相关论文: An Innovative Data-Driven and Adaptive Reinforceme…

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a…

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to understand video content remains constrained by suboptimal frame selection strategies. Existing approaches often rely on…

Recent pre-trained vision-language models (PT-VLMs) often face a Multi-Domain Task Incremental Learning (MTIL) scenario in practice, where several classes and domains of multi-modal tasks are incrementally arrived. Without access to…

We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient descent) to quickly solve parametric convex optimization…

Generative recommendation has recently emerged as a promising paradigm for sequential recommendation. It formulates the task as an autoregressive generation process, predicting tokens of the next item conditioned on user interaction…

LLM agents that store knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial…

Agentic systems operating over large tool ecosystems must plan and execute long-horizon workflows under weak or non-verifiable supervision. While frontier models mitigate these challenges through scale and large context budgets, small…

Pre-trained vision-language-action (VLA) models offer a promising foundation for generalist robot policies, but often produce brittle behaviors or unsafe failures when deployed zero-shot in out-of-distribution scenarios. We present…

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Prescriptive Process Monitoring is a prominent problem in Process Mining, which consists in identifying a set of actions to be recommended with the goal of optimising a target measure of interest or Key Performance Indicator (KPI). One…

Data preparation is a foundational yet notoriously challenging component of the machine learning lifecycle, characterized by a vast combinatorial search space. While reinforcement learning (RL) offers a promising direction, state-of-the-art…

This study presents an Exploratory Retrieval-Augmented Planning (ExRAP) framework, designed to tackle continual instruction following tasks of embodied agents in dynamic, non-stationary environments. The framework enhances Large Language…

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters. While large language models have demonstrated this ability, how…

In recent years, several frameworks and systems have been proposed that extend Inductive Logic Programming (ILP) to the Answer Set Programming (ASP) paradigm. In ILP, examples must all be explained by a hypothesis together with a given…

Previous studies have used prescriptive process monitoring to find actionable policies in business processes and conducted case studies in similar domains, such as the loan application process and the traffic fine process. However, care…

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…

With the widespread deployment of deep learning models, they influence their environment in various ways. The induced distribution shifts can lead to unexpected performance degradation in deployed models. Existing methods to anticipate…

Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often persists after unlearning. Existing adversarial approaches…