Human motion generation has advanced markedly with the advent of diffusion models. Most recent studies have concentrated on generating motion sequences based on text prompts, commonly referred to as text-to-motion generation. However, the bidirectional generation of motion and text, enabling tasks such as motion-to-text alongside text-to-motion, has been largely unexplored. This capability is essential for aligning diverse modalities and supports unconditional generation. In this paper, we introduce PackDiT, the first diffusion-based generative model capable of performing various tasks simultaneously, including motion generation, motion prediction, text generation, text-to-motion, motion-to-text, and joint motion-text generation. Our core innovation leverages mutual blocks to integrate multiple diffusion transformers (DiTs) across different modalities seamlessly. We train PackDiT on the HumanML3D dataset, achieving state-of-the-art text-to-motion performance with an FID score of 0.106, along with superior results in motion prediction and in-between tasks. Our experiments further demonstrate that diffusion models are effective for motion-to-text generation, achieving performance comparable to that of autoregressive models.

This paper introduces a novel algorithm for constructing decision trees using large language models (LLMs) in a zero-shot manner based on Classification and Regression Trees (CART) principles. Traditional decision tree induction methods rely heavily on labeled data to recursively partition data using criteria such as information gain or the Gini index. In contrast, we propose a method that uses the pre-trained knowledge embedded in LLMs to build decision trees without requiring training data. Our approach leverages LLMs to perform operations essential for decision tree construction, including attribute discretization, probability calculation, and Gini index computation based on the probabilities. We show that these zero-shot decision trees can outperform baseline zero-shot methods and achieve competitive performance compared to supervised data-driven decision trees on tabular datasets. The decision trees constructed via this method provide transparent and interpretable models, addressing data scarcity while preserving interpretability. This work establishes a new baseline in low-data machine learning, offering a principled, knowledge-driven alternative to data-driven tree construction.

Large language models (LLMs) offer a promising way forward for automating software engineering tasks, such as bug fixes, feature additions, etc., via multi-step LLM-based agentic workflows. However, existing metrics for evaluating such workflows, mainly build status and occasionally log analysis, are too sparse and limited in providing the information needed to assess the quality of changes made. In this work, we designed LLM-based critics to derive well-structured and rigorous intermediate/step-level, execution-free evaluation proxies for repo-level code changes. Importantly, we assume access to the gold test patch for the problem (i.e., reference-aware) to assess both semantics and executability of generated patches. With the gold test patch as a reference, we predict executability of all editing locations with an F1 score of 91.6%, aggregating which, we can predict the build status in 84.8% of the instances in SWE-bench. In particular, such an execution-focused LLM critic outperforms other reference-free and reference-aware LLM critics by 38.9% to 72.5%. Moreover, we demonstrate the usefulness of such a reference-aware framework in comparing patches generated by different agentic workflows. Finally, we open-source the library developed for this project, which allows further usage for either other agentic workflows or other benchmarks. The source code is available at https://github.com/amazon-science/code-agent-eval.

Large language models (LLMs) provide powerful foundations to perform fine-grained text re-ranking. However, they are often prohibitive in reality due to constraints on computation bandwidth. In this work, we propose a \textbf{flexible} architecture called \textbf{Matroyshka Re-Ranker}, which is designed to facilitate \textbf{runtime customization} of model layers and sequence lengths at each layer based on users' configurations. Consequently, the LLM-based re-rankers can be made applicable across various real-world situations. The increased flexibility may come at the cost of precision loss. To address this problem, we introduce a suite of techniques to optimize the performance. First, we propose \textbf{cascaded self-distillation}, where each sub-architecture learns to preserve a precise re-ranking performance from its super components, whose predictions can be exploited as smooth and informative teacher signals. Second, we design a \textbf{factorized compensation mechanism}, where two collaborative Low-Rank Adaptation modules, vertical and horizontal, are jointly employed to compensate for the precision loss resulted from arbitrary combinations of layer and sequence compression. We perform comprehensive experiments based on the passage and document retrieval datasets from MSMARCO, along with all public datasets from BEIR benchmark. In our experiments, Matryoshka Re-Ranker substantially outperforms the existing methods, while effectively preserving its superior performance across various forms of compression and different application scenarios.

Test-time prompt tuning enhances zero-shot generalization of vision-language models but tends to ignore the relatedness among test samples during inference. Online test-time prompt tuning provides a simple way to leverage the information in previous test samples, albeit with the risk of prompt collapse due to error accumulation. To enhance test-time prompt tuning, we propose DynaPrompt, short for dynamic test-time prompt tuning, exploiting relevant data distribution information while reducing error accumulation. Built on an online prompt buffer, DynaPrompt adaptively selects and optimizes the relevant prompts for each test sample during tuning. Specifically, we introduce a dynamic prompt selection strategy based on two metrics: prediction entropy and probability difference. For unseen test data information, we develop dynamic prompt appending, which allows the buffer to append new prompts and delete the inactive ones. By doing so, the prompts are optimized to exploit beneficial information on specific test data, while alleviating error accumulation. Experiments on fourteen datasets demonstrate the effectiveness of dynamic test-time prompt tuning. Despite achieving remarkable successes, foundation models such as Contrastive Language-Image Pretraining (CLIP) (Radford et al., 2021) still suffer from distribution shifts when adapting to downstream tasks (Zhou et al., 2022a;b; Xiao et al., 2024). To improve test-time adaptation of the model in the presence of distribution shifts, recent works introduce learnable prompts at test time. The methods freeze the CLIP model parameters while only tuning the learnable prompts for test data. As shown in Figure 1a, test-time prompt tuning (TPT) (Shu et al., 2022) adapts the prompt to each test sample individually, which is widely followed by recent works (Ma et al., 2023; Samadh et al., 2023; Yoon et al., 2024).

