Knowledge Tracing (KT) aims to predict students' future performances based on their former exercises and additional information in educational settings. KT has received significant attention since it facilitates personalized experiences in educational situations. Simultaneously, the autoregressive modeling on the sequence of former exercises has been proven effective for this task. One of the primary challenges in autoregressive modeling for Knowledge Tracing is effectively representing the anterior (pre-response) and posterior (post-response) states of learners across exercises. Existing methods often employ complex model architectures to update learner states using question and response records. In this study, we propose a novel perspective on knowledge tracing task by treating it as a generative process, consistent with the principles of autoregressive models. We demonstrate that knowledge states can be directly represented through autoregressive encodings on a question-response alternate sequence, where model generate the most probable representation in hidden state space by analyzing history interactions. This approach underpins our framework, termed Alternate Autoregressive Knowledge Tracing (AAKT). Additionally, we incorporate supplementary educational information, such as question-related skills, into our framework through an auxiliary task, and include extra exercise details, like response time, as additional inputs. Our proposed framework is implemented using advanced autoregressive technologies from Natural Language Generation (NLG) for both training and prediction. Empirical evaluations on four real-world KT datasets indicate that AAKT consistently outperforms all baseline models in terms of AUC, ACC, and RMSE. Furthermore, extensive ablation studies and visualized analysis validate the effectiveness of key components in AAKT.

Fill-in-the-Middle (FIM) has become integral to code language models, enabling generation of missing code given both left and right contexts. However, the current FIM training paradigm, which reorders original training sequences and then performs regular next-token prediction (NTP), often leads to models struggling to generate content that aligns smoothly with the surrounding context. Crucially, while existing works rely on rule-based post-processing to circumvent this weakness, such methods are not practically usable in open-domain code completion tasks as they depend on restrictive, dataset-specific assumptions (e.g., generating the same number of lines as in the ground truth). Moreover, model performance on FIM tasks deteriorates significantly without these unrealistic assumptions. We hypothesize that NTP alone is insufficient for models to learn effective planning conditioned on the distant right context, a critical factor for successful code infilling. To overcome this, we propose Horizon-Length Prediction (HLP), a novel training objective that teaches models to predict the number of remaining middle tokens (i.e., horizon length) at each step. HLP advances FIM with lookahead planning, enabling models to inherently learn infilling boundaries for arbitrary left and right contexts without relying on dataset-specific post-processing. Our evaluation across different models and sizes shows that HLP significantly improves FIM performance by up to 24% relatively on diverse benchmarks, across file-level and repository-level, and without resorting to unrealistic post-processing methods. Furthermore, the enhanced planning capability gained through HLP boosts model performance on code reasoning. Importantly, HLP only incurs negligible training overhead and no additional inference cost, ensuring its practicality for real-world scenarios.

This study introduces bifurcated attention, a method designed to enhance language model inference in shared-context batch decoding scenarios. Our approach addresses the challenge of redundant memory IO costs, a critical factor contributing to latency in high batch sizes and extended context lengths. Bifurcated attention achieves this by strategically dividing the attention mechanism during incremental decoding into two separate GEMM operations: one focusing on the KV cache from prefill, and another on the decoding process itself. While maintaining the computational load (FLOPs) of standard attention mechanisms, bifurcated attention ensures precise computation with significantly reduced memory IO. Our empirical results show over 2.1$\times$ speedup when sampling 16 output sequences and more than 6.2$\times$ speedup when sampling 32 sequences at context lengths exceeding 8k tokens on a 7B model that uses multi-head attention. The efficiency gains from bifurcated attention translate into lower latency, making it particularly suitable for real-time applications. For instance, it enables massively parallel answer generation without substantially increasing latency, thus enhancing performance when integrated with post-processing techniques such as re-ranking.

Approximation of solutions to partial differential equations (PDE) is an important problem in computational science and engineering. Using neural networks as an ansatz for the solution has proven a challenge in terms of training time and approximation accuracy. In this contribution, we discuss how sampling the hidden weights and biases of the ansatz network from data-agnostic and data-dependent probability distributions allows us to progress on both challenges. In most examples, the random sampling schemes outperform iterative, gradient-based optimization of physics-informed neural networks regarding training time and accuracy by several orders of magnitude. For time-dependent PDE, we construct neural basis functions only in the spatial domain and then solve the associated ordinary differential equation with classical methods from scientific computing over a long time horizon. This alleviates one of the greatest challenges for neural PDE solvers because it does not require us to parameterize the solution in time. For second-order elliptic PDE in Barron spaces, we prove the existence of sampled networks with $L^2$ convergence to the solution. We demonstrate our approach on several time-dependent and static PDEs. We also illustrate how sampled networks can effectively solve inverse problems in this setting. Benefits compared to common numerical schemes include spectral convergence and mesh-free construction of basis functions.

