Related papers: A Simple and Efficient Implementation of Strong Ca…

Deductive verification of concurrent programs under weak memory has thus far been limited to simple programs over a monolithic state space. For scalabiility, we also require modular techniques with verifiable library abstractions. This…

The pursuit of general-purpose artificial intelligence depends on large language models (LLMs) that can handle both structured reasoning and open-ended generation. We present Omni-Thinker, a unified reinforcement learning (RL) framework…

An ongoing challenge in neural information processing is: how do neurons adjust their connectivity to improve task performance over time (i.e., actualize learning)? It is widely believed that there is a consistent, synaptic-level learning…

In this paper, we propose a Deep Reinforcement Learning (RL) framework for task arrangement, which is a critical problem for the success of crowdsourcing platforms. Previous works conduct the personalized recommendation of tasks to workers…

Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for retrieval at each reasoning step, limiting information…

For those of us who generally live in the world of syntax, semantic proof techniques such as reducibility, realizability or logical relations seem somewhat magical despite -- or perhaps due to -- their seemingly unreasonable effectiveness.…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and…

We propose a novel approach to addressing two fundamental challenges in Model-based Reinforcement Learning (MBRL): the computational expense of repeatedly finding a good policy in the learned model, and the objective mismatch between model…

Hybrid Transformer architectures, which combine softmax attention blocks and recurrent neural networks (RNNs), have shown a desirable performance-throughput tradeoff for long-context modeling, but their adoption and studies are hindered by…

Communication is not only an action of choosing a signal, but needs to consider the context and sensor signals. It also needs to decide what information is communicated and how it is represented in or understood from signals. Therefore,…

In recent years, the notion of local robustness (or robustness for short) has emerged as a desirable property of deep neural networks. Intuitively, robustness means that small perturbations to an input do not cause the network to perform…

Abstract reasoning and logic inference are difficult problems for neural networks, yet essential to their applicability in highly structured domains. In this work we demonstrate that a well known technique such as spectral regularization…

Linear temporal logic (LTL) is a compelling framework for specifying complex, structured tasks for reinforcement learning (RL) agents. Recent work has shown that interpreting LTL instructions as finite automata, which can be seen as…

Explicit planning is a critical capability for LLM-based agents solving complex data-centric tasks, which require precise tool calling over external data sources. Existing strategies fall into two paradigms based on planning horizon: (1)…

Powered by advances in deep learning (DL) techniques, machine learning and artificial intelligence have achieved astonishing successes. However, the rapidly growing needs for DL also led to communication- and resource-intensive distributed…

The primary goal of ad-hoc retrieval (document retrieval in the context of question answering) is to find relevant documents satisfied the information need posted in a natural language query. It requires a good understanding of the query…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Model-based Reinforcement Learning (RL) is a popular learning paradigm due to its potential sample efficiency compared to model-free RL. However, existing empirical model-based RL approaches lack the ability to explore. This work studies a…

Reinforcement learning (RL) is a goal-oriented learning solution that has proven to be successful for Neural Architecture Search (NAS) on the CIFAR and ImageNet datasets. However, a limitation of this approach is its high computational…

Programming languages are expected to support programmer's effort to structure program code. The ML module system, object systems and mixins are good examples of language constructs promoting modular programming. Among the three, mixins can…