We combine concept-based neural networks with generative, flow-based classifiers into a novel, intrinsically explainable, exactly invertible approach to supervised learning. Prototypical neural networks, a type of concept-based neural network, represent an exciting way forward in realizing human-comprehensible machine learning without concept annotations, but a human-machine semantic gap continues to haunt current approaches. We find that reliance on indirect interpretation functions for prototypical explanations imposes a severe limit on prototypes' informative power. From this, we posit that invertibly learning prototypes as distributions over the latent space provides more robust, expressive, and interpretable modeling. We propose one such model, called ProtoFlow, by composing a normalizing flow with Gaussian mixture models. ProtoFlow (1) sets a new state-of-the-art in joint generative and predictive modeling and (2) achieves predictive performance comparable to existing prototypical neural networks while enabling richer interpretation.

This paper investigates the ontological characterization of Large Language Models (LLMs) like ChatGPT. Between inflationary and deflationary accounts, we pay special attention to their status as agents. This requires explaining in detail the architecture, processing, and training procedures that enable LLMs to display their capacities, and the extensions used to turn LLMs into agent-like systems. After a systematic analysis we conclude that a LLM fails to meet necessary and sufficient conditions for autonomous agency in the light of embodied theories of mind: the individuality condition (it is not the product of its own activity, it is not even directly affected by it), the normativity condition (it does not generate its own norms or goals), and, partially the interactional asymmetry condition (it is not the origin and sustained source of its interaction with the environment). If not agents, then ... what are LLMs? We argue that ChatGPT should be characterized as an interlocutor or linguistic automaton, a library-that-talks, devoid of (autonomous) agency, but capable to engage performatively on non-purposeful yet purpose-structured and purpose-bounded tasks. When interacting with humans, a "ghostly" component of the human-machine interaction makes it possible to enact genuine conversational experiences with LLMs. Despite their lack of sensorimotor and biological embodiment, LLMs textual embodiment (the training corpus) and resource-hungry computational embodiment, significantly transform existing forms of human agency. Beyond assisted and extended agency, the LLM-human coupling can produce midtended forms of agency, closer to the production of intentional agency than to the extended instrumentality of any previous technologies.

As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different languages. However, such language adaptation is often accompanied by catastrophic forgetting of the base model's capabilities, severely limiting the usefulness of the resulting model. We address this issue by proposing Branch-and-Merge (BaM), a new adaptation method based on iteratively merging multiple models, fine-tuned on a subset of the available training data. BaM is based on the insight that this yields lower magnitude but higher quality weight changes, reducing forgetting of the source domain while maintaining learning on the target domain. We demonstrate in an extensive empirical study on Bulgarian and German that BaM can significantly reduce forgetting while matching or even improving target domain performance compared to both standard continued pretraining and instruction finetuning across different model architectures.

When planning for autonomous driving, it is crucial to consider essential traffic elements such as lanes, intersections, traffic regulations, and dynamic agents. However, they are often overlooked by the traditional end-to-end planning methods, likely leading to inefficiencies and non-compliance with traffic regulations. In this work, we endeavor to integrate the perception of these elements into the planning task. To this end, we propose Perception Helps Planning (PHP), a novel framework that reconciles lane-level planning with perception. This integration ensures that planning is inherently aligned with traffic constraints, thus facilitating safe and efficient driving. Specifically, PHP focuses on both edges of a lane for planning and perception purposes, taking into consideration the 3D positions of both lane edges and attributes for lane intersections, lane directions, lane occupancy, and planning. In the algorithmic design, the process begins with the transformer encoding multi-camera images to extract the above features and predicting lane-level perception results. Next, the hierarchical feature early fusion module refines the features for predicting planning attributes. Finally, the double-edge interpreter utilizes a late-fusion process specifically designed to integrate lane-level perception and planning information, culminating in the generation of vehicle control signals. Experiments on three Carla benchmarks show significant improvements in driving score of 27.20%, 33.47%, and 15.54% over existing algorithms, respectively, achieving the state-of-the-art performance, with the system operating up to 22.57 FPS.

Knowledge-intensive visual question answering requires models to effectively use external knowledge to help answer visual questions. A typical pipeline includes a knowledge retriever and an answer generator. However, a retriever that utilizes local information, such as an image patch, may not provide reliable question-candidate relevance scores. Besides, the two-tower architecture also limits the relevance score modeling of a retriever to select top candidates for answer generator reasoning. In this paper, we introduce an additional module, a multi-modal reranker, to improve the ranking quality of knowledge candidates for answer generation. Our reranking module takes multi-modal information from both candidates and questions and performs cross-item interaction for better relevance score modeling. Experiments on OK-VQA and A-OKVQA show that multi-modal reranker from distant supervision provides consistent improvements. We also find a training-testing discrepancy with reranking in answer generation, where performance improves if training knowledge candidates are similar to or noisier than those used in testing.

