AgroBench: Vision-Language Model Benchmark in Agriculture

Precise automated understanding of agricultural tasks such as disease identification is essential for sustainable crop production. Recent advances in vision-language models (VLMs) are expected to further expand the range of agricultural tasks by facilitating human-model interaction through easy, text-based communication. Here, we introduce AgroBench (Agronomist AI Benchmark), a benchmark for evaluating VLM models across seven agricultural topics, covering key areas in agricultural engineering and relevant to real-world farming. Unlike recent agricultural VLM benchmarks, AgroBench is annotated by expert agronomists. Our AgroBench covers a state-of-the-art range of categories, including 203 crop categories and 682 disease categories, to thoroughly evaluate VLM capabilities. In our evaluation on AgroBench, we reveal that VLMs have room for improvement in fine-grained identification tasks. Notably, in weed identification, most open-source VLMs perform close to random. With our wide range of topics and expert-annotated categories, we analyze the types of errors made by VLMs and suggest potential pathways for future VLM development. Our dataset and code are available at https://dahlian00.github.io/AgroBenchPage/ .

Iterative Augmentation with Summarization Refinement (IASR) Evaluation for Unstructured Survey data Modeling and Analysis

Text data augmentation is a widely used strategy for mitigating data sparsity in natural language processing (NLP), particularly in low-resource settings where limited samples hinder effective semantic modeling. While augmentation can improve input diversity and downstream interpretability, existing techniques often lack mechanisms to ensure semantic preservation during large-scale or iterative generation, leading to redundancy and instability. This work introduces a principled evaluation framework for large language model (LLM) based text augmentation, comprising two components: (1) Scalability Analysis, which measures semantic consistency as augmentation volume increases, and (2) Iterative Augmentation with Summarization Refinement (IASR), which evaluates semantic drift across recursive paraphrasing cycles. Empirical evaluations across state-of-the-art LLMs show that GPT-3.5 Turbo achieved the best balance of semantic fidelity, diversity, and generation efficiency. Applied to a real-world topic modeling task using BERTopic with GPT-enhanced few-shot labeling, the proposed approach results in a 400% increase in topic granularity and complete elimination of topic overlaps. These findings validated the utility of the proposed frameworks for structured evaluation of LLM-based augmentation in practical NLP pipelines.

Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds

Reconstructing 3D human bodies from sparse views has been an appealing topic, which is crucial to broader the related applications. In this paper, we propose a quite challenging but valuable task to reconstruct the human body from only two images, i.e., the front and back view, which can largely lower the barrier for users to create their own 3D digital humans. The main challenges lie in the difficulty of building 3D consistency and recovering missing information from the highly sparse input. We redesign a geometry reconstruction model based on foundation reconstruction models to predict consistent point clouds even input images have scarce overlaps with extensive human data training. Furthermore, an enhancement algorithm is applied to supplement the missing color information, and then the complete human point clouds with colors can be obtained, which are directly transformed into 3D Gaussians for better rendering quality. Experiments show that our method can reconstruct the entire human in 190 ms on a single NVIDIA RTX 4090, with two images at a resolution of 1024x1024, demonstrating state-of-the-art performance on the THuman2.0 and cross-domain datasets. Additionally, our method can complete human reconstruction even with images captured by low-cost mobile devices, reducing the requirements for data collection. Demos and code are available at https://hustvl.github.io/Snap-Snap/.

Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume distributionally similar data. This is a significant limitation when detecting and defending against novel potential threats like backdoors, which are by definition out-of-distribution. In this work, we introduce a new method for understanding, monitoring and controlling fine-tuned LLMs that interprets weights, rather than activations, thereby side stepping the need for data that is distributionally similar to the unknown training data. We demonstrate that the top singular vectors of the weight difference between a fine-tuned model and its base model correspond to newly acquired behaviors. By monitoring the cosine similarity of activations along these directions, we can detect salient behaviors introduced during fine-tuning with high precision. For backdoored models that bypasses safety mechanisms when a secret trigger is present, our method stops up to 100% of attacks with a false positive rate below 1.2%. For models that have undergone unlearning, we detect inference on erased topics with accuracy up to 95.42% and can even steer the model to recover "unlearned" information. Besides monitoring, our method also shows potential for pre-deployment model auditing: by analyzing commercial instruction-tuned models (OLMo, Llama, Qwen), we are able to uncover model-specific fine-tuning focus including marketing strategies and Midjourney prompt generation. Our implementation can be found at https://github.com/fjzzq2002/WeightWatch.

Topic Modeling and Link-Prediction for Material Property Discovery

Link prediction infers missing or future relations between graph nodes, based on connection patterns. Scientific literature networks and knowledge graphs are typically large, sparse, and noisy, and often contain missing links between entities. We present an AI-driven hierarchical link prediction framework that integrates matrix factorization to infer hidden associations and steer discovery in complex material domains. Our method combines Hierarchical Nonnegative Matrix Factorization (HNMFk) and Boolean matrix factorization (BNMFk) with automatic model selection, as well as Logistic matrix factorization (LMF), we use to construct a three-level topic tree from a 46,862-document corpus focused on 73 transition-metal dichalcogenides (TMDs). These materials are studied in a variety of physics fields with many current and potential applications. An ensemble BNMFk + LMF approach fuses discrete interpretability with probabilistic scoring. The resulting HNMFk clusters map each material onto coherent topics like superconductivity, energy storage, and tribology. Also, missing or weakly connected links are highlight between topics and materials, suggesting novel hypotheses for cross-disciplinary exploration. We validate our method by removing publications about superconductivity in well-known superconductors, and show the model predicts associations with the superconducting TMD clusters. This shows the method finds hidden connections in a graph of material to latent topic associations built from scientific literature, especially useful when examining a diverse corpus of scientific documents covering the same class of phenomena or materials but originating from distinct communities and perspectives. The inferred links generating new hypotheses, produced by our method, are exposed through an interactive Streamlit dashboard, designed for human-in-the-loop scientific discovery.

