Xiaoyu Shen

Beyond Global Similarity: Multi-Conditional Retrieval for Fine-Grained Cross-Modal Understanding CVPR 2026 Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework ACL 2026 Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models CVPR 2026 UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking CVPR 2026 What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models CVPR 2026 Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant EMNLP 2025 Beyond Content Relevance: Evaluating Instruction Following in Retrieval Models ICLR 2025 CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs ICLR 2025 Context Guided Transformer Entropy Modeling for Video Compression ICCV 2025 Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation NAACL 2025 From Calculation to Adjudication: Examining LLM Judges on Mathematical Reasoning Tasks ACL 2025 HAF-RM: A Hybrid Alignment Framework for Reward Model Training ACL 2025 InternLM-Law: An Open-Sourced Chinese Legal Large Language Model COLING 2025 LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding ACL 2025 MultiConIR: Towards Multi-Condition Information Retrieval EMNLP 2025 Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices CVPR 2025 Multimodal Language Models See Better When They Look Shallower EMNLP 2025 PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasks EMNLP 2025 Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai ACL 2025 SkipGPT: Each Token is One of a Kind ICML 2025 Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning ACL 2025 VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs EMNLP 2025 A Preference-driven Paradigm for Enhanced Translation with Large Language Models NAACL 2024 Assessing “Implicit” Retrieval Robustness of Large Language Models EMNLP 2024 Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning EMNLP 2024 Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice? EMNLP 2024 LawBench: Benchmarking Legal Knowledge of Large Language Models EMNLP 2024 SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects EACL 2024 StableMask: Refining Causal Masking in Decoder-only Transformer ICML 2024 The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models EMNLP 2024 The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis ACL 2024 To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models EMNLP 2024 Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism EMNLP 2024 Meta Self-Refinement for Robust Learning with Weak Supervision EACL 2023 Neural Ranking with Weak Supervision for Open-Domain Question Answering : A Survey EACL 2023 Weaker Than You Think: A Critical Look at Weakly Supervised Learning ACL 2023 xPQA: Cross-Lingual Product Question Answering in 12 Languages ACL 2023 A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation NAACL 2022 FocusQA: Open-Domain Question Answering with a Context in Focus EMNLP 2022 From Rewriting to Remembering: Common Ground for Conversational QA Models ACL 2022 Logical Fallacy Detection EMNLP 2022 Product Answer Generation from Heterogeneous Sources: A New Benchmark and Best Practices ACL 2022 RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining ACL 2022 semiPQA: A Study on Product Question Answering over Semi-structured Data ACL 2022 Neural Data-to-Text Generation with LM-based Text Augmentation EACL 2021 On Training Instance Selection for Few-Shot Neural Text Generation ACL 2021 Preventing Author Profiling through Zero-Shot Multilingual Back-Translation EMNLP 2021 DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool COLING 2020 Data Augmentation for Multiclass Utterance Classification – A Systematic Study COLING 2020 Diversifying Dialogue Generation with Non-Conversational Text ACL 2020 MovieChats: Chat like Humans in a Closed Domain EMNLP 2020 Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence ACL 2020 Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator EMNLP 2019 Improving Multi-turn Dialogue Modelling with Utterance ReWriter ACL 2019 Select and Attend: Towards Controllable Content Selection in Text Generation EMNLP 2019 Unsupervised Rewriter for Multi-Sentence Compression ACL 2019 NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation EMNLP 2018 A Conditional Variational Framework for Dialog Generation ACL 2017 DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset IJCNLP 2017 Estimation of Gap Between Current Language Models and Human Performance Interspeech 2017