A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence. In this work, we introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general modalities, learn in context (i.e., few-shot), and follow instructions (i.e., zero-shot). Specifically, we train Kosmos-1 from scratch on web-scale multimodal corpora, including arbitrarily interleaved text and images, image-caption pairs, and text data. We evaluate various settings, including zero-shot, few-shot, and multimodal chain-of-thought prompting, on a wide range of tasks without any gradient updates or finetuning. Experimental results show that Kosmos-1 achieves impressive performance on (i) language understanding, generation, and even OCR-free NLP (directly fed with document images), (ii) perception-language tasks, including multimodal dialogue, image captioning, visual question answering, and (iii) vision tasks, such as image recognition with descriptions (specifying classification via text instructions). We also show that MLLMs can benefit from cross-modal transfer, i.e., transfer knowledge from language to multimodal, and from multimodal to language. In addition, we introduce a dataset of Raven IQ test, which diagnoses the nonverbal reasoning capability of MLLMs.

Forward gradient learning computes a noisy directional gradient and is a biologically plausible alternative to backprop for learning deep neural networks. However, the standard forward gradient algorithm, when applied naively, suffers from high variance when the number of parameters to be learned is large. In this paper, we propose a series of architectural and algorithmic modifications that together make forward gradient learning practical for standard deep learning benchmark tasks. We show that it is possible to substantially reduce the variance of the forward gradient estimator by applying perturbations to activations rather than weights. We further improve the scalability of forward gradient by introducing a large number of local greedy loss functions, each of which involves only a small number of learnable parameters, and a new MLPMixer-inspired architecture, LocalMixer, that is more suitable for local learning. Our approach matches backprop on MNIST and CIFAR-10 and significantly outperforms previously proposed backprop-free algorithms on ImageNet. Most deep neural networks today are trained using the backpropagation algorithm (a.k.a. Although artificial neural networks were originally inspired by biological neurons, backprop has always been considered as "biologically implausible" as the brain does not form symmetric backward connections or perform synchronized computations. From an engineering perspective, backprop is incompatible with a massive level of model parallelism, and restricts potential hardware designs. These concerns call for a drastically different learning algorithm for deep networks. In the past, there have been attempts to address the above weight transport problem by introducing random backward weights (Lillicrap et al., 2016; Nøkland, 2016), but they have been found to scale poorly on larger datasets such as ImageNet (Bartunov et al., 2018). Addressing the issue of global synchronization, several papers showed that greedy local loss functions can be almost as good as end-to-end learning (Belilovsky et al., 2019; Löwe et al., 2019; Xiong et al., 2020). However, they still rely on backprop for learning a number of internal layers within each local module.

The easy and accurate identification of varieties is fundamental in agriculture, especially in the olive sector, where more than 1200 olive varieties are currently known worldwide. Varietal misidentification leads to many potential problems for all the actors in the sector: farmers and nursery workers may establish the wrong variety, leading to its maladaptation in the field; olive oil and table olive producers may label and sell a non-authentic product; consumers may be misled; and breeders may commit errors during targeted crossings between different varieties. To date, the standard for varietal identification and certification consists of two methods: morphological classification and genetic analysis. The morphological classification consists of the visual pairwise comparison of different organs of the olive tree, where the most important organ is considered to be the endocarp. In contrast, different methods for genetic classification exist (RAPDs, SSR, and SNP). Both classification methods present advantages and disadvantages. Visual morphological classification requires highly specialized personnel and is prone to human error. Genetic identification methods are more accurate but incur a high cost and are difficult to implement. This paper introduces OliVaR, a novel approach to olive varietal identification. OliVaR uses a teacher-student deep learning architecture to learn the defining characteristics of the endocarp of each specific olive variety and perform classification. We construct what is, to the best of our knowledge, the largest olive variety dataset to date, comprising image data for 131 varieties from the Mediterranean basin. We thoroughly test OliVaR on this dataset and show that it correctly predicts olive varieties with over 86% accuracy.

Multilingual speech recognition with neural networks is often implemented with batch-learning, when all of the languages are available before training. An ability to add new languages after the prior training sessions can be economically beneficial, but the main challenge is catastrophic forgetting. In this work, we combine the qualities of weight factorization and elastic weight consolidation in order to counter catastrophic forgetting and facilitate learning new languages quickly. Such combination allowed us to eliminate catastrophic forgetting while still achieving performance for the new languages comparable with having all languages at once, in experiments of learning from an initial 10 languages to achieve 26 languages without catastrophic forgetting and a reasonable performance compared to training all languages from scratch.

Noisy Student Training (NST) has recently demonstrated extremely strong performance in Automatic Speech Recognition(ASR). In this paper, we propose a data selection strategy named LM Filter to improve the performance of NST on non-target domain data in ASR tasks. Hypotheses with and without a Language Model are generated and the CER differences between them are utilized as a filter threshold. Results reveal that significant improvements of 10.4% compared with no data filtering baselines. We can achieve 3.31% CER in AISHELL-1 test set, which is best result from our knowledge without any other supervised data. We also perform evaluations on the supervised 1000 hour AISHELL-2 dataset and competitive results of 4.73% CER can be achieved.