With the advanced vision capabilities of GPT-4o and Gemini Flash, an important question arises regarding the accuracy of these functionalities in practical business applications. Our assumption was that multimodal models are good at reading and summarizing charts. When given an image of a slide deck, they do a good job of summarizing key insights from it, often including relevant data points. Existing research into this question has evaluated the efficacy of LLM's when parsing tables [3], concluding that the LLMs were highly sensitive to input prompts which drive performance. Other works also evaluate LLMs ability to reason and read mathematical graphs [2] and find that GPT models outperform alternatives. This paper aims to explore whether multimodal models perform well on a variant of this skill - answering straightforward questions that require the models to pick out a number from a slide deck.

Real world deployments of word alignment are almost certain to cover both high and low resource languages. However, the state-of-the-art for this task recommends a different model class depending on the availability of gold alignment training data for a particular language pair. We propose BinaryAlign, a novel word alignment technique based on binary sequence labeling that outperforms existing approaches in both scenarios, offering a unifying approach to the task. Additionally, we vary the specific choice of multilingual foundation model, perform stratified error analysis over alignment error type, and explore the performance of BinaryAlign on non-English language pairs. We make our source code publicly available.

With the widespread availability of LLMs since the release of ChatGPT and increased public scrutiny, commercial model development appears to have focused their efforts on 'safety' training concerning legal liabilities at the expense of social impact evaluation. This mimics a similar trend which we could observe for search engine autocompletion some years prior. We draw on scholarship from NLP and search engine auditing and present a novel evaluation task in the style of autocompletion prompts to assess stereotyping in LLMs. We assess LLMs by using four metrics, namely refusal rates, toxicity, sentiment and regard, with and without safety system prompts. Our findings indicate an improvement to stereotyping outputs with the system prompt, but overall a lack of attention by LLMs under study to certain harms classified as toxic, particularly for prompts about peoples/ethnicities and sexual orientation. Mentions of intersectional identities trigger a disproportionate amount of stereotyping. Finally, we discuss the implications of these findings about stereotyping harms in light of the coming intermingling of LLMs and search and the choice of stereotyping mitigation policy to adopt. We address model builders, academics, NLP practitioners and policy makers, calling for accountability and awareness concerning stereotyping harms, be it for training data curation, leader board design and usage, or social impact measurement.

-- Drug sample comparison is a process used by the French National Police to identify drug distribution networks. The current approach is based on a manual comparison done by forensic experts. In this article, we present our approach to acquire, formalise, and specify expert knowledge to improve the current process. We use an ontology coupled with logical rules to model the underlying knowledge. The different steps of our approach are designed to be reused in other application domains. The results obtained are explainable making them usable by experts in different fields. The fight against drug trafficking has been one of the French government's priorities since the end of 2019 and has led to the creation of the National Stup plan. This plan comprises 55 measures, including the use of new indicators to understand consumer habits and dealers' methods. The work described in this article is part of this plan and aims to support scientific experts in the decision-making process for narcotic profiling. As part of the fight against drug trafficking, several arrests may be made, often accompanied by seizures. Forensic experts perform several analyses on samples from a seizure. They aim to correlate different samples from different seizures to identify trafficking networks best. To do so, experts use sample matching to pair samples according to their characteristics. Paired samples constitute an ensemble called a batch. The sample characteristics used are represented by different data, namely: macroscopic data (e.g., sample dimension, drug logos), qualitative data (e.g., list of active substances), quantitative data (e.g., dosage of substances) or non-confidential seizure data (e.g., date, place of seizure). In France, such data is stored in the national STUPS database.

Control of off-road vehicles is challenging due to the complex dynamic interactions with the terrain. Accurate modeling of these interactions is important to optimize driving performance, but the relevant physical phenomena are too complex to model from first principles. Therefore, we present an offline meta-learning algorithm to construct a rapidly-tunable model of residual dynamics and disturbances. Our model processes terrain images into features using a visual foundation model (VFM), then maps these features and the vehicle state to an estimate of the current actuation matrix using a deep neural network (DNN). We then combine this model with composite adaptive control to modify the last layer of the DNN in real time, accounting for the remaining terrain interactions not captured during offline training. We provide mathematical guarantees of stability and robustness for our controller and demonstrate the effectiveness of our method through simulations and hardware experiments with a tracked vehicle and a car-like robot. We evaluate our method outdoors on different slopes with varying slippage and actuator degradation disturbances, and compare against an adaptive controller that does not use the VFM terrain features. We show significant improvement over the baseline in both hardware experimentation and simulation.