SEADialogues: A Multilingual Culturally Grounded Multi-turn Dialogue Dataset on Southeast Asian Languages

Although numerous datasets have been developed to support dialogue systems, most existing chit-chat datasets overlook the cultural nuances inherent in natural human conversations. To address this gap, we introduce SEADialogues, a culturally grounded dialogue dataset centered on Southeast Asia, a region with over 700 million people and immense cultural diversity. Our dataset features dialogues in eight languages from six Southeast Asian countries, many of which are low-resource despite having sizable speaker populations. To enhance cultural relevance and personalization, each dialogue includes persona attributes and two culturally grounded topics that reflect everyday life in the respective communities. Furthermore, we release a multi-turn dialogue dataset to advance research on culturally aware and human-centric large language models, including conversational dialogue agents.

Improving Community Detection in Academic Networks by Handling Publication Bias

Finding potential research collaborators is a challenging task, especially in today's fast-growing and interdisciplinary research landscape. While traditional methods often rely on observable relationships such as co-authorships and citations to construct the research network, in this work, we focus solely on publication content to build a topic-based research network using BERTopic with a fine-tuned SciBERT model that connects and recommends researchers across disciplines based on shared topical interests. A major challenge we address is publication imbalance, where some researchers publish much more than others, often across several topics. Without careful handling, their less frequent interests are hidden under dominant topics, limiting the network's ability to detect their full research scope. To tackle this, we introduce a cloning strategy that clusters a researcher's publications and treats each cluster as a separate node. This allows researchers to be part of multiple communities, improving the detection of interdisciplinary links. Evaluation on the proposed method shows that the cloned network structure leads to more meaningful communities and uncovers a broader set of collaboration opportunities.

Evaluating Podcast Recommendations with Profile-Aware LLM-as-a-Judge

Evaluating personalized recommendations remains a central challenge, especially in long-form audio domains like podcasts, where traditional offline metrics suffer from exposure bias and online methods such as A/B testing are costly and operationally constrained. In this paper, we propose a novel framework that leverages Large Language Models (LLMs) as offline judges to assess the quality of podcast recommendations in a scalable and interpretable manner. Our two-stage profile-aware approach first constructs natural-language user profiles distilled from 90 days of listening history. These profiles summarize both topical interests and behavioral patterns, serving as compact, interpretable representations of user preferences. Rather than prompting the LLM with raw data, we use these profiles to provide high-level, semantically rich context-enabling the LLM to reason more effectively about alignment between a user's interests and recommended episodes. This reduces input complexity and improves interpretability. The LLM is then prompted to deliver fine-grained pointwise and pairwise judgments based on the profile-episode match. In a controlled study with 47 participants, our profile-aware judge matched human judgments with high fidelity and outperformed or matched a variant using raw listening histories. The framework enables efficient, profile-aware evaluation for iterative testing and model selection in recommender systems.

HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways

HealthBranches is a novel benchmark dataset for medical Question-Answering (Q&A), specifically designed to evaluate complex reasoning in Large Language Models (LLMs). This dataset is generated through a semi-automated pipeline that transforms explicit decision pathways from medical source into realistic patient cases with associated questions and answers. Covering 4,063 case studies across 17 healthcare topics, each data point is based on clinically validated reasoning chains. HealthBranches supports both open-ended and multiple-choice question formats and uniquely includes the full reasoning path for each Q&A. Its structured design enables robust evaluation of LLMs' multi-step inference capabilities, including their performance in structured Retrieval-Augmented Generation (RAG) contexts. HealthBranches establishes a foundation for the development of more trustworthy, interpretable, and clinically reliable LLMs in high-stakes domains while also serving as a valuable resource for educational purposes.

Oedipus and the Sphinx: Benchmarking and Improving Visual Language Models for Complex Graphic Reasoning

Evaluating the performance of visual language models (VLMs) in graphic reasoning tasks has become an important research topic. However, VLMs still show obvious deficiencies in simulating human-level graphic reasoning capabilities, especially in complex graphic reasoning and abstract problem solving, which are less studied and existing studies only focus on simple graphics. To evaluate the performance of VLMs in complex graphic reasoning, we propose ReasonBench, the first evaluation benchmark focused on structured graphic reasoning tasks, which includes 1,613 questions from real-world intelligence tests. ReasonBench covers reasoning dimensions related to location, attribute, quantity, and multi-element tasks, providing a comprehensive evaluation of the performance of VLMs in spatial, relational, and abstract reasoning capabilities. We benchmark 11 mainstream VLMs (including closed-source and open-source models) and reveal significant limitations of current models. Based on these findings, we propose a dual optimization strategy: Diagrammatic Reasoning Chain (DiaCoT) enhances the interpretability of reasoning by decomposing layers, and ReasonTune enhances the task adaptability of model reasoning through training, all of which improves VLM performance by 33.5\%. All experimental data and code are in the repository: https://huggingface.co/datasets/cistine/ReasonBench.