In deep reinforcement learning (RL), data augmentation is widely considered as a tool to induce a set of useful priors about semantic consistency and improve sample efficiency and generalization performance. However, even when the prior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency. Meanwhile, the agent is forgetful of the prior due to the non-stationary nature of RL. These observations suggest two extreme schedules of distillation: (i) over the entire training; or (ii) only at the end. Hence, we devise a stand-alone network distillation method to inject the consistency prior at any time (even after RL), and a simple yet efficient framework to automatically schedule the distillation. Specifically, the proposed framework first focuses on mastering train environments regardless of generalization by adaptively deciding which {\it or no} augmentation to be used for the training. After this, we add the distillation to extract the remaining benefits for generalization from all the augmentations, which requires no additional new samples. In our experiments, we demonstrate the utility of the proposed framework, in particular, that considers postponing the augmentation to the end of RL training.

Crossmodal knowledge distillation (KD) extends traditional knowledge distillation to the area of multimodal learning and demonstrates great success in various applications. To achieve knowledge transfer across modalities, a pretrained network from one modality is adopted as the teacher to provide supervision signals to a student network learning from another modality. In contrast to the empirical success reported in prior works, the working mechanism of crossmodal KD remains a mystery. In this paper, we present a thorough understanding of crossmodal KD. We begin with two case studies and demonstrate that KD is not a universal cure in crossmodal knowledge transfer. We then present the modality Venn diagram (MVD) to understand modality relationships and the modality focusing hypothesis (MFH) revealing the decisive factor in the efficacy of crossmodal KD. Experimental results on 6 multimodal datasets help justify our hypothesis, diagnose failure cases, and point directions to improve crossmodal knowledge transfer in the future. Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network to another (Wang & Yoon, 2021; Gou et al., 2021). Its core mechanism is a teacher-student learning framework, where the student network is trained to mimic the teacher through a loss. The loss function, initially proposed by (Hinton et al., 2015) as the KL divergence between teacher and student soft labels, has been extended in many ways (Zagoruyko & Komodakis, 2016; Tung & Mori, 2019; Park et al., 2019; Peng et al., 2019; Tian et al., 2019). KD has been successfully applied to various fields and demonstrates its high practical value. The wide applicability of KD stems from its generality: any student can learn from any teacher. To be more precise, the student and teacher network may differ in several ways. Three common scenarios are: (1) model capacity difference: Many works (Zagoruyko & Komodakis, 2016; Tung & Mori, 2019; Park et al., 2019; Peng et al., 2019) on model compression aim to learn a lightweight student matching the performance of its cumbersome teacher for deployment benefits.

Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL problems are not robust and safe against carefully designed observational perturbations. We formally analyze the unique properties of designing effective observational adversarial attackers in the safe RL setting. We show that baseline adversarial attack techniques for standard RL tasks are not always effective for safe RL and propose two new approaches - one maximizes the cost and the other maximizes the reward. One interesting and counter-intuitive finding is that the maximum reward attack is strong, as it can both induce unsafe behaviors and make the attack stealthy by maintaining the reward. We further propose a robust training framework for safe RL and evaluate it via comprehensive experiments. This paper provides a pioneer work to investigate the safety and robustness of RL under observational attacks for future safe RL studies. Code is available at: \url{https://github.com/liuzuxin/safe-rl-robustness}

Large language models (LLMs) have shown remarkable reasoning capabilities given chain-of-thought prompts (examples with intermediate reasoning steps). Existing benchmarks measure reasoning ability indirectly, by evaluating accuracy on downstream tasks such as mathematical reasoning. However, it is unclear how these models obtain the answers and whether they rely on simple heuristics rather than the generated chain-of-thought. To enable systematic exploration of the reasoning ability of LLMs, we present a new synthetic question-answering dataset called PrOntoQA, where each example is generated from a synthetic world model represented in first-order logic. This allows us to parse the generated chain-of-thought into symbolic proofs for formal analysis. Our analysis on InstructGPT and GPT-3 shows that LLMs are quite capable of making correct individual deduction steps, and so are generally capable of reasoning, even in fictional contexts. However, they have difficulty with proof planning: When multiple valid deduction steps are available, they are not able to systematically explore the different options.

Inspired by Regularized Lottery Ticket Hypothesis, which states that competitive smooth (non-binary) subnetworks exist within a dense network, we propose a fewshot class-incremental learning method referred to as Soft-SubNetworks (SoftNet). Our objective is to learn a sequence of sessions incrementally, where each session only includes a few training instances per class while preserving the knowledge of the previously learned ones. SoftNet jointly learns the model weights and adaptive non-binary soft masks at a base training session in which each mask consists of the major and minor subnetwork; the former aims to minimize catastrophic forgetting during training, and the latter aims to avoid overfitting to a few samples in each new training session. We provide comprehensive empirical validations demonstrating that our SoftNet effectively tackles the few-shot incremental learning problem by surpassing the performance of state-of-the-art baselines over benchmark datasets. The public code is available at https://github.com/ihaeyong/ Lifelong Learning, or Continual Learning, is a learning paradigm to expand knowledge and skills through sequential training of multiple tasks (Thrun, 1995). While the standard scenarios for continual learning assume a sufficiently large number of instances per task, a lifelong learner for real-world applications often suffers from insufficient training instances for each problem to solve. This paper aims to tackle the issue of limited training instances for practical Class-Incremental Learning (CIL), referred to as Few-Shot CIL (FSCIL) (Ren et al., 2019; Chen and Lee, 2020; Tao et al., 2020; Zhang et al., 2021; Cheraghian et al., 2021; Shi et al., 2021). However, there are two critical challenges in solving FSCIL problems: catastrophic forgetting and overfitting. Catastrophic forgetting (Goodfellow et al., 2013; Kirkpatrick et al., 2017) or Catastrophic Interference McCloskey and Cohen (1989) is a phenomenon in which a continual learner loses the previously learned task knowledge by updating the weights to adapt to new tasks, resulting in significant performance degeneration on previous tasks.