Existing methods like ensemble still struggle to aggregate these models with the desired higher-order communications. In this work, we propose Cola, a novel paradigm that coordinates multiple VLMs for visual reasoning.

What's happening in Myanmar's civil war as military holds elections? Voters in parts of Myanmar are heading to the polls on Sunday for an election that critics view as a bid by the country's generals to legitimise military rule, nearly five years after they overthrew the government of Nobel Laureate Aung San Suu Kyi. The multi-phased election is unfolding amid a raging civil war, with ethnic armed groups and opposition militias fighting the military for control of vast stretches of territory, stretching from the borderlands with Bangladesh and India in the west, across the central plains, to the frontiers with China and Thailand in the north and east. Another third will be covered during a second and third phase in January, while voting has been cancelled altogether in the remainder. Fighting, including air raids and arson, has intensified in several areas.

Existing methods like ensemble still struggle to aggregate these models with the desired higher-order communications. In this work, we propose Cola, a novel paradigm that coordinates multiple VLMs for visual reasoning.

Large language models (LLMs) often struggle to perform multi-target reasoning in long-context scenarios where relevant information is scattered across extensive documents. To address this challenge, we introduce NeuroSymbolic Augmented Reasoning (NSAR), which combines the benefits of neural and symbolic reasoning during inference. NSAR explicitly extracts symbolic facts from text and generates executable Python code to handle complex reasoning steps. Through extensive experiments across seven languages and diverse context lengths, we demonstrate that NSAR significantly outperforms both a vanilla RAG baseline and advanced prompting strategies in accurately identifying and synthesizing multiple pieces of information. Our results highlight the effectiveness of combining explicit symbolic operations with neural inference for robust, interpretable, and scalable reasoning in multilingual settings.

Recommender systems (RecSys) are widely used across various modern digital platforms and have garnered significant attention. Traditional recommender systems usually focus only on fixed and simple recommendation scenarios, making it difficult to generalize to new and unseen recommendation tasks in an interactive paradigm. Recently, the advancement of large language models (LLMs) has revolutionized the foundational architecture of RecSys, driving their evolution into more intelligent and interactive personalized recommendation assistants. However, most existing studies rely on fixed task-specific prompt templates to generate recommendations and evaluate the performance of personalized assistants, which limits the comprehensive assessments of their capabilities. This is because commonly used datasets lack high-quality textual user queries that reflect real-world recommendation scenarios, making them unsuitable for evaluating LLM-based personalized recommendation assistants. To address this gap, we introduce RecBench+, a new dataset benchmark designed to access LLMs' ability to handle intricate user recommendation needs in the era of LLMs. RecBench+ encompasses a diverse set of queries that span both hard conditions and soft preferences, with varying difficulty levels. We evaluated commonly used LLMs on RecBench+ and uncovered below findings: 1) LLMs demonstrate preliminary abilities to act as recommendation assistants, 2) LLMs are better at handling queries with explicitly stated conditions, while facing challenges with queries that require reasoning or contain misleading information. Our dataset has been released at https://github.com/jiani-huang/RecBench.git.

Automatic Speech Recognition (ASR) technology has witnessed significant advancements in recent years, revolutionizing human-computer interactions. While major languages have benefited from these developments, lesser-resourced languages like Urdu face unique challenges. This paper provides an extensive exploration of the dynamic landscape of ASR research, focusing particularly on the resource-constrained Urdu language, which is widely spoken across South Asian nations. It outlines current research trends, technological advancements, and potential directions for future studies in Urdu ASR, aiming to pave the way for forthcoming researchers interested in this domain. By leveraging contemporary technologies, analyzing existing datasets, and evaluating effective algorithms and tools, the paper seeks to shed light on the unique challenges and opportunities associated with Urdu language processing and its integration into the broader field of speech research.

Machine translation systems for high resource languages perform exceptionally well and produce high quality translations. Unfortunately, the vast majority of languages are not considered high resource and lack the quantity of parallel sentences needed to train such systems. These under-represented languages are not without resources, however, and bilingual dictionaries and grammar books are available as linguistic reference material. With current large language models (LLMs) supporting near book-length contexts, we can begin to use the available material to ensure advancements are shared among all of the world's languages. In this paper, we demonstrate incorporating grammar books in the prompt of GPT-4 to improve machine translation and evaluate the performance on 16 topologically diverse low-resource languages, using a combination of reference material to show that the machine translation performance of LLMs can be improved using this method.

Building-specific knowledge such as building type and function information is important for numerous energy applications. However, comprehensive datasets containing this information for individual households are missing in many regions of Europe. For the first time, we investigate whether it is feasible to predict building types and functional classes at a European scale based on only open GIS datasets available across countries. We train a graph neural network (GNN) classifier on a large-scale graph dataset consisting of OpenStreetMap (OSM) buildings across the EU, Norway, Switzerland, and the UK. To efficiently perform training using the large-scale graph, we utilize localized subgraphs. A graph transformer model achieves a high Cohen's kappa coefficient of 0.754 when classifying buildings into 9 classes, and a very high Cohen's kappa coefficient of 0.844 when classifying buildings into the residential and non-residential classes. The experimental results imply three core novel contributions to literature. Firstly, we show that building classification across multiple countries is possible using a multi-source dataset consisting of information about 2D building shape, land use, degree of urbanization, and countries as input, and OSM tags as ground truth. Secondly, our results indicate that GNN models that consider contextual information about building neighborhoods improve predictive performance compared to models that only consider individual buildings and ignore the neighborhood. Thirdly, we show that training with GNNs on localized subgraphs instead of standard GNNs improves performance for the task of building classification.

Vision-language models (VLMs) like CLIP have been adapted for Multi-Label Recognition (MLR) with partial annotations by leveraging prompt-learning, where positive and negative prompts are learned for each class to associate their embeddings with class presence or absence in the shared vision-text feature space. While this approach improves MLR performance by relying on VLM priors, we hypothesize that learning negative prompts may be suboptimal, as the datasets used to train VLMs lack image-caption pairs explicitly focusing on class absence. To analyze the impact of positive and negative prompt learning on MLR, we introduce PositiveCoOp and NegativeCoOp, where only one prompt is learned with VLM guidance while the other is replaced by an embedding vector learned directly in the shared feature space without relying on the text encoder. Through empirical analysis, we observe that negative prompts degrade MLR performance, and learning only positive prompts, combined with learned negative embeddings (PositiveCoOp), outperforms dual prompt learning approaches. Moreover, we quantify the performance benefits that prompt-learning offers over a simple vision-features-only baseline, observing that the baseline displays strong performance comparable to dual prompt learning approach (DualCoOp), when the proportion of missing labels is low, while requiring half the training compute and 16 times fewer parameters

In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen our understanding of how this ability is acquired at the training stage. However, existing evaluation frameworks primarily focus on language abilities and knowledge, often overlooking the assessment of ICL ability. In this work, we introduce the ICLEval benchmark to evaluate the ICL abilities of LLMs, which encompasses two key sub-abilities: exact copying and rule learning. Through the ICLEval benchmark, we demonstrate that ICL ability is universally present in different LLMs, and model size is not the sole determinant of ICL efficacy. Surprisingly, we observe that ICL abilities, particularly copying, develop early in the pretraining process and stabilize afterward. Our source codes and benchmark are released at https://github.com/yiye3/ICLEval.