Graphical User Interface (GUI) tasks are vital for automating workflows such as software testing, user interface navigation. For users, the GUI is the most intuitive platform for interacting with a computer. Previous work identified a key challenge in developing visual GUI agents: GUI grounding - the ability to accurately locate screen elements based on instructions. However, most existing GUI agents rely on structured data formats like DOM or HTML files in training or inferencing, which are inaccessible across all applications, particular in a general desktop environments such as Windows OS. To address this, we introduce WinClick, a novel visual GUI agent developed in Windows platform. WinClick leverages screenshots to detect actionable regions. To overcome the challenge of GUI grounding, we enhance WinClick with GUI grounding pre-training and propose an LLM-based method for aligning GUI grounding data. Additionally, we introduce WinSpot, the first comprehensive benchmark for GUI grounding on Windows. Our experiments demonstrate that WinClick, combined with GUI grounding pre-training, significantly outperforms existing baselines, offering a scalable solution for GUI automation in desktop environments. WinSpot is publicly available at https://github.com/zackhuiiiii/WinSpot.

An important part of data science is the use of visualisations to display data in a way that is easy to digest. Visualisations often rely on underlying statistical or machine learning models -- ranging from basic calculations like category means to advanced methods such as principal component analysis of multidimensional datasets -- to convey insights. We introduce an analogous concept for word descriptions of data, which we call wordalisations. Wordalisations describe data in easy to digest words, without necessarily reporting numerical values from the data. We show how to create wordalisations using large language models, through prompt templates engineered according to a task-agnostic structure which can be used to automatically generate prompts from data. We show how to produce reliable and engaging texts on three application areas: scouting football players, personality tests, and international survey data. Using the model cards framework, we emphasise the importance of clearly stating the model we are imposing on the data when creating the wordalisation, detailing how numerical values are translated into words, incorporating background information into prompts for the large language model, and documenting the limitations of the wordalisations. We argue that our model cards approach is a more appropriate framework for setting best practices in wordalisation of data than performance tests on benchmark datasets.

The exponential growth of AI in science necessitates efficient and scalable solutions for retrieving and preserving research information. Here, we present a tool for the development of a customized question-answer (QA) dataset, called Interactive Trained Research Innovator (iTRI) - QA, tailored for the needs of researchers leveraging language models (LMs) to retrieve scientific knowledge in a QA format. Our approach integrates curated QA datasets with a specialized research paper dataset to enhance responses' contextual relevance and accuracy using fine-tuned LM. The framework comprises four key steps: (1) the generation of high-quality and human-generated QA examples, (2) the creation of a structured research paper database, (3) the fine-tuning of LMs using domain-specific QA examples, and (4) the generation of QA dataset that align with user queries and the curated database. This pipeline provides a dynamic and domain-specific QA system that augments the utility of LMs in academic research that will be applied for future research LM deployment. We demonstrate the feasibility and scalability of our tool for streamlining knowledge retrieval in scientific contexts, paving the way for its integration into broader multi-disciplinary applications.

Loyal AI is loyal to the community that builds it. An AI is loyal to a community if the community has ownership, alignment, and control. Community owned models can only be used with the approval of the community and share the economic rewards communally. Community aligned models have values that are aligned with the consensus of the community. Community controlled models perform functions designed by the community. Since we would like permissionless access to the loyal AI's community, we need the AI to be open source. The key scientific question then is: how can we build models that are openly accessible (open source) and yet are owned and governed by the community. This seeming impossibility is the focus of this paper where we outline a concrete pathway to Open, Monetizable and Loyal models (OML), building on our earlier work on OML, arXiv:2411.03887(1) , and a representation via a cryptographic-ML library http://github.com/sentient-agi/oml-1.0-fingerprinting .

This year, jurisdictions worldwide, including the United States, the European Union, the United Kingdom, and China, are set to enact or revise laws governing frontier AI. Their efforts largely rely on the assumption that increasing model scale through pretraining is the path to more advanced AI capabilities. Yet growing evidence suggests that this "pretraining paradigm" may be hitting a wall and major AI companies are turning to alternative approaches, like inference-time "reasoning," to boost capabilities instead. This paradigm shift presents fundamental challenges for the frontier AI governance frameworks that target pretraining scale as a key bottleneck useful for monitoring, control, and exclusion, threatening to undermine this new legal order as it emerges. This essay seeks to identify these challenges and point to new paths forward for regulation. First, we examine the existing frontier AI regulatory regime and analyze some key traits and vulnerabilities. Second, we introduce the concept of the "pretraining frontier," the capabilities threshold made possible by scaling up pretraining alone, and demonstrate how it could make the regulatory field more diffuse and complex and lead to new forms of competition. Third, we lay out a regulatory approach that focuses on increasing transparency and leveraging new natural technical bottlenecks to effectively oversee changing frontier AI development while minimizing regulatory burdens and protecting fundamental rights. Our analysis provides concrete mechanisms for governing frontier AI systems across diverse technical paradigms, offering policymakers tools for addressing both current and future regulatory challenges in frontier AI.