Xing Sun

Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving AAAI 2026 HiChunk: Evaluating and Enhancing Retrieval Augmented Generation with Hierarchical Chunking ACL 2026 Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG ACL 2026 Query-Aware Knowledge Retrieval via Hyperbolic Structuring ACL 2026 Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM ICML 2025 Probability-Density-aware Semi-supervised Learning AAAI 2025 RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing Agents ACL 2025 Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing ACL 2025 RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following ACL 2025 MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL COLING 2025 FIPO: Free-form Instruction-oriented Prompt Optimization with Preference Dataset and Modular Fine-tuning Schema COLING 2025 Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis CVPR 2025 Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts EMNLP 2025 Learning Interleaved Image-Text Comprehension in Vision-Language Large Models ICLR 2025 RocketEval: Efficient automated LLM evaluation via grading checklist ICLR 2025 DS-VLM: Diffusion Supervision Vision Language Model ICML 2025 FlexiReID: Adaptive Mixture of Expert for Multi-Modal Person Re-Identification ICML 2025 A General and Efficient Training for Transformer via Token Expansion CVPR 2024 Sinkhorn Distance Minimization for Knowledge Distillation COLING 2024 Visual Hallucination Elevates Speech Recognition AAAI 2024 SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space AAAI 2024 Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation AAAI 2024 SoftCLIP: Softer Cross-Modal Alignment Makes CLIP Stronger AAAI 2024 Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence EMNLP 2024 Multimodal Label Relevance Ranking via Reinforcement Learning ECCV 2024 HRVDA: High-Resolution Visual Document Assistant CVPR 2024 Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models CVPR 2024 Aligning and Prompting Everything All at Once for Universal Visual Perception CVPR 2024 CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes NIPS 2023 Graph-Based Self-Learning for Robust Person Re-Identification WACV 2023 Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration ICCV 2023 D3G: Exploring Gaussian Prior for Temporal Sentence Grounding with Glance Annotation ICCV 2023 Coarse-to-Fine: Learning Compact Discriminative Representation for Single-Stage Image Retrieval ICCV 2023 Mitigating Memorization of Noisy Labels via Regularization between Representations ICLR 2023 Span-level Aspect-based Sentiment Analysis via Table Filling ACL 2023 PAC-Net: Highlight Your Video via History Preference Modeling ECCV 2022 Self-supervised Models are Good Teaching Assistants for Vision Transformers ICML 2022 AS-MLP: An Axial Shifted MLP Architecture for Vision ICLR 2022 Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer AAAI 2022 Training-Free Transformer Architecture Search CVPR 2022 DIFNet: Boosting Visual Information Flow for Image Captioning CVPR 2022 Efficient Decoder-Free Object Detection with Transformers ECCV 2022 DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning ECCV 2022 Learning To Know Where To See: A Visibility-Aware Approach for Occluded Person Re-Identification ICCV 2021 Removing the Background by Adding the Background: Towards Background Robust Self-Supervised Video Representation Learning CVPR 2021 Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification CVPR 2021 Dig into Multi-modal Cues for Video Retrieval with Hierarchical Alignment IJCAI 2021 Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval With Partial Query ICCV 2021 PR-Net: Preference Reasoning for Personalized Video Highlight Detection ICCV 2021 Learning with Instance-Dependent Label Noise: A Sample Sieve Approach ICLR 2021 One for More: Selecting Generalizable Samples for Generalizable ReID Model AAAI 2021 Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion AAAI 2021 Learning Canonical View Representation for 3D Shape Recognition With Arbitrary Views ICCV 2021 Temporal Modulation Network for Controllable Space-Time Video Super-Resolution CVPR 2021 Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians ECCV 2020 Pruning Filter in Filter NIPS 2020 Rethinking Temporal Fusion for Video-Based Person Re-Identification on Semantic and Time Aspect AAAI 2020 Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification AAAI 2020 Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification AAAI 2020 Filter Grafting for Deep Neural Networks CVPR 2020 Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training CVPR 2019 On the Size and Recovery of Submatrices of Ones in a Random Binary Matrix JMLR 2008