--Machine learning for robotics promises to unlock generalization to novel tasks and environments. Guided by this promise, many recent works have focused on scaling up robot data collection and developing larger, more expressive policies to achieve this. But how do we measure progress towards this goal of policy generalization in practice? Evaluating and quantifying generalization is the Wild West of modern robotics, with each work proposing and measuring different types of generalization in their own, often difficult to reproduce, settings. In this work, our goal is (1) to outline the forms of generalization we believe are important in robot manipulation in a comprehensive and fine-grained manner, and (2) to provide reproducible guidelines for measuring these notions of generalization. We first propose - Gen, a taxonomy of generalization for robot manipulation structured around visual, semantic, and behavioral generalization. We discuss how our taxonomy encompasses most prior notions of generalization in robotics. Next, we instantiate -Gen with a concrete real-world benchmark based on the widely-used Bridge V2 dataset. We evaluate a variety of state-of-the-art models on this benchmark to demonstrate the utility of our taxonomy in practice. Our taxonomy of generalization can yield many interesting insights into existing models: for example, we observe that current vision-language-action models struggle with various types of semantic generalization, despite the promise of pre-training on internet-scale language datasets. We believe -Gen and our guidelines can improve the dissemination and evaluation of progress towards generalization in robotics, which we hope will guide model design and future data collection efforts. We provide videos and demos at our website stargen-taxonomy.github.io. Learning-based robotics often comes with the promise of generalization. As an example, an ambitious goal is to train a policy on diverse household data so it can enter a new home and fold laundry. This vision has led to many recent works that train robot policies on diverse datasets via imitation learning [1-13] with the hope of broad generalization. For example, if a robot encounters an unseen item of clothing in a new home, it should infer how to fold it using its extensive prior experience. However, in contrast to other domains like language and vision, we have yet to reach a point in robotics where policies can reliably generalize in this manner. In pursuit of reliable and broad generalization, recent work has focused on scaling up data collection [2-4, 14-20] and developing more expressive models [3, 7-13], following the successes of other machine learning fields. Although these advances have led to more capable policies that certainly generalize to some novel scenarios, it is often unclear from existing evaluations how generalist these policies truly are.

Multi-terrain cost-efficient path planning is a crucial task in robot navigation, requiring the identification of a path from the start to the goal that not only avoids obstacles but also minimizes travel costs. This is especially crucial for real-world applications where robots need to navigate diverse terrains in outdoor environments, where recharging or refueling is difficult. However, there is very limited research on this topic. In this paper, we develop a prompt-based approach, LLM-Advisor, which leverages large language models (LLMs) as effective advisors for path planning. The LLM-Advisor selectively provides suggestions, demonstrating its ability to recognize when no modifications are necessary. When suggestions are made, 70.59% of the paths suggested for the A* algorithm, 69.47% for the RRT* algorithm, and 78.70% for the LLM-A* algorithm achieve greater cost efficiency. Since LLM-Advisor may occasionally lack common sense in their suggestions, we propose two hallucination-mitigation strategies. Furthermore, we experimentally verified that GPT-4o performs poorly in zero-shot path planning, even when terrain descriptions are clearly provided, demonstrating its low spatial awareness. We also experimentally demonstrate that using an LLM as an advisor is more effective than directly integrating it into the path-planning loop. Since LLMs may generate hallucinations, using LLMs in the loop of a search-based method (such as A*) may lead to a higher number of failed paths, demonstrating that our proposed LLM-Advisor is a better choice.

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), face notable limitations: RLHF suffers from instability and inefficiency in multi-objective optimization, while DPO lacks mechanisms for dynamic trade-offs. To address these challenges, we propose Post-Training Extrapolation Optimization (PEO), a novel and efficient framework for bi-factorial alignment. PEO generates a family of Pareto-optimal policies in a single training pass by leveraging a three-phase pipeline: (1) aspect-specific learning, (2) generalist initialization via interpolation, and (3) post-training optimization via extrapolation. PEO enables dynamic adaptation to diverse user preferences at inference time without retraining. Our comprehensive experiments across multiple LLMs demonstrate that PEO achieves superior Pareto fronts compared to baselines, offering improved flexibility and computational efficiency. Theoretical analyses further highlight PEO's capacity to overcome optimization bottlenecks, paving the way for scalable, personalized alignment.

Dementia, a progressive neurodegenerative disorder, affects memory, reasoning, and daily functioning, creating challenges for individuals and healthcare systems. Early detection is crucial for timely interventions that may slow disease progression. Large pre-trained models (LPMs) for text and audio, such as Generative Pre-trained Transformer (GPT), Bidirectional Encoder Representations from Transformers (BERT), and Contrastive Language-Audio Pretraining (CLAP), have shown promise in identifying cognitive impairments. However, existing studies generally rely heavily on expert-annotated datasets and unimodal approaches, limiting robustness and scalability. This study proposes a context-based multimodal method, integrating both text and audio data using the best-performing LPMs in each modality. By incorporating contextual embeddings, our method improves dementia detection performance. Additionally, motivated by the effectiveness of contextual embeddings, we further experimented with a context-based In-Context Learning (ICL) as a complementary technique. Results show that GPT-based embeddings, particularly when fused with CLAP audio features, achieve an F1-score of $83.33\%$, surpassing state-of-the-art dementia detection models. Furthermore, raw text data outperforms expert-annotated datasets, demonstrating that LPMs can extract meaningful linguistic and acoustic patterns without extensive manual labeling. These findings highlight the potential for scalable, non-invasive diagnostic tools that reduce reliance on costly annotations while maintaining high accuracy. By integrating multimodal learning with contextual embeddings, this work lays the foundation for future advancements in personalized dementia detection and cognitive health research.

