We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.

Large Language Models (LLMs) have shown strong general capabilities in many applications. However, how to make them reliable tools for some specific tasks such as automated short answer grading (ASAG) remains a challenge. We present SteLLA (Structured Grading System Using LLMs with RAG) in which a) Retrieval Augmented Generation (RAG) approach is used to empower LLMs specifically on the ASAG task by extracting structured information from the highly relevant and reliable external knowledge based on the instructor-provided reference answer and rubric, b) an LLM performs a structured and question-answering-based evaluation of student answers to provide analytical grades and feedback. A real-world dataset that contains students' answers in an exam was collected from a college-level Biology course. Experiments show that our proposed system can achieve substantial agreement with the human grader while providing break-down grades and feedback on all the knowledge points examined in the problem. A qualitative and error analysis of the feedback generated by GPT4 shows that GPT4 is good at capturing facts while may be prone to inferring too much implication from the given text in the grading task which provides insights into the usage of LLMs in the ASAG system.

Word sense disambiguation (WSD) is one of the main challenges in Computational Linguistics. TreeMatch is a WSD system originally developed using data from SemEval 2007 Task 7 (Coarse-grained English All-words Task) that has been adapted for use in SemEval 2010 Task 17 (All-words Word Sense Disambiguation on a Specific Domain). The system is based on a fully unsupervised method using dependency knowledge drawn from a domain specific knowledge base that was built for this task. When evaluated on the task, the system precision performs above the Most Frequent Selection baseline.

We propose AToM-Bot, a novel task generation and execution framework for proactive robot-human interaction, which leverages the human mental and physical state inference capabilities of the Vision Language Model (VLM) prompted by the Affective Theory of Mind (AToM). Without requiring explicit commands by humans, AToM-Bot proactively generates and follows feasible tasks to improve general human well-being. When around humans, AToM-Bot first detects current human needs based on inferred human states and observations of the surrounding environment. It then generates tasks to fulfill these needs, taking into account its embodied constraints. We designed 16 daily life scenarios spanning 4 common scenes and tasked the same visual stimulus to 59 human subjects and our robot. We used the similarity between human open-ended answers and robot output, and the human satisfaction scores to metric robot performance. AToM-Bot received high human evaluations in need detection (6.42/7, 91.7%), embodied solution (6.15/7, 87.8%) and task execution (6.17/7, 88.1%). We show that AToM-Bot excels in generating and executing feasible plans to fulfill unspoken human needs. Videos and code are available at https://affective-tom-bot.github.io.

Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases. Drawing an analogy to the human psyche's conflict between evolutionary survival instincts and societal norm adherence elucidated in Freud's psychoanalysis theory, we argue that LLMs suffer a similar fundamental conflict, arising between their inherent desire for syntactic and semantic continuity, established during the pre-training phase, and the post-training alignment with human values. This conflict renders LLMs vulnerable to adversarial attacks, wherein intensifying the models' desire for continuity can circumvent alignment efforts, resulting in the generation of harmful information. Through a series of experiments, we first validated the existence of the desire for continuity in LLMs, and further devised a straightforward yet powerful technique, such as incomplete sentences, negative priming, and cognitive dissonance scenarios, to demonstrate that even advanced LLMs struggle to prevent the generation of harmful information. In summary, our study uncovers the root of LLMs' vulnerabilities to adversarial attacks, hereby questioning the efficacy of solely relying on sophisticated alignment methods, and further advocates for a new training idea that integrates modal concepts alongside traditional amodal concepts, aiming to endow LLMs with a more nuanced understanding of real-world contexts and ethical considerations.

Support-query shift few-shot learning aims to classify unseen examples (query set) to labeled data (support set) based on the learned embedding in a low-dimensional space under a distribution shift between the support set and the query set. However, in real-world scenarios the shifts are usually unknown and varied, making it difficult to estimate in advance. Therefore, in this paper, we propose a novel but more difficult challenge, RSQS, focusing on Realistic Support-Query Shift few-shot learning. The key feature of RSQS is that the individual samples in a meta-task are subjected to multiple distribution shifts in each meta-task. In addition, we propose a unified adversarial feature alignment method called DUal adversarial ALignment framework (DuaL) to relieve RSQS from two aspects, i.e., inter-domain bias and intra-domain variance. On the one hand, for the inter-domain bias, we corrupt the original data in advance and use the synthesized perturbed inputs to train the repairer network by minimizing distance in the feature level. On the other hand, for intra-domain variance, we proposed a generator network to synthesize hard, i.e., less similar, examples from the support set in a self-supervised manner and introduce regularized optimal transportation to derive a smooth optimal transportation plan. Lastly, a benchmark of RSQS is built with several state-of-the-art baselines among three datasets (CIFAR100, mini-ImageNet, and Tiered-Imagenet). Experiment results show that DuaL significantly outperforms the state-of-the-art methods in our benchmark.

