Tianyi Zhou

How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients ACL 2026 Optimizing Length Compression in Large Reasoning Models ACL 2026 Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models AAAI 2026 FedMerge: Federated Model Merging for Personalization AAAI 2026 MindCross: Fast New Subject Adaptation with Limited Data for Cross-subject Video Reconstruction from Brain Signals AAAI 2026 Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs EACL 2026 Schoenfeld’s Anatomy of Mathematical Reasoning by Language Models ACL 2026 Sparser Mixture-of-Adapters with Cross-Layer Generalization NAACL 2025 Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion CVPR 2025 Preference Controllable Reinforcement Learning with Advanced Multi-Objective Optimization ICML 2025 Tilted Sharpness-Aware Minimization ICML 2025 R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts ICML 2025 Where to show Demos in Your Prompt: A Positional Bias of In-Context Learning EMNLP 2025 Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theory EMNLP 2025 Transformers Learn Low Sensitivity Functions: Investigations and Implications ICLR 2025 Your Mixture-of-Experts LLM Is Secretly an Embedding Model for Free ICLR 2025 OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities ICLR 2025 DataGen: Unified Synthetic Dataset Generation via Large Language Models ICLR 2025 Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach AAAI 2025 BenTo: Benchmark Reduction with In-Context Transferability ICLR 2025 Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement NAACL 2025 Multiple LLM Agents Debate for Equitable Cultural Alignment ACL 2025 From Lists to Emojis: How Format Bias Affects Model Alignment ACL 2025 What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective ACL 2025 GUI Agents: A Survey ACL 2025 Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning ACL 2025 ATLAS: Agent Tuning via Learning Critical Steps ACL 2025 Is Your Multimodal Language Model Oversensitive to Safe Queries? ICLR 2025 The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise ICLR 2025 Many-Objective Multi-Solution Transport ICLR 2025 Diffusion Curriculum: Synthetic-to-Real Data Curriculum via Image-Guided Diffusion ICCV 2025 Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs AISTATS 2025 RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters ICCV 2025 Wait, We Don’t Need to “Wait”! Removing Thinking Tokens Improves Reasoning Efficiency EMNLP 2025 RuleR: Improving LLM Controllability by Rule-based Data Recycling NAACL 2025 Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization NIPS 2024 Pre-trained Large Language Models Use Fourier Features to Compute Addition NIPS 2024 The Closeness of In-Context Learning and Weight Shifting for Softmax Regression NIPS 2024 Meta-Task Prompting Elicits Embeddings from Large Language Models ACL 2024 Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning ACL 2024 Multi-Objective Linguistic Control of Large Language Models ACL 2024 Retrieval-Augmented Retrieval: Large Language Models are Strong Zero-Shot Retriever ACL 2024 Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements ACL 2024 Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning ACL 2024 HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models CVPR 2024 Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld CVPR 2024 Corpus-Steered Query Expansion with Large Language Models EACL 2024 Do text-free diffusion models learn discriminative visual representations? ECCV 2024 When and How do negative prompts take effect? ECCV 2024 1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? EMNLP 2024 SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding EMNLP 2024 Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA EMNLP 2024 AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models EMNLP 2024 DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLMs Jailbreakers EMNLP 2024 Federated Recommendation with Additive Personalization ICLR 2024 AlpaGasus: Training a Better Alpaca with Fewer Data ICLR 2024 Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning ICLR 2024 Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation ICLR 2024 InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models ICML 2024 ODIN: Disentangled Reward Mitigates Hacking in RLHF ICML 2024 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models ICML 2024 One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts ICML 2024 From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning NAACL 2024 An End-to-End Submodular Framework for Data-Efficient In-Context Learning NAACL 2024 H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models NIPS 2023 Structured Federated Learning through Clustered Additive Modeling NIPS 2023 How Many Demonstrations Do You Need for In-context Learning? EMNLP 2023 Subclass-balancing Contrastive Learning for Long-tailed Recognition ICCV 2023 Module-wise Adaptive Distillation for Multimodality Foundation Models NIPS 2023 Does Continual Learning Equally Forget All Parameters? ICML 2023 Continual Task Allocation in Meta-Policy Network via Sparse Prompting ICML 2023 Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time ICML 2023 Structured Cooperative Learning with Graphical Model Priors ICML 2023 When to Learn What: Model-Adaptive Data Augmentation Curriculum ICCV 2023 Dual Personalization on Federated Recommendation IJCAI 2023 Merging Experts into One: Improving Computational Efficiency of Mixture of Experts EMNLP 2023 Learning To Collaborate in Decentralized Learning of Personalized Models CVPR 2022 Diverse Client Selection for Federated Learning via Submodular Maximization ICLR 2022 Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification ICLR 2022 Pareto Policy Pool for Model-based Offline Reinforcement Learning ICLR 2022 Retrospective Adversarial Replay for Continual Learning NIPS 2022 Adversarial Auto-Augment with Label Preservation: A Representation Learning Principle Guided Approach NIPS 2022 Federated Learning from Pre-Trained Models: A Contrastive Learning Approach NIPS 2022 Token Dropping for Efficient BERT Pretraining ACL 2022 FedProto: Federated Prototype Learning across Heterogeneous Clients AAAI 2022 EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning ICML 2022 Identity-Disentangled Adversarial Augmentation for Self-supervised Learning ICML 2022 Personalized Federated Learning With a Graph IJCAI 2022 Phrase-level Textual Adversarial Attack with Label Preservation NAACL 2022 TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack EMNLP 2022 Class-Disentanglement and Applications in Adversarial Detection and Defense NIPS 2021 Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction EMNLP 2021 CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum NIPS 2021 Constrained Robust Submodular Partitioning NIPS 2021 Robust Curriculum Learning: from clean label detection to noisy label self-correction ICLR 2021 AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly ICLR 2021 Isometric Propagation Network for Generalized Zero-shot Learning ICLR 2021 Curriculum Learning by Optimizing Learning Dynamics AISTATS 2021 Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction AAAI 2020 Attribute Propagation Network for Graph Zero-Shot Learning AAAI 2020 Time-Consistent Self-Supervision for Semi-Supervised Learning ICML 2020 Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention COLING 2020 Curriculum Learning by Dynamic Instance Hardness NIPS 2020 Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together NAACL 2019 Bias Also Matters: Bias Attribution for Deep Neural Network Explanation ICML 2019 Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering ICCV 2019 Jumpout : Improved Dropout for Deep Neural Networks with ReLUs ICML 2019 Learning to Propagate for Graph Meta-Learning NIPS 2019 Curriculum-guided Hindsight Experience Replay NIPS 2019 Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph IJCAI 2019 Diverse Ensemble Evolution: Curriculum Data-Model Marriage NIPS 2018 Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling IJCAI 2018 Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling ICLR 2018 Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity ICLR 2018 Scaling Submodular Maximization via Pruned Submodularity Graphs AISTATS 2017 Divide-and-Conquer Learning by Anchoring a Conical Hull NIPS 2014 Shifted Subspaces Tracking on Sparse Outlier for Motion Segmentation IJCAI 2013 Greedy Bilateral Sketch, Completion & Smoothing AISTATS 2013 Multi-label Subspace Ensemble AISTATS 2012