Tianyi Zhang

Mango: Multi-Agent Web Navigation via Global-View Optimization ACL 2026 Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy AAAI 2026 GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents ACL 2026 RISK: A Framework for GUI Agents in E-commerce Risk Management ACL 2026 Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification ACL 2026 From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization CVPR 2025 A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation EMNLP 2025 Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation EMNLP 2025 MASTER: A Multi-Agent System with LLM Specialized MCTS NAACL 2025 Adaptive Merchant-Centric Risk Control via Unbiased Decision-Making and Dynamic Optimization in E-Commerce AAAI 2025 Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation ICML 2025 Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos ICML 2025 CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems ACL 2025 Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video ICLR 2025 Selective Prompt Anchoring for Code Generation ICML 2025 LeanQuant: Accurate and Scalable Large Language Model Quantization with Loss-error-aware Grid ICLR 2025 Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy ICCV 2025 Quanta Neural Networks: From Photons to Perception ICCV 2025 Probing Political Ideology in Large Language Models: How Latent Political Representations Generalize Across Tasks EMNLP 2025 PDDLEGO: Iterative Planning in Textual Environments NAACL 2024 KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization NIPS 2024 NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention NIPS 2024 Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks NIPS 2024 Multi-Modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation AAAI 2024 Transformer-Based Selective Super-resolution for Efficient Image Refinement AAAI 2024 Compositional Inversion for Stable Diffusion Models AAAI 2024 PROC2PDDL: Open-Domain Planning Representations from Texts ACL 2024 DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision CVPR 2024 Robust Incremental Structure-from-Motion with Hybrid Features ECCV 2024 CodeJudge: Evaluating Code Generation with Large Language Models EMNLP 2024 A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasks EMNLP 2024 GroupCover: A Secure, Efficient and Scalable Inference Framework for On-device Model Protection based on TEEs ICML 2024 A powerful and modern AAC composition tool for impaired speakers INTERSPEECH 2024 Generating Progressive Images from Pathological Transitions via Diffusion Model MICCAI 2024 Patch-Based Selection and Refinement for Early Object Detection WACV 2024 Graph Self-supervised Learning via Proximity Distribution Minimization UAI 2023 Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations EMNLP 2023 When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization EACL 2023 AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback NIPS 2023 Evaluating Verifiability in Generative Search Engines EMNLP 2023 Efficient Graph Field Integrators Meet Point Clouds ICML 2023 DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation ICML 2023 Coder Reviewer Reranking for Code Generation ICML 2023 Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions NIPS 2023 TempLM: Distilling Language Models into Template-Based Generators ACL 2023 Human-in-the-loop Schema Induction ACL 2023 SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs IJCAI 2023 Multi-class Classification from Multiple Unlabeled Datasets with Partial Risk Regularization ACML 2022 LADIS: Language Disentanglement for 3D Shape Editing EMNLP 2022 Decentralized Training of Foundation Models in Heterogeneous Environments NIPS 2022 From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers ICML 2022 CREATIVESUMM: Shared Task on Automatic Summarization for Creative Writing COLING 2022 Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification EMNLP 2022 Retaining Knowledge for Learning with Dynamic Definition NIPS 2022 Learning to Stop with Surprisingly Few Samples COLT 2021 Revisiting Few-sample BERT Fine-tuning ICLR 2021 PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS With Relationship Recovery CVPR 2021 On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies NAACL 2021 Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection AAAI 2021 A One-step Approach to Covariate Shift Adaptation ACML 2020 Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach AISTATS 2020 Splitting vs. Merging: Mining Object Regions with Discrepancy and Intersection Loss for Weakly Supervised Semantic Segmentation ECCV 2020 Demystifying Orthogonal Monte Carlo and Beyond NIPS 2020 Identifying Mislabeled Data using the Area Under the Margin Ranking NIPS 2020 Simplifying Graph Convolutional Networks ICML 2019 SWALP : Stochastic Weight Averaging in Low Precision Training ICML 2019