Related papers: Single Time-Stamped Tries for Retroactive Call Sub…

Tabling has been used for some time to improve efficiency of Prolog programs by memorizing answered queries. The same idea can be naturally used to memorize visited states during search for planning. In this paper we present a planner…

The next location recommendation is at the core of various location-based applications. Current state-of-the-art models have attempted to solve spatial sparsity with hierarchical gridding and model temporal relation with explicit time…

We introduce STRIVE (SpatioTemporal Reinforcement with Importance-aware Variant Exploration), a structured reinforcement learning framework for video question answering. While group-based policy optimization methods have shown promise in…

Despite recent successes, test-time scaling - i.e., dynamically expanding the token budget during inference as needed - remains brittle for vision-language models (VLMs): unstructured chains-of-thought about images entangle perception and…

Train timetable rescheduling (TTR) aims to promptly restore the original operation of trains after unexpected disturbances or disruptions. Currently, this work is still done manually by train dispatchers, which is challenging to maintain…

Generative retrieval has emerged as a powerful paradigm for LLM-based recommendation. However, industrial recommender systems often benefit from restricting the output space to a constrained subset of items based on business logic (e.g.…

Structured tabular data is a fundamental data type in numerous fields, and the capacity to reason over tables is crucial for answering questions and validating hypotheses. However, constructing labeled data for complex reasoning tasks is…

Test-time adaptation offers a promising avenue for improving reasoning performance in large language models without additional supervision, but existing approaches often apply a uniform optimization objective across all inputs, leading to…

Spiking Transformers have recently emerged as promising architectures for combining the efficiency of spiking neural networks with the representational power of self-attention. However, the lack of standardized implementations, evaluation…

Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN models, the backpropagation through time (BPTT) with surrogate gradients (SG) method has achieved high…

This paper presents a critical discussion of popular approaches to ensure the Liskov substitution principle in class hierarchies (e.g. Design by Contract(TM), specification inheritance). It will be shown that they have some deficiencies…

Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past frames. Traditional methods, which use recurrent neural…

Test-time scaling improves language model reasoning by spending additional compute to explore multiple solution trajectories. The key challenge is to maximize accuracy while minimizing the total number of generated tokens during reasoning.…

Signal temporal logic (STL) provides a user-friendly interface for defining complex tasks for robotic systems. Recent efforts aim at designing control laws or using reinforcement learning methods to find policies which guarantee…

Traffic prediction is a cornerstone of modern intelligent transportation systems and a critical task in spatio-temporal forecasting. Although advanced Spatio-temporal Graph Neural Networks (STGNNs) and pre-trained models have achieved…

While Transformer architectures have demonstrated impressive scalability across domains, they continue to face challenges in long-context reasoning, computational efficiency, and structural generalization - largely due to rigid layer…

Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective…

Logic programming with tabling and constraints (TCLP, tabled constraint logic programming) has been shown to be more expressive and in some cases more efficient than LP, CLP or LP + tabling. Previous designs of TCLP systems did not fully…

We propose a new iterative greedy algorithm for reconstructions of sparse signals with or without noisy perturbations in compressed sensing. The proposed algorithm, called \emph{subspace thresholding pursuit} (STP) in this paper, is a…

Self-taught reasoners (STaRs) enhance the mathematical reasoning abilities of large language models (LLMs) by leveraging self-generated responses for self-training. Recent studies have incorporated reward models to guide response selection…