Citations are essential building blocks in scientific writing. The scientific community is longing for support in their generation. Citation generation involves two complementary subtasks: Determining the citation worthiness of a context and, if it's worth it, proposing the best candidate papers for the citation placeholder. The latter subtask is called local citation recommendation (LCR). This paper proposes CiteBART, a custom BART pre-training based on citation token masking to generate citations to achieve LCR. In the base scheme, we mask the citation token in the local citation context to make the citation prediction. In the global one, we concatenate the citing paper's title and abstract to the local citation context to learn to reconstruct the citation token. CiteBART outperforms state-of-the-art approaches on the citation recommendation benchmarks except for the smallest FullTextPeerRead dataset. The effect is significant in the larger benchmarks, e.g., Refseer and ArXiv. We present a qualitative analysis and an ablation study to provide insights into the workings of CiteBART. Our analyses confirm that its generative nature brings about a zero-shot capability.

Few inventions and innovations have genuinely transformed education at large, particularly by enhancing access to knowledge. Notable among these are the advent of writing around 3300 BCE, which facilitated the transmission of knowledge across generations and cultures; the Gutenberg printing press in approximately 1440 CE, which greatly simplified the duplication and dissemination of ideas and knowledge, thereby encouraging wider literacy and education; the large-scale deployment of the World Wide Web in the late 1990s and early 2000s, which allowed for rapid, affordable, and accessible information sharing via the Internet, especially through online encyclopedias such as Wikipedia; and, more recently, the public emergence of Large Language Models (LLMs) [1] in 2022, such as ChatGPT (Chat Generative Pre-Trained Transformer) [2], which have made information access even more straightforward. However, LLMs differ from previous inventions that facilitated the spread of information and knowledge in several key ways [3, 4]. While writing, the printing press, and the Internet primarily made information more accessible, LLMs provide an array of additional functions, such as multi-language translation, summarisation, simplification of complex information, and advanced writing capabilities to structure and organise content. In other words, LLMs assist people not only with accessing information but also with tasks traditionally considered cognitive.

Understanding how infants perceive speech sounds and language structures is still an open problem. Previous research in artificial neural networks has mainly focused on large dataset-dependent generative models, aiming to replicate language-related phenomena such as ''perceptual narrowing''. In this paper, we propose a novel approach using a small-sized generative neural network equipped with a continual learning mechanism based on predictive coding for mono-and bilingual speech sound learning (referred to as language sound acquisition during ''critical period'') and a compositional optimization mechanism for generation where no learning is involved (later infancy sound imitation). Our model prioritizes interpretability and demonstrates the advantages of online learning: Unlike deep networks requiring substantial offline training, our model continuously updates with new data, making it adaptable and responsive to changing inputs. Through experiments, we demonstrate that if second language acquisition occurs during later infancy, the challenges associated with learning a foreign language after the critical period amplify, replicating the perceptual narrowing effect.

Reasoning ability is essential for Large Multimodal Models (LMMs). In the absence of multimodal chain-of-thought annotated data, self-evolving training, where the model learns from its own outputs, has emerged as an effective and scalable approach for enhancing reasoning abilities. Despite its growing usage, a comprehensive understanding of self-evolving training, particularly in the context of multimodal reasoning, remains limited. In this paper, we delve into the intricacies of self-evolving training for multimodal reasoning, pinpointing three key factors: Training Method, Reward Model, and Prompt Variation. We systematically examine each factor and explore how various configurations affect the training's effectiveness. Our analysis leads to a set of best practices for each factor, aimed at optimizing multimodal reasoning. Furthermore, we explore the Self-Evolution Dynamics during training and the impact of automatic balancing mechanisms in boosting performance. After all the investigations, we present a final recipe for self-evolving training in multimodal reasoning, encapsulating these design choices into a framework we call MSTaR (Multimodal Self-evolving Training for Reasoning), which is universally effective for models with different sizes on various benchmarks, e.g., surpassing the pre-evolved model significantly on 5 multimodal reasoning benchmarks without using additional human annotations, as demonstrated on MiniCPM-V-2.5 (8B), Phi-3.5-Vision (4B) and InternVL2 (2B). We believe this study fills a significant gap in the understanding of self-evolving training for multimodal reasoning and offers a robust framework for future research. Our policy and reward models, as well as the collected data, is released to facilitate further investigation in multimodal reasoning.

