12 papers
Last-Iterate Guarantees for Online Reinforcement Learning in Structured Constrained MDPs
Nam Phuong Tran, Trinh Ha Mai Huynh, Tuyen Pham Le +3
In safety-critical applications, deployment uses a single policy, whose performance and constraint satisfaction should hold directly rather than only for an average or mixture of t…
Meta-Learning Preferences for Multilingual LLM Alignment
Jiaying Lin, Seongho Son, Nam Phuong Tran +3
Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of suf…
Unlocking Compositional Generalization in Continual Few-Shot Learning
Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dao Sy Duy Minh +3
Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level pa…
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
Chi-Nguyen Tran, Dao Sy Duy Minh, Huynh Trung Kiet +3
Cross-view geo-localization (CVGL), which matches an oblique drone view to a geo-referenced satellite tile, has emerged as a key alternative for autonomous drone navigation when GN…
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
Phu-Hoa Pham, Chi-Nguyen Tran, Nguyen Lam Phu Quy +3
Streaming decision trees are natural candidates for open-world continual learning, as they perform local updates, enjoy bounded memory, and static decision boundaries. Despite thes…
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
Huynh Trung Kiet, Dao Sy Duy Minh, Tuan Nguyen +5
Large language models increasingly mediate decisions that turn on moral judgement, yet a growing body of evidence shows that their implicit preferences are not culturally neutral.…
Extrapolating Volition with Recursive Information Markets
Abhimanyu Pallavi Sudhir, Long Tran-Thanh
One of the impediments to the efficiency of information markets is the inherent information asymmetry present in them, exacerbated by the "buyer's inspection paradox" (the buyer ca…
Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
Tuan Nguyen, Long Tran-Thanh
Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches primarily operate during training,…
Learning in Repeated Multi-Objective Stackelberg Games with Payoff Manipulation
Phurinut Srisawad, Juergen Branke, Long Tran-Thanh
We study payoff manipulation in repeated multi-objective Stackelberg games, where a leader may strategically influence a follower's deterministic best response, e.g., by offering a…
Market-based Architectures in RL and Beyond
Abhimanyu Pallavi Sudhir, Long Tran-Thanh
Market-based agents refer to reinforcement learning agents which determine their actions based on an internal market of sub-agents. We introduce a new type of market-based algorith…
Identifying the Best Arm in the Presence of Global Environment Shifts
Phurinut Srisawad, Juergen Branke, Long Tran-Thanh
This paper formulates a new Best-Arm Identification problem in the non-stationary stochastic bandits setting, where the means of all arms are shifted in the same way due to a globa…
Betting on what is neither verifiable nor falsifiable
Abhimanyu Pallavi Sudhir, Long Tran-Thanh
Prediction markets are useful for estimating probabilities of claims whose truth will be revealed at some fixed time -- this includes questions about the values of real-world event…