Multimodal Large Language Model (MLLM) have demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve performance on specific downstream tasks. However, during fine-tuning, MLLM often faces the risk of forgetting knowledge acquired during pre-training, which can result in a decline in generalization abilities. To balance the trade-off between generalization and specialization, we propose measuring the parameter importance for both pre-trained and fine-tuning distributions, based on frozen pre-trained weight magnitude and accumulated fine-tuning gradient values. We further apply an importance-aware weight allocation strategy, selectively updating relatively important parameters for downstream tasks. We conduct empirical evaluations on both image captioning and visual question-answering tasks using various MLLM architectures. The comprehensive experimental analysis demonstrates the effectiveness of the proposed solution, highlighting the efficiency of the crucial modules in enhancing downstream specialization performance while mitigating generalization degradation in MLLM Fine-Tuning.

Satirical news is real news combined with a humorous comment or exaggerated content, and it often mimics the format and style of real news. However, satirical news is often misunderstood as misinformation, especially by individuals from different cultural and social backgrounds. This research addresses the challenge of distinguishing satire from truthful news by leveraging multilingual satire detection methods in English and Arabic. We explore both zero-shot and chain-of-thought (CoT) prompting using two language models, Jais-chat(13B) and LLaMA-2-chat(7B). Our results show that CoT prompting offers a significant advantage for the Jais-chat model over the LLaMA-2-chat model. Specifically, Jais-chat achieved the best performance, with an F1-score of 80\% in English when using CoT prompting. These results highlight the importance of structured reasoning in CoT, which enhances contextual understanding and is vital for complex tasks like satire detection.

Recent studies suggest large language models (LLMs) can exhibit human-like reasoning, aligning with human behavior in economic experiments, surveys, and political discourse. This has led many to propose that LLMs can be used as surrogates or simulations for humans in social science research. However, LLMs differ fundamentally from humans, relying on probabilistic patterns, absent the embodied experiences or survival objectives that shape human cognition. We assess the reasoning depth of LLMs using the 11-20 money request game. Nearly all advanced approaches fail to replicate human behavior distributions across many models. Causes of failure are diverse and unpredictable, relating to input language, roles, and safeguarding. These results advise caution when using LLMs to study human behavior or as surrogates or simulations. 'She has twelve misshapen feet, and six necks of the most prodigious length; and at the end of each neck she has a frightful head with three rows of teeth ...

Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax attention in Transformer structures. However, the optimal design of these linear models is still an open question. In this work, we attempt to answer this question by finding the best linear approximation to softmax attention from a theoretical perspective. We start by unifying existing linear complexity models as the linear attention form and then identify three conditions for the optimal linear attention design: i) Dynamic memory ability; ii) Static approximation ability; iii) Least parameter approximation. We find that none of the current linear models meet all three conditions, resulting in suboptimal performance. Instead, we propose Meta Linear Attention (MetaLA) as a solution that satisfies these conditions. Our experiments on Multi-Query Associative Recall (MQAR) task, language modeling, image classification, and Long-Range Arena (LRA) benchmark demonstrate that MetaLA is more effective than the existing linear models.

Comprehensively understanding surgical scenes in Surgical Visual Question Answering (Surgical VQA) requires reasoning over multiple objects. Previous approaches address this task using cross-modal fusion strategies to enhance reasoning ability. However, these methods often struggle with limited scene understanding and question comprehension, and some rely on external resources (e.g., pre-extracted object features), which can introduce errors and generalize poorly across diverse surgical environments. To address these challenges, we propose SCAN, a simple yet effective memory-augmented framework that leverages Multimodal LLMs to improve surgical context comprehension via Self-Contained Inquiry. SCAN operates autonomously, generating two types of memory for context augmentation: Direct Memory (DM), which provides multiple candidates (or hints) to the final answer, and Indirect Memory (IM), which consists of self-contained question-hint pairs to capture broader scene context. DM directly assists in answering the question, while IM enhances understanding of the surgical scene beyond the immediate query. Reasoning over these object-aware memories enables the model to accurately interpret images and respond to questions. Extensive experiments on three publicly available Surgical VQA datasets demonstrate that SCAN achieves state-of-the-art performance, offering improved accuracy and robustness across various surgical scenarios.

Large Language Models (LLMs) have shown significant potential in understanding human communication and interaction. However, their performance in the domain of child-inclusive interactions, including in clinical settings, remains less explored. In this work, we evaluate generic LLMs' ability to analyze child-adult dyadic interactions in a clinically relevant context involving children with ASD. Specifically, we explore LLMs in performing four tasks: classifying child-adult utterances, predicting engaged activities, recognizing language skills and understanding traits that are clinically relevant. Our evaluation shows that generic LLMs are highly capable of analyzing long and complex conversations in clinical observation sessions, often surpassing the performance of non-expert human evaluators. The results show their potential to segment interactions of interest, assist in language skills evaluation, identify engaged activities, and offer clinical-relevant context for assessments.