The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks. Previously studied CL assumes that data are given in sequence nose-to-tail for different tasks, thus indeed belonging to Serial Continual Learning (SCL). This paper studies the novel paradigm of Parallel Continual Learning (PCL) in dynamic multi-task scenarios, where a diverse set of tasks is encountered at different time points. PCL presents challenges due to the training of an unspecified number of tasks with varying learning progress, leading to the difficulty of guaranteeing effective model updates for all encountered tasks. In our previous conference work, we focused on measuring and reducing the discrepancy among gradients in a multi-objective optimization problem, which, however, may still contain negative transfers in every model update. To address this issue, in the dynamic multi-objective optimization problem, we introduce task-specific elastic factors to adjust the descent direction towards the Pareto front. The proposed method, called Elastic Multi-Gradient Descent (EMGD), ensures that each update follows an appropriate Pareto descent direction, minimizing any negative impact on previously learned tasks. To balance the training between old and new tasks, we also propose a memory editing mechanism guided by the gradient computed using EMGD. This editing process updates the stored data points, reducing interference in the Pareto descent direction from previous tasks. Experiments on public datasets validate the effectiveness of our EMGD in the PCL setting.

We introduce a probability distribution, combined with an efficient sampling algorithm, for weights and biases of fully-connected neural networks. In a supervised learning context, no iterative optimization or gradient computations of internal network parameters are needed to obtain a trained network. The sampling is based on the idea of random feature models. However, instead of a data-agnostic distribution, e.g., a normal distribution, we use both the input and the output training data to sample shallow and deep networks. We prove that sampled networks are universal approximators. For Barron functions, we show that the $L^2$-approximation error of sampled shallow networks decreases with the square root of the number of neurons. Our sampling scheme is invariant to rigid body transformations and scaling of the input data, which implies many popular pre-processing techniques are not required. In numerical experiments, we demonstrate that sampled networks achieve accuracy comparable to iteratively trained ones, but can be constructed orders of magnitude faster. Our test cases involve a classification benchmark from OpenML, sampling of neural operators to represent maps in function spaces, and transfer learning using well-known architectures.

Large-scale code generation models such as Codex and CodeT5 have achieved impressive performance. However, libraries are upgraded or deprecated very frequently and re-training large-scale language models is computationally expensive. Therefore, Continual Learning (CL) is an important aspect that remains underexplored in the code domain. In this paper, we introduce a benchmark called CodeTask-CL that covers a wide range of tasks, including code generation, translation, summarization, and refinement, with different input and output programming languages. Next, on our CodeTask-CL benchmark, we compare popular CL techniques from NLP and Vision domains. We find that effective methods like Prompt Pooling (PP) suffer from catastrophic forgetting due to the unstable training of the prompt selection mechanism caused by stark distribution shifts in coding tasks. We address this issue with our proposed method, Prompt Pooling with Teacher Forcing (PP-TF), that stabilizes training by enforcing constraints on the prompt selection mechanism and leads to a 21.54% improvement over Prompt Pooling. Along with the benchmark, we establish a training pipeline that can be used for CL on code models, which we believe can motivate further development of CL methods for code models. Our code is available at https://github.com/amazon-science/codetaskcl-pptf

We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages and are generated using a scalable conversion framework that transpiles prompts and test cases from the original Python datasets into the corresponding data in the target language. Using these benchmarks, we are able to assess the performance of code generation models in a multi-lingual fashion, and discovered generalization ability of language models on out-of-domain languages, advantages of multi-lingual models over mono-lingual, the ability of few-shot prompting to teach the model new languages, and zero-shot translation abilities even on mono-lingual settings. Furthermore, we use our code generation model to perform large-scale bootstrapping to obtain synthetic canonical solutions in several languages, which can be used for other code-related evaluations such as code insertion, robustness, or summarization tasks. Overall, our benchmarks represents a significant step towards a deeper understanding of language models' code generation abilities. We publicly release our code and datasets at https://github.com/amazon-research/mxeval.

ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint. Model compression is a promising approach to address these challenges. Several techniques are proposed to compress large pretrained models typically used for vision or textual data. Out of many available compression techniques, we identified that quantization is mostly applicable for code generation task as it does not require significant retraining cost. As quantization represents model parameters with lower-bit integer (e.g., int8), the model size and runtime latency would both benefit from such int representation. We extensively study the impact of quantized model on code generation tasks across different dimension: (i) resource usage and carbon footprint, (ii) accuracy, and (iii) robustness. To this end, through systematic experiments we find a recipe of quantization technique that could run even a $6$B model in a regular laptop without significant accuracy or robustness degradation. We further found the recipe is readily applicable to code summarization task as well.

Incorporating external knowledge into Named Entity Recognition (NER) systems has been widely studied in the generic domain. In this paper, we focus on clinical domain where only limited data is accessible and interpretability is important. Recent advancement in technology and the acceleration of clinical trials has resulted in the discovery of new drugs, procedures as well as medical conditions. These factors motivate towards building robust zero-shot NER systems which can quickly adapt to new medical terminology. We propose an auxiliary gazetteer model and fuse it with an NER system, which results in better robustness and interpretability across different clinical datasets. Our gazetteer based fusion model is data efficient, achieving +1.7 micro-F1 gains on the i2b2 dataset using 20% training data, and brings + 4.7 micro-F1 gains on novel entity mentions never presented during training. Moreover, our fusion model is able to quickly adapt to new mentions in gazetteers without re-training and the gains from the proposed fusion model are transferable to related datasets.