Yuandong Tian

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge EMNLP 2025 Agent-as-a-Judge: Evaluate Agents with Agents ICML 2025 GSM-$∞$: How Do your LLMs Behave over Infinitely Increasing Reasoning Complexity and Context Length? ICML 2025 Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning ICML 2025 AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs ICML 2025 From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications ICML 2025 SpinQuant: LLM Quantization with Learned Rotations ICLR 2025 Towards General-Purpose Model-Free Reinforcement Learning ICLR 2025 MagicPIG: LSH Sampling for Efficient LLM Generation ICLR 2025 Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces ICLR 2025 Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hacking ICLR 2025 Param$\Delta$ for Direct Mixing: Post-Train Large Language Model At Zero Cost ICLR 2025 R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference ICLR 2025 Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback EMNLP 2025 You Only Use Reactive Attention Slice When Retrieving From Long Context EMNLP 2025 LoCoCo: Dropping In Convolutions for Long Context Compression ICML 2024 Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics NIPS 2024 On the Surprising Effectiveness of Attention Transfer for Vision Transformers NIPS 2024 Learning Personalized Alignment for Evaluating Open-ended Text Generation EMNLP 2024 To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning EMNLP 2024 H-GAP: Humanoid Control with a Generalist Planner ICLR 2024 JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention ICLR 2024 RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment ICLR 2024 Efficient Streaming Language Models with Attention Sinks ICLR 2024 GenCO: Generating Diverse Designs with Combinatorial Constraints ICML 2024 Contrastive Predict-and-Search for Mixed Integer Linear Programs ICML 2024 MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases ICML 2024 TravelPlanner: A Benchmark for Real-World Planning with Language Agents ICML 2024 GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection ICML 2024 Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning ICML 2023 SurCo: Learning Linear SURrogates for COmbinatorial Nonlinear Optimization Problems ICML 2023 H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models NIPS 2023 Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information NIPS 2023 DOC: Improving Long Story Coherence With Detailed Outline Control ACL 2023 Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer NIPS 2023 MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection ICLR 2023 Efficient Planning in a Compact Latent Action Space ICLR 2023 Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning ICLR 2023 Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time ICML 2023 Learning Compiler Pass Orders using Coreset and Normalized Value Prediction ICML 2023 DreamShard: Generalizable Embedding Table Placement for Recommender Systems NIPS 2022 Re3: Generating Longer Stories With Recursive Reprompting and Revision EMNLP 2022 On the Importance of Asymmetry for Siamese Representation Learning CVPR 2022 Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games AISTATS 2022 Learning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and the Explanations AAAI 2022 Denoised MDPs: Learning World Models Better Than the World Itself ICML 2022 NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training ICLR 2022 Multi-objective Optimization by Learning Space Partition ICLR 2022 Understanding Dimensional Collapse in Contrastive Self-supervised Learning ICLR 2022 Understanding Deep Contrastive Learning via Coordinate-wise Optimization NIPS 2022 FBNetV3: Joint Architecture-Recipe Search Using Predictor Pretraining CVPR 2021 NovelD: A Simple yet Effective Exploration Criterion NIPS 2021 Latent Execution for Neural Program Synthesis Beyond Domain-Specific Languages NIPS 2021 MADE: Exploration via Maximizing Deviation from Explored Regions NIPS 2021 Learning Space Partitions for Path Planning NIPS 2021 Learn-to-Share: A Hardware-friendly Transfer Learning Framework Exploiting Computation and Parameter Sharing ICML 2021 Understanding self-supervised learning dynamics without contrastive pairs ICML 2021 Few-Shot Neural Architecture Search ICML 2021 Understanding Robustness in Teacher-Student Setting: A New Perspective AISTATS 2021 FP-NAS: Fast Probabilistic Neural Architecture Search CVPR 2021 Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension ICML 2020 Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search NIPS 2020 Neural Architecture Search Using Deep Neural Networks and Monte Carlo Tree Search AAAI 2020 FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions CVPR 2020 Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP ICLR 2020 Deep Symbolic Superoptimization Without Human Knowledge ICLR 2020 Joint Policy Search for Multi-agent Collaboration with Imperfect Information NIPS 2020 Learning to Perform Local Rewriting for Combinatorial Optimization NIPS 2019 Coda: An End-to-End Neural Program Decompiler NIPS 2019 One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers NIPS 2019 Hierarchical Decision Making by Generating and Following Natural Language Instructions NIPS 2019 CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication ACL 2019 ELF OpenGo: an analysis and open reimplementation of AlphaZero ICML 2019 FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search CVPR 2019 M^3RL: Mind-aware Multi-agent Management Reinforcement Learning ICLR 2019 Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees ICLR 2019 Bayesian Relational Memory for Semantic Visual Navigation ICCV 2019 When is a Convolutional Filter Easy to Learn? ICLR 2018 Gradient Descent Learns One-hidden-layer CNN: Don’t be Afraid of Spurious Local Minima ICML 2018 ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games NIPS 2017 An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis ICML 2017 Semantic Amodal Segmentation CVPR 2017 Hierarchical Data-Driven Descent for Efficient Optimal Deformation Estimation ICCV 2013