Xiang Cheng

29 papers · 2016–2026 · 12 conferences · across top CS/AI conferences

Achievements

+8 more ↓

🏃 Academic Marathon (9) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (11) 🐝 Cross-Pollinator (9)

🏃 Academic Marathon (9) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (9) 🏆 Keyword Champion (4) 🏆 Grand Slam 🗃️ Keyword Collector (113) 💎 Century Club (24) 🔥 Unstoppable (10)

Conferences

AAAI (6) IJCAI (4) NIPS (4) COLT (3) ICML (3) EMNLP (2) ICLR (2) ACL (1) AISTATS (1) ALT (1) IJCNLP (1) OSDI (1)

Top co-authors

Suvrit Sra (5) Sen Su (4) Ruiping Li (3) Kwangjun Ahn (3) Peter Bartlett (3) Yong Liu (2) Michael I. Jordan (2) Jingzhao Zhang (2) Lawrence Carin (2) Bo Xu (2)

Keywords

markov chain monte carlo (5) sampling algorithm (4) large language model (4) langevin dynamics (3) reinforcement learning (2) differential privacy (2) in-context learning (2) stochastic differential equation (2) path finding (2) reward function (2) wasserstein distance (2) knowledge graph reasoning (2) mixing time (2) domain adaptation (2) generative adversarial imitation learning (2) transfer learning (1) zero-shot learning (1) performance optimization (1) non-convex optimization (1) stochastic gradient descent (1)

Papers

TinyChemVL: Advancing Chemical Vision-Language Models via Efficient Visual Token Reduction and Complex Reaction Tasks AAAI 2026 Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks ACL 2026 PrivSV: Differentially Private Steering Vector for Large Language Models AAAI 2026 From Chaos to Cure: A Prefix Heuristics Guided Model-Agnostic Adaptive Detoxification Framework AAAI 2026 Towards Robust Event-Based Depth Estimation: Bridging Synthetic and Real Domains with Motion Adaptation AAAI 2026 Graph Transformers Dream of Electric Flow ICLR 2025 Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot EMNLP 2025 On Understanding Attention-Based In-Context Learning for Categorical Data ICML 2025 Principles and Methodologies for Serial Performance Optimization OSDI 2025 Linear attention is (maybe) all you need (to understand Transformer optimization) ICLR 2024 Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context ICML 2024 Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions NIPS 2023 Restart Sampling for Improving Generative Processes NIPS 2023 Transformers learn to implement preconditioned gradient descent for in-context learning NIPS 2023 Efficient Sampling on Riemannian Manifolds via Langevin MCMC NIPS 2022 Optimal dimension dependence of the Metropolis-Adjusted Langevin Algorithm COLT 2021 An End-to-End Solution for Named Entity Recognition in eCommerce Search AAAI 2021 Differentially Private Correlation Alignment for Domain Adaptation IJCAI 2021 Multi-Task Learning with Generative Adversarial Training for Multi-Passage Machine Reading Comprehension AAAI 2020 Stochastic Gradient and Langevin Processes ICML 2020 LISNN: Improving Spiking Neural Networks with Lateral Interactions for Robust Object Recognition IJCAI 2020 DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning IJCNLP 2019 DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning EMNLP 2019 Underdamped Langevin MCMC: A non-asymptotic analysis COLT 2018 Exploring Encoder-Decoder Model for Distant Supervised Relation Extraction IJCAI 2018 FLAG n’ FLARE: Fast Linearly-Coupled Adaptive Gradient Methods AISTATS 2018 Convergence of Langevin MCMC in KL-divergence ALT 2018 Deep Supervised Hashing with Nonlinear Projections IJCAI 2017 Asymptotic behavior of \ell_p-based Laplacian regularization in semi-supervised learning COLT 2016