui Huang, Yuechen Zhang, Xu He et al.2025 · 0 citationsarXiv
VLPose: Bridging the Domain Gap in Pose Estimation With Language-Vision Tuning.40788797 · Li, Jingyao, Chen, Pengguang, Ju, Xuan et al.2025 · 3 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(11):10836-10847
SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration2510.19767v1 · Xichen Zhang, Sitong Wu, Haoru Tan et al.2025 · 0 citationsarXiv
Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning2510.19807v2 · Xichen Zhang, Sitong Wu, Yinghao Zhu et al.2025 · 0 citationsarXiv
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy2510.13778v1 · Xinyi Chen, Yilun Chen, Yanwei Fu et al.2025 · 0 citationsarXiv
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models2510.10606v4 · Yuqi Liu, Liangyu Chen, Jiazhen Liu et al.2025 · 0 citationsarXiv
DreamOmni2: Multimodal Instruction-based Editing and Generation2510.06679v1 · Bin Xia, Bohao Peng, Yuechen Zhang et al.2025 · 0 citationsarXiv
Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents2510.06214v1 · Mingkang Zhu, Xi Chen, Bei Yu et al.2025 · 0 citationsarXiv
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models2510.05095v1 · Mingkang Zhu, Xi Chen, Bei Yu et al.2025 · 0 citationsarXiv
MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech2509.25131v1 · Chengyao Wang, Zhisheng Zhong, Bohao Peng et al.2025 · 1 citationarXiv
Exploiting Discriminative Codebook Prior for Autoregressive Image Generation2508.10719v1 · Longxiang Tang, Ruihang Chu, Xiang Wang et al.2025 · 0 citationsarXiv
DreamVE: Unified Instruction-based Image and Video Editing2508.06080v1 · Bin Xia, Jiyang Liu, Yuechen Zhang et al.2025 · 0 citationsarXiv
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning2507.13348v1 · Senqiao Yang, Junyi Li, Xin Lai et al.2025 · 4 citationsarXiv
DynamicBench: Evaluating Real-Time Report Generation in Large Language Models2506.21343v1 · Jingyao Li, Hao Sun, Zile Qiao et al.2025 · 0 citationsarXiv
TGDPO: Harnessing Token-Level Reward Guidance for Enhancing Direct Preference Optimization2506.14574v1 · Mingkang Zhu, Xi Chen, Zhongdao Wang et al.2025 · 0 citationsarXiv
Logits-Based Finetuning2505.24461v2 · Jingyao Li, Senqiao Yang, Sitong Wu et al.2025 · 1 citationarXiv
RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models2505.19125v1 · Yuqi Liu, Qin Jin, Tianyuan Qu et al.2025 · 0 citationsarXiv
ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay2505.16282v1 · Fanbin Lu, Zhisheng Zhong, Shu Liu et al.2025 · 0 citationsarXiv
Training-Free Efficient Video Generation via Dynamic Token Carving2505.16864v2 · Yuechen Zhang, Jinbo Xing, Bin Xia et al.2025 · 2 citationsarXiv
VisionReasoner: Unified Reasoning-Integrated Visual Perception via Reinforcement Learning2505.12081v5 · Yuqi Liu, Tianyuan Qu, Zhisheng Zhong et al.2025 · 0 citationsarXiv
TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning2504.16505v2 · Meng Chu, Yukang Chen, Haokun Gui et al.2025 · 1 citationarXiv
Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?2503.12496v2 · Tianyuan Qu, Longxiang Tang, Bohao Peng et al.2025 · 2 citationsarXiv
STEVE: A Step Verification Pipeline for Computer-use Agent Training2503.12532v2 · Fanbin Lu, Zhisheng Zhong, Ziqin Wei et al.2025 · 0 citationsarXiv
Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation2503.08575v1 · Mingkang Zhu, Xi Chen, Zhongdao Wang et al.2025 · 0 citationsarXiv
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement2503.06520v3 · Yuqi Liu, Bohao Peng, Zhisheng Zhong et al.2025 · 0 citationsarXiv
Enhancing LLM Knowledge Learning through Generalization2503.03705v2 · Mingkang Zhu, Xi Chen, Zhongdao Wang et al.2025 · 2 citationsarXiv
GRADEO: Towards Human-Like Evaluation for Text-to-Video Generation via Multi-Step Reasoning2503.02341v2 · Zhun Mou, Bin Xia, Zhengchao Huang et al.2025 · 0 citationsarXiv
MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers2501.03931v2 · Yuechen Zhang, Yaoyang Liu, Bin Xia et al.2025 · 2 citationsarXiv
Generative Video Propagation2412.19761v1 · Shaoteng Liu, Tianyu Wang, Jui-Hsien Wang et al.2024 · 5 citationsarXiv
DreamOmni: Unified Image Generation and Editing2412.17098v2 · Bin Xia, Yuechen Zhang, Jingyao Li et al.2024 · 4 citationsarXiv
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition2412.09501v1 · Zhisheng Zhong, Chengyao Wang, Yuqi Liu et al.2024 · 2 citationsarXiv
Career total: 408 works. 216 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.