With the rapid growth of interdisciplinary demands for geospatial modeling and the rise of large language models (LLMs), geospatial code generation technology has seen significant advancements. However, existing LLMs often face challenges in the geospatial code generation process due to incomplete or unclear user requirements and insufficient knowledge of specific platform syntax rules, leading to the generation of non-executable code, a phenomenon known as "code hallucination." To address this issue, this paper proposes a Chain of Programming (CoP) framework, which decomposes the code generation process into five steps: requirement analysis, algorithm design, code implementation, code debugging, and code annotation. The framework incorporates a shared information pool, knowledge base retrieval, and user feedback mechanisms, forming an end-to-end code generation flow from requirements to code, without the need for model fine-tuning. Based on a geospatial problem classification framework and evaluation benchmarks, the CoP strategy significantly improves the logical clarity, syntactical correctness, and executability of the generated code, with improvements ranging from 3.0% to 48.8%. Comparative and ablation experiments further validate the superiority of the CoP strategy over other optimization approaches and confirm the rationality and necessity of its key components. Through case studies on building data visualization and fire data analysis, this paper demonstrates the application and effectiveness of CoP in various geospatial scenarios. The CoP framework offers a systematic, step-by-step approach to LLM-based geospatial code generation tasks, significantly enhancing code generation performance in geospatial tasks and providing valuable insights for code generation in other vertical domains.

In the endeavor to make autonomous robots take actions, task planning is a major challenge that requires translating high-level task descriptions into long-horizon action sequences. Despite recent advances in language model agents, they remain prone to planning errors and limited in their ability to plan ahead. To address these limitations in robotic planning, we advocate a self-refining scheme that iteratively refines a draft plan until an equilibrium is reached. Remarkably, this process can be optimized end-to-end from an analytical perspective without the need to curate additional verifiers or reward models, allowing us to train self-refining planners in a simple supervised learning fashion. Meanwhile, a nested equilibrium sequence modeling procedure is devised for efficient closed-loop planning that incorporates useful feedback from the environment (or an internal world model). Our method is evaluated on the VirtualHome-Env benchmark, showing advanced performance with better scaling for inference computation. Based on their extensive world knowledge, LLM agents seem close to autonomously performing robotic tasks, such as in household scenarios. However, growing evidence shows that existing LLM agents struggle with task planning (Kaelbling & Lozano-Pérez, 2011) that decomposes a high-level task into mid-level actions. While this problem requires long-horizon planning as well as consideration of environmental feedback, LLMs are often limited by: (1) unidirectional dependency: due to autoregressive generation, previous tokens cannot attend to future tokens, resulting in limited ability to plan ahead (Wu et al., 2024a); (2) lack of error correction for existing outputs, unless with a heavy system 2; (3) fixed forward process hindering the allocation of more inference computation to further improve planning performance. These inherent limitations of LLMs lead to inefficiency in the closed-loop long-horizon robotic planning. To address above challenges of LLM planners in closed-loop long-horizon planning, we advocate the approach of self-refinement (Welleck et al., 2023; Shinn et al., 2023; Kim et al., 2023; Madaan et al., 2023) that iteratively improves a previously generated plan. The reasons behind are threefold: (1) bidirectional dependency: since the output is conditioned on a previous draft plan, it can attend to all tokens in the plan (from an old version), thus improving its ability to plan ahead; (2) internal error correction which allows implicit self-correction in a forward pass without an explicit, heavy system 2; (3) dynamic computation allocation by iterating through a self-refinement process until convergence.

Education is poised for a transformative shift with the advent of neurosymbolic artificial intelligence (NAI), which will redefine how we support deeply adaptive and personalized learning experiences. NAI-powered education systems will be capable of interpreting complex human concepts and contexts while employing advanced problem-solving strategies, all grounded in established pedagogical frameworks. This will enable a level of personalization in learning systems that to date has been largely unattainable at scale, providing finely tailored curricula that adapt to an individual's learning pace and accessibility needs, including the diagnosis of student understanding of subjects at a fine-grained level, identifying gaps in foundational knowledge, and adjusting instruction accordingly. In this paper, we propose a system that leverages the unique affordances of pedagogical agents -- embodied characters designed to enhance learning -- as critical components of a hybrid NAI architecture. To do so, these agents can thus simulate nuanced discussions, debates, and problem-solving exercises that push learners beyond rote memorization toward deep comprehension. We discuss the rationale for our system design and the preliminary findings of our work. We conclude that education in the era of NAI will make learning more accessible, equitable, and aligned with real-world skills. This is an era that will explore a new depth of understanding in educational tools.

This report presents a comparative analysis of open-source vulnerability scanners for conversational large language models (LLMs). As LLMs become integral to various applications, they also present potential attack surfaces, exposed to security risks such as information leakage and jailbreak attacks. Our study evaluates prominent scanners - Garak, Giskard, PyRIT, and CyberSecEval - that adapt red-teaming practices to expose these vulnerabilities. We detail the distinctive features and practical use of these scanners, outline unifying principles of their design and perform quantitative evaluations to compare them. These evaluations uncover significant reliability issues in detecting successful attacks, highlighting a fundamental gap for future development. Additionally, we contribute a preliminary labelled dataset, which serves as an initial step to bridge this gap. Based on the above, we provide strategic recommendations to assist organizations choose the most suitable scanner for their red-teaming needs, accounting for customizability, test suite comprehensiveness, and industry-specific use cases.