A household robot should be able to navigate to target objects without requiring users to first annotate everything in their home. Most current approaches to object navigation do not test on real robots and rely solely on reconstructed scans of houses and their expensively labeled semantic 3D meshes. In this work, our goal is to build an agent that builds self-supervised models of the world via exploration, the same as a child might - thus we (1) eschew the expense of labeled 3D mesh and (2) enable self-supervised in-situ finetuning in the real world. We identify a strong source of self-supervision (Location Consistency - LocCon) that can train all components of an ObjectNav agent, using unannotated simulated houses. Our key insight is that embodied agents can leverage location consistency as a self-supervision signal - collecting images from different views/angles and applying contrastive learning. We show that our agent can perform competitively in the real world and simulation. Our results also indicate that supervised training with 3D mesh annotations causes models to learn simulation artifacts, which are not transferrable to the real world. In contrast, our LocCon shows the most robust transfer in the real world among the set of models we compare to, and that the real-world performance of all models can be further improved with self-supervised LocCon in-situ training.

Generalized Category Discovery (GCD) aims to recognize both known and novel categories from a set of unlabeled data, based on another dataset labeled with only known categories. Without considering differences between known and novel categories, current methods learn about them in a coupled manner, which can hurt model's generalization and discriminative ability. Furthermore, the coupled training approach prevents these models transferring category-specific knowledge explicitly from labeled data to unlabeled data, which can lose high-level semantic information and impair model performance. To mitigate above limitations, we present a novel model called Decoupled Prototypical Network (DPN). By formulating a bipartite matching problem for category prototypes, DPN can not only decouple known and novel categories to achieve different training targets effectively, but also align known categories in labeled and unlabeled data to transfer category-specific knowledge explicitly and capture high-level semantics. Furthermore, DPN can learn more discriminative features for both known and novel categories through our proposed Semantic-aware Prototypical Learning (SPL). Besides capturing meaningful semantic information, SPL can also alleviate the noise of hard pseudo labels through semantic-weighted soft assignment. Extensive experiments show that DPN outperforms state-of-the-art models by a large margin on all evaluation metrics across multiple benchmark datasets. Code and data are available at https://github.com/Lackel/DPN.

Currently, a growing number of mature natural language processing applications make people's life more convenient. Such applications are built by source code - the language in software engineering. However, the applications for understanding source code language to ease the software engineering process are under-researched. Simultaneously, the transformer model, especially its combination with transfer learning, has been proven to be a powerful technique for natural language processing tasks. These breakthroughs point out a promising direction for process source code and crack software engineering tasks. This paper describes CodeTrans - an encoder-decoder transformer model for tasks in the software engineering domain, that explores the effectiveness of encoder-decoder transformer models for six software engineering tasks, including thirteen sub-tasks. Moreover, we have investigated the effect of different training strategies, including single-task learning, transfer learning, multi-task learning, and multi-task learning with fine-tuning. CodeTrans outperforms the state-of-the-art models on all the tasks. To expedite future works in the software engineering domain, we have published our pre-trained models of CodeTrans. https://github.com/agemagician/CodeTrans

Many Natural Language Processing and Computational Linguistics applications involve the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a serious problem haunting these applications for decades, that is, how to automatically and accurately assess quality of these applications. In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation---how to pinpoint content differences of two text passages (especially for large passages such as articles and books). Our idea is intuitive and very different from existing approaches. We treat one text passage as a small knowledge base, and ask it a large number of questions to exhaustively identify all content points in it. By comparing the correctly answered questions from two text passages, we will be able to compare their content precisely. The experiment using 2007 DUC summarization corpus clearly shows promising results.