High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away from prior dedicated heuristic approaches and revisits the most fundamental idea to HR perception by enhancing the long-context capability of MLLMs, driven by recent advances in long-context techniques like retrieval-augmented generation (RAG) for general LLMs. Towards this end, this paper presents the first study exploring the use of RAG to address HR perception challenges. Specifically, we propose Retrieval-Augmented Perception (RAP), a training-free framework that retrieves and fuses relevant image crops while preserving spatial context using the proposed Spatial-Awareness Layout. To accommodate different tasks, the proposed Retrieved-Exploration Search (RE-Search) dynamically selects the optimal number of crops based on model confidence and retrieval scores. Experimental results on HR benchmarks demonstrate the significant effectiveness of RAP, with LLaVA-v1.5-13B achieving a 43% improvement on $V^*$ Bench and 19% on HR-Bench.

Multi-Modal Large Language Models (MLLMs) have exhibited remarkable performance on various vision-language tasks such as Visual Question Answering (VQA). Despite accumulating evidence of privacy concerns associated with task-relevant content, it remains unclear whether MLLMs inadvertently memorize private content that is entirely irrelevant to the training tasks. In this paper, we investigate how randomly generated task-irrelevant private content can become spuriously correlated with downstream objectives due to partial mini-batch training dynamics, thus causing inadvertent memorization. Concretely, we randomly generate task-irrelevant watermarks into VQA fine-tuning images at varying probabilities and propose a novel probing framework to determine whether MLLMs have inadvertently encoded such content. Our experiments reveal that MLLMs exhibit notably different training behaviors in partial mini-batch settings with task-irrelevant watermarks embedded. Furthermore, through layer-wise probing, we demonstrate that MLLMs trigger distinct representational patterns when encountering previously seen task-irrelevant knowledge, even if this knowledge does not influence their output during prompting. Our code is available at https://github.com/illusionhi/ProbingPrivacy.

Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks by connecting multiple vertices through hyperedges, enhancing modeling capabilities, and reducing information loss. Developing foundation models for hypergraphs is challenging due to their distinct data, which includes both vertex features and intricate structural information. We present Hyper-FM, a Hypergraph Foundation Model for multi-domain knowledge extraction, featuring Hierarchical High-Order Neighbor Guided Vertex Knowledge Embedding for vertex feature representation and Hierarchical Multi-Hypergraph Guided Structural Knowledge Extraction for structural information. Additionally, we curate 10 text-attributed hypergraph datasets to advance research between HGNNs and LLMs. Experiments on these datasets show that Hyper-FM outperforms baseline methods by approximately 13.3\%, validating our approach. Furthermore, we propose the first scaling law for hypergraph foundation models, demonstrating that increasing domain diversity significantly enhances performance, unlike merely augmenting vertex and hyperedge counts. This underscores the critical role of domain diversity in scaling hypergraph models.

Large Language Models (LLMs) have shown significant promise across various natural language processing tasks. However, their application in the field of pathology, particularly for extracting meaningful insights from unstructured medical texts such as pathology reports, remains underexplored and not well quantified. In this project, we leverage state-of-the-art language models, including the GPT family, Mistral models, and the open-source Llama models, to evaluate their performance in comprehensively analyzing pathology reports. Specifically, we assess their performance in cancer type identification, AJCC stage determination, and prognosis assessment, encompassing both information extraction and higher-order reasoning tasks. Based on a detailed analysis of their performance metrics in a zero-shot setting, we developed two instruction-tuned models: Path-llama3.1-8B and Path-GPT-4o-mini-FT. These models demonstrated superior performance in zero-shot cancer type identification, staging, and prognosis assessment compared to the other models evaluated.

Designing proper experiments and selecting optimal intervention targets is a longstanding problem in scientific or causal discovery. Identifying the underlying causal structure from observational data alone is inherently difficult. Obtaining interventional data, on the other hand, is crucial to causal discovery, yet it is usually expensive and time-consuming to gather sufficient interventional data to facilitate causal discovery. Previous approaches commonly utilize uncertainty or gradient signals to determine the intervention targets. However, numerical-based approaches may yield suboptimal results due to the inaccurate estimation of the guiding signals at the beginning when with limited interventional data. In this work, we investigate a different approach, whether we can leverage Large Language Models (LLMs) to assist with the intervention targeting in causal discovery by making use of the rich world knowledge about the experimental design in LLMs. Specifically, we present Large Language Model Guided Intervention Targeting (LeGIT) -- a robust framework that effectively incorporates LLMs to augment existing numerical approaches for the intervention targeting in causal discovery. Across 4 realistic benchmark scales, LeGIT demonstrates significant improvements and robustness over existing methods and even surpasses humans, which demonstrates the usefulness of LLMs in assisting with experimental design for scientific discovery.

Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external tools introduces security risks, such as indirect prompt injection (IPI) attacks. Despite defenses designed for IPI attacks, their robustness remains questionable due to insufficient testing against adaptive attacks. In this paper, we evaluate eight different defenses and bypass all of them using adaptive attacks, consistently achieving an attack success rate of over 50%. This reveals critical vulnerabilities in current defenses. Our research underscores the need for adaptive attack evaluation when designing defenses to ensure robustness and reliability. The code is available at https://github.com/uiuc-kang-lab/AdaptiveAttackAgent.