ÌÇÐÄTV

We are delighted to celebrate the 19 accepted papers involving colleagues and students from the Department of Computer Science (DCS) at the University of ÌÇÐÄTV, together with their collaborators.

The papers span an exciting range of topics: the foundations of machine learning, reinforcement learning and decision-making, causal discovery, trustworthy AI, alignment of large language models, robotics, computer vision, and more.

Congratulations to all the authors! Here is the full list of 19 accepted papers at NeurIPS 2026!

• Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment. Loukas Sfountouris, Giannis Daras, .
• Deep Gaussian Processes on Directed Acyclic Graphs. Federico Perlino, Oliver Hamelijnck, Adam Johansen, Theodoros Damoulas.
• Distributionally-Robust Policy Learning with Observational Data. .
• GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs. Peyman Bagershahi, Fangxin Wang, Sourav Medya, .
• How does feature learning change the function space evolution? , Bruno Loureiro, Long Tran-Thanh, .
• Humanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward Gating. Haozhuo Zhang, Qiang Zhang, Jian Tang, Mingzhe Ni, , Angelo Cangelosi, Wei Pan.
• Inference-Time Nash Alignment. Hadi Hosseini, , Duohan Zhang.
• Meta-Learning Preferences for Multilingual LLM Alignment. Jiaying Lin, Seongho Son, Nam Phuong Tran, Long Tran-Thanh, Ilija Bogunovic, .
• Mildly Overparameterized ReLU Networks on Orthogonal Data: Incremental Learning and Implicit Bias. James Town, Etienne Boursier, , , Ranko Lazic. (Spotlight)
• MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound. Phu-Hoa Pham, Tran Chi Nguyen, Phu Quy Nguyen Lam, Dao Sy Duy Minh, Trung-Kiet Huynh, Long Tran-Thanh.
• Provably Accurate Shapley Value Estimation in High Dimensions via Sparse Leverage Sampling. Ricardo Parada, Akbarkhuja Anvarkhujaev, Carlos Martin, William Chang, Long Tran-Thanh, Nam Phuong Tran.
• SCDBench: A Benchmark for LLM-Based Smart Contract Decompilers. , Dawn Song, Arthur Gervais.
• Subprocess-Constrained Markov Decision Processes. Jiarui Gan, .
• The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection. Benedict Russell, , .
• Training-Free Cultural Alignment of Large Language Models via Persona Disagreement. Dao Sy Duy Minh, Trung-Kiet Huynh, Tran Chi Nguyen, Phu Quy Nguyen Lam, Phu-Hoa Pham, , The Anh Han, Long Tran-Thanh.
• Unlocking Compositional Generalization in Continual Few-Shot Learning. Phu Quy Nguyen Lam, Phu-Hoa Pham, Dao Sy Duy Minh, Tran Chi Nguyen, Trung-Kiet Huynh, Long Tran-Thanh.
• Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery. Tran Chi Nguyen, Dao Sy Duy Minh, Trung-Kiet Huynh, Phu-Hoa Pham, Phu Quy Nguyen Lam, Long Tran-Thanh.
• Weighted Sampling for Online Causal Discovery. , Philips George John, Sayantan Sen, Naganand Yadati.
• When Uncertainty Is the Target: Adversarial Attacks on Uncertainty-Aware Predictors. A. Q. M. Sazzad Sayyed, , Nathaniel D. Bastian, Francesco Restuccia.