Given an unconditional generative model and a predictor for a target property (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. As a highly efficient technique for steering generative models toward flexible outcomes, training-free guidance has gained increasing attention in diffusion models. However, existing methods only handle data in continuous spaces, while many scientific applications involve both continuous and discrete data (referred to as multimodality). Another emerging trend is the growing use of the simple and general flow matching framework in building generative foundation models, where guided generation remains under-explored. To address this, we introduce TFG-Flow, a novel training-free guidance method for multimodal generative flow. TFG-Flow addresses the curse-of-dimensionality while maintaining the property of unbiased sampling in guiding discrete variables. We validate TFG-Flow on four molecular design tasks and show that TFG-Flow has great potential in drug design by generating molecules with desired properties. Recent advancements in generative foundation models have demonstrated their increasing power across a wide range of domains (Reid et al., 2024; Achiam et al., 2023; Abramson et al., 2024). In particular, diffusion-based foundation models, such as Stable Diffusion (Esser et al., 2024) and SORA (Brooks et al., 2024) have achieved significant success, catalyzing a new wave of applications in areas such as art and science. As these models become more prevalent, a critical question arises: how can we steer these foundation models to achieve specific properties during inference time? One promising direction is using classifier-based guidance (Dhariwal & Nichol, 2021) or classifierfree guidance (Ho & Salimans, 2022), which typically necessitate training a specialized model for each conditioning signal (e.g., a noise-conditional classifier or a text-conditional denoiser). This resource-intensive and time-consuming process greatly limits their applicability. Recently, there has been growing interest in training-free guidance for diffusion models, which allows users to steer the generation process using an off-the-shelf differentiable target predictor without requiring additional model training (Ye et al., 2024). A target predictor can be any classifier, loss, or energy function used to score the quality of the generated samples. Training-free guidance offers a flexible and efficient means of customizing generation, holding the potential to transform the field of generative AI.

Recent advances in Large Language Models (LLMs) have intensified the debate surrounding the fundamental nature of their reasoning capabilities. While achieving high performance on benchmarks such as GPQA and MMLU, these models exhibit limitations in more complex reasoning tasks, highlighting the need for more rigorous evaluation methodologies. We propose a novel phenomenological approach that goes beyond traditional accuracy metrics to probe the underlying mechanisms of model behavior, establishing a framework that could broadly impact how we analyze and understand AI systems. Using positional bias in multiple-choice reasoning tasks as a case study, we demonstrate how systematic perturbations can reveal fundamental aspects of model decision-making. To analyze these behaviors, we develop two complementary phenomenological models: a Probabilistic Mixture Model (PMM) that decomposes model responses into reasoning, memorization, and guessing components and an Information-Theoretic Consistency (ITC) analysis that quantifies the relationship between model confidence and strategy selection. Through controlled experiments on reasoning benchmarks, we show that true reasoning remains challenging for current models, with apparent success often relying on sophisticated combinations of memorization and pattern matching rather than genuine logical deduction. More fundamentally, we demonstrate that accuracy alone often overstates a model's reasoning abilities, as model behavior can be characterized through underlying mechanisms in the phase space of cognitive strategies, revealing how models dynamically balance different approaches when responding to queries. This framework enables quantitative criteria for real-world deployments, allowing applications to specify reliability thresholds based on strategy distributions rather than aggregate performance metrics.

Healthcare systems continuously generate vast amounts of electronic health records (EHRs), commonly stored in the Fast Healthcare Interoperability Resources (FHIR) standard. Despite the wealth of information in these records, their complexity and volume make it difficult for users to retrieve and interpret crucial health insights. Recent advances in Large Language Models (LLMs) offer a solution, enabling semantic question answering (QA) over medical data, allowing users to interact with their health records more effectively. However, ensuring privacy and compliance requires edge and private deployments of LLMs. This paper proposes a novel approach to semantic QA over EHRs by first identifying the most relevant FHIR resources for a user query (Task1) and subsequently answering the query based on these resources (Task2). We explore the performance of privately hosted, fine-tuned LLMs, evaluating them against benchmark models such as GPT-4 and GPT-4o. Our results demonstrate that fine-tuned LLMs, while 250x smaller in size, outperform GPT-4 family models by 0.55% in F1 score on Task1 and 42% on Meteor Task in Task2. Additionally, we examine advanced aspects of LLM usage, including sequential fine-tuning, model self-evaluation (narcissistic evaluation), and the impact of training data size on performance. The models and datasets are available here: https://huggingface.co/genloop

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in inefficiencies that affect both computational demands and task-specific outcomes. A framework was proposed to restructure these redundancies through advanced clustering techniques and dynamic thresholding, ensuring that critical semantic relationships are preserved while removing unnecessary overlaps. Evaluations revealed improved memory efficiency and faster inference times, alongside better alignment in latent knowledge clusters that enhanced interpretability. Improvements in error rates and adversarial robustness suggest that restructuring redundancies has broader implications for increasing model reliability across diverse applications. Comparative analyses highlighted reductions in resource consumption and notable gains in performance, particularly in translation and summarization tasks. Energy metrics demonstrated significant savings during training phases, further validating the practicality of the approach for real-world deployments. Representational fidelity was also enhanced, with latent space evaluations indicating better cluster alignment and higher semantic consistency. The methodology bridges a key gap in model optimization through directly addressing redundancies at the structural level. Its application opens avenues for scalable, efficient, and contextually aware systems that can adapt to complex, domain-specific tasks without compromising on performance.

Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documents, limiting their effectiveness in knowledge-intensive tasks. To address this limitation, retrieval-augmented generation (RAG) models have been developed, enabling generative models to incorporate relevant document fragments into their inputs. In this paper, we design and evaluate a RAG-based virtual assistant specifically tailored for the University of S\~ao Paulo. Our system architecture comprises two key modules: a retriever and a generative model. We experiment with different types of models for both components, adjusting hyperparameters such as chunk size and the number of retrieved documents. Our optimal retriever model achieves a Top-5 accuracy of 30%, while our most effective generative model scores 22.04\% against ground truth answers. Notably, when the correct document chunks are supplied to the LLMs, accuracy significantly improves to 54.02%, an increase of over 30 percentage points. Conversely, without contextual input, performance declines to 13.68%. These findings highlight the critical role of database access in enhancing LLM performance. They also reveal the limitations of current semantic search methods in accurately identifying relevant documents and underscore the ongoing challenges LLMs face in generating precise responses.

The task of predicting time and location from images is challenging and requires complex human-like puzzle-solving ability over different clues. In this work, we formalize this ability into core skills and implement them using different modules in an expert pipeline called PuzzleGPT. PuzzleGPT consists of a perceiver to identify visual clues, a reasoner to deduce prediction candidates, a combiner to combinatorially combine information from different clues, a web retriever to get external knowledge if the task can't be solved locally, and a noise filter for robustness. This results in a zero-shot, interpretable, and robust approach that records state-of-the-art performance on two datasets -- TARA and WikiTilo. PuzzleGPT outperforms large VLMs such as BLIP-2, InstructBLIP, LLaVA, and even GPT-4V, as well as automatically generated reasoning pipelines like VisProg, by at least 32% and 38%, respectively. It even rivals or surpasses finetuned models.

We introduce the concept of the self-referencing causal cycle (abbreviated RECALL) - a mechanism that enables large language models (LLMs) to bypass the limitations of unidirectional causality, which underlies a phenomenon known as the reversal curse. When an LLM is prompted with sequential data, it often fails to recall preceding context. For example, when we ask an LLM to recall the line preceding "O say does that star-spangled banner yet wave" in the U.S. National Anthem, it often fails to correctly return "Gave proof through the night that our flag was still there" - this is due to the reversal curse. It occurs because language models such as ChatGPT and Llama generate text based on preceding tokens, requiring facts to be learned and reproduced in a consistent token order. While the reversal curse is often viewed as a limitation, we offer evidence of an alternative view: it is not always an obstacle in practice. We find that RECALL is driven by what we designate as cycle tokens - sequences that connect different parts of the training data, enabling recall of preceding tokens from succeeding ones. Through rigorous probabilistic formalization and controlled experiments, we demonstrate how the cycles they induce influence a model's ability to reproduce information. To facilitate reproducibility, we provide our code and experimental details at https://anonymous.4open.science/r/remember-B0B8/.

The recent surge of building software systems powered by Large Language Models (LLMs) has led to the development of various testing frameworks, primarily focused on treating prompt templates as the unit of testing. Despite the significant costs associated with test input execution and output assessment, the curation of optimized test suites is yet overlooked in these tools, which calls for tailored test selection or prioritization strategies. In this paper, we show that diversity-based testing techniques, such as Adaptive Random Testing (ART) with appropriate string distance metrics, can be effectively applied to the testing of prompt templates. Our proposed adaptive testing approach adjusts the conventional ART process to this context by selecting new test inputs based on scores derived from existing test suite and their labelling results. Our results, obtained using various implementations that explore several string-based distances, confirm that our approach enables the discovery of failures with reduced testing budgets and promotes the generation of more varied outputs.

In this paper, we present ENTER, an interpretable Video Question Answering (VideoQA) system based on event graphs. Event graphs convert videos into graphical representations, where video events form the nodes and event-event relationships (temporal/causal/hierarchical) form the edges. This structured representation offers many benefits: 1) Interpretable VideoQA via generated code that parses event-graph; 2) Incorporation of contextual visual information in the reasoning process (code generation) via event graphs; 3) Robust VideoQA via Hierarchical Iterative Update of the event graphs. Existing interpretable VideoQA systems are often top-down, disregarding low-level visual information in the reasoning plan generation, and are brittle. While bottom-up approaches produce responses from visual data, they lack interpretability. Experimental results on NExT-QA, IntentQA, and EgoSchema demonstrate that not only does our method outperform existing top-down approaches while obtaining competitive performance against bottom-up approaches, but more importantly, offers superior interpretability and explainability in the reasoning process.

Large Language Models have advanced automated software development, however, it remains a challenge to correctly infer dependencies, namely, identifying the internal components and external packages required for a repository to successfully run. Existing studies highlight that dependency-related issues cause over 40\% of observed runtime errors on the generated repository. To address this, we introduce DI-BENCH, a large-scale benchmark and evaluation framework specifically designed to assess LLMs' capability on dependency inference. The benchmark features 581 repositories with testing environments across Python, C#, Rust, and JavaScript. Extensive experiments with textual and execution-based metrics reveal that the current best-performing model achieves only a 42.9% execution pass rate, indicating significant room for improvement. DI-BENCH establishes a new viewpoint for evaluating LLM performance on repositories, paving the way for more robust end-to-end software synthesis.