13 accepted papers
Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges. Systematic studies reveal pervasive feature splitting that fragments coherent concept…
Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General Time-series Model (GTM), which advances representation learning via a novel frequency-domain attention mechanism that cap…
This paper proposes a variant of multiple-play stochastic bandits tailored to resource allocation problems arising from LLM applications, edge intelligence, etc. The model is composed of finite number of arms and plays. Each arm has a stochastic number of capacities, and each unit of capacity is ass
This paper revisits fairness-aware interactive recommendation (e.g., TikTok, KuaiShou) by introducing a novel control knob, i.e., the lifecycle of items. We make threefold contributions. First, we conduct a comprehensive empirical analysis and uncover that item lifecycles in short-video platforms fo
Large Language Models (LLMs) are increasingly deployed as human assistants across various domains where they help to make choices. However, the mechanisms behind LLMs’ choice behavior remain unclear, posing risks in safety-critical situations. Inspired by the intrinsic and extrinsic motivation frame…
This paper revisits the estimation bias control problem of Q-learning, motivated by the fact that the estimation bias is not always evil, i.e., some environments benefit from overestimation bias or underestimation bias, while others suffer from these biases. Different from previous coarse-grained b…
We study the problem of federated contextual combinatorial cascading bandits, where agents collaborate under the coordination of a central server to provide tailored recommendations to users. Existing works consider either a synchronous framework, necessitating full agent participation and global sy…
LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks. Our research embarks on a quest to uncover the root causes of compositional reasoning failures of LLMs, uncovering that most of them stem from the improperly generated or leveraged implicit reasonin…
Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various important real-world applications, such as search engines and recommender systems. While the ground-truth logging policy is usually unknown, previous work…
This paper proposes a new variant of multi-play MAB model, to capture important factors of the sequential user-centric selection problem arising from mobile edge computing, ridesharing applications, etc. In the proposed model, each arm is associated with discrete units of resources, each play is as…
Multi-player multi-armed bandits (MMAB) study how decentralized players cooperatively play the same multi-armed bandit so as to maximize their total cumulative rewards. Existing MMAB models mostly assume when more than one player pulls the same arm, they either have a collision and obtain zero rewar…
We generalize the multiple-play multi-armed bandits (MP-MAB) problem with a shareable arms setting, in which several plays can share the same arm. Furthermore, each shareable arm has a finite reward capacity and a “per-load” reward distribution, both of which are unknown to the learner. The reward f…
Upper confidence bound (UCB) based contextual bandit algorithms require one to know the tail property of the reward distribution. Unfortunately, such tail property is usually unknown or difficult to specify in real-world applications. Using a tail property heavier than the ground truth leads to a sl…