Yao Hu

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models ACL 2026 CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models AAAI 2026 Leveraging Outline-Optimized Generative Interactions and Critique for Self-Refining Outlines with Reinforcement Learning ACL 2026 LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient ACL 2026 OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models CVPR 2026 PROMO: Promptable Outfitting for Efficient High-Fidelity Virtual Try-On CVPR 2026 R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms ACL 2026 ReMatch: Boosting Representation through Matching for Multimodal Retrieval CVPR 2026 Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors ACL 2026 SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility ACL 2026 The Clustering Strikes Back: Building Cost-Effective and High-Performance ANNS at Scale with Helmsman (Operational Systems) OSDI 2026 A Sanity Check for AI-generated Image Detection ICLR 2025 Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation ACL 2025 CogLM: Tracking Cognitive Development of Large Language Models NAACL 2025 DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision EMNLP 2025 DynamicFace: High-Quality and Consistent Face Swapping for Image and Video using Composable 3D Facial Priors ICCV 2025 DynaPrompt: Dynamic Test-Time Prompt Tuning ICLR 2025 EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation EMNLP 2025 From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen ACL 2025 InsBank: Evolving Instruction Subset for Ongoing Alignment EMNLP 2025 iPET: An Interactive Emotional Companion Dialogue System with LLM-Powered Virtual Pet World Simulation ACL 2025 LamRA: Large Multimodal Model as Your Advanced Retrieval Assistant CVPR 2025 Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning NAACL 2025 MoDification: Mixture of Depths Made Easy NAACL 2025 Object-centric Video Question Answering with Visual Grounding and Referring ICCV 2025 RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios EMNLP 2025 Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation ACL 2025 SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment EMNLP 2025 SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generation EMNLP 2025 SNS-Bench: Defining, Building, and Assessing Capabilities of Large Language Models in Social Networking Services ICML 2025 Speculative Decoding for Multi-Sample Inference EMNLP 2025 Target-Driven Distillation: Consistency Distillation with Target Timestep Selection and Decoupled Guidance AAAI 2025 Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair EMNLP 2025 Towards the Law of Capacity Gap in Distilling Language Models ACL 2025 Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective COLING 2025 UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization ICLR 2025 VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models ICCV 2025 ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty COLING 2025 AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries AAAI 2024 BatchEval: Towards Human-like Text Evaluation ACL 2024 Controllable Mind Visual Diffusion Model AAAI 2024 Efficient Stochastic Approximation of Minimax Excess Risk Optimization ICML 2024 Focused Large Language Models are Stable Many-Shot Learners EMNLP 2024 Instruction Embedding: Latent Representations of Instructions Towards Task Identification NeurIPS 2024 Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation ACL 2024 Poor-Supervised Evaluation for SuperLLM via Mutual Consistency ACL 2024 PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference ACL 2024 Small-loss Adaptive Regret for Online Convex Optimization ICML 2024 SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation CVPR 2024 VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation NeurIPS 2024 VISA: Reasoning Video Object Segmentation via Large Language Model ECCV 2024 Vript: A Video Is Worth Thousands of Words NeurIPS 2024 ZONE: Zero-Shot Instruction-Guided Local Editing CVPR 2024 2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition EMNLP 2023 OvarNet: Towards Open-Vocabulary Object Attribute Recognition CVPR 2023 Towards Open-Vocabulary Video Instance Segmentation ICCV 2023 Multi-Shot Temporal Event Localization: A Benchmark CVPR 2021 Salient Object Ranking With Position-Preserved Attention ICCV 2021 Spatial-temporal Causal Inference for Partial Image-to-video Adaptation AAAI 2021 Stochastic Bandits with Graph Feedback in Non-Stationary Environments AAAI 2021 SwiftNet: Real-Time Video Object Segmentation CVPR 2021 Adapting to Smoothness: A More Universal Algorithm for Online Convex Optimization AAAI 2020 Deep Time-Stream Framework for Click-through Rate Prediction by Tracking Interest Evolution AAAI 2020 Multi-View Partial Multi-Label Learning with Graph-Based Disambiguation AAAI 2020 Uncertainty Aware Graph Gaussian Process for Semi-Supervised Learning AAAI 2020 Hybrid Item-Item Recommendation via Semi-Parametric Embedding IJCAI 2019 Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning IJCAI 2019 Multi-Objective Generalized Linear Bandits IJCAI 2019 Multi-View Active Learning for Video Recommendation IJCAI 2019 Multi-View Multi-Label Learning with View-Specific Information Extraction IJCAI 2019 Optimal Algorithms for Lipschitz Bandits with Heavy-tailed Rewards ICML 2019 Active Learning via Neighborhood Reconstruction IJCAI 2013 A Unified Approximate Nearest Neighbor Search Scheme by Combining Data Structure and Hashing IJCAI 2013 Complementary Projection Hashing ICCV 2013