To address an important gap in creating children's stories for vocabulary enrichment, we investigate the automatic evaluation of how well stories convey the semantics of target vocabulary words, a task with substantial implications for generating educational content. We motivate this task, which we call measuring contextual informativeness in children's stories, and provide a formal task definition as well as a dataset for the task. We further propose a method for automating the task using a large language model (LLM). Our experiments show that our approach reaches a Spearman correlation of 0.4983 with human judgments of informativeness, while the strongest baseline only obtains a correlation of 0.3534. An additional analysis shows that the LLM-based approach is able to generalize to measuring contextual informativeness in adult-directed text, on which it also outperforms all baselines.

Reinforcement learning from human feedback (RLHF) has become an essential step in fine-tuning large language models (LLMs) to align them with human preferences. However, human labelers are selfish and have diverse preferences. They may strategically misreport their online feedback to influence the system's aggregation towards their own preferences. Current practice simply averages labelers' feedback per time and fails to identify the most accurate human labeler, leading to linear regret $\mathcal{O}(T)$ for $T$ time slots. To our best knowledge, we are the first to study online learning mechanisms against strategic human labelers in the LLM fine-tuning process. We formulate a new dynamic Bayesian game and dynamically adjust human labelers' weights in the preference aggregation, ensuring their truthful feedback and sublinear regret $\mathcal{O}(T^{1/2})$. Simulation results demonstrate our mechanism's great advantages over the existing benchmark schemes.

Continual learning (CL) is a new online learning technique over sequentially generated streaming data from different tasks, aiming to maintain a small forgetting loss on previously-learned tasks. Existing work focuses on reducing the forgetting loss under a given task sequence. However, if similar tasks continuously appear to the end time, the forgetting loss is still huge on prior distinct tasks. In practical IoT networks, an autonomous vehicle to sample data and learn different tasks can route and alter the order of task pattern at increased travelling cost. To our best knowledge, we are the first to study how to opportunistically route the testing object and alter the task sequence in CL. We formulate a new optimization problem and prove it NP-hard. We propose a polynomial-time algorithm to achieve approximation ratios of $\frac{3}{2}$ for underparameterized case and $\frac{3}{2} + r^{1-T}$ for overparameterized case, respectively, where $r:=1-\frac{n}{m}$ is a parameter of feature number $m$ and sample number $n$ and $T$ is the task number. Simulation results verify our algorithm's close-to-optimum performance.

Counting calories just got easier. Are you tired of the endless hassle of counting calories and manually logging every meal? Say goodbye to the frustration with The Drop, the world's first fully automated nutrition tracker. This groundbreaking wearable device is designed to revolutionize how you monitor your diet, making nutrition tracking effortless and intuitive. GET SECURITY ALERTS, EXPERT TIPS - SIGN UP FOR KURT'S NEWSLETTER - THE CYBERGUY REPORT HERE The Drop is a wearable nutrition tracker powered by innovative Nutri Track technology.

Diffusion-based audio-driven talking avatar methods have recently gained attention for their high-fidelity, vivid, and expressive results. However, their slow inference speed limits practical applications. Despite the development of various distillation techniques for diffusion models, we found that naive diffusion distillation methods do not yield satisfactory results. Distilled models exhibit reduced robustness with open-set input images and a decreased correlation between audio and video compared to teacher models, undermining the advantages of diffusion models. To address this, we propose FADA (Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation). We first designed a mixed-supervised loss to leverage data of varying quality and enhance the overall model capability as well as robustness. Additionally, we propose a multi-CFG distillation with learnable tokens to utilize the correlation between audio and reference image conditions, reducing the threefold inference runs caused by multi-CFG with acceptable quality degradation. Extensive experiments across multiple datasets show that FADA generates vivid videos comparable to recent diffusion model-based methods while achieving an NFE speedup of 4.17-12.5 times. Demos are available at our webpage http://fadavatar.github.io.

In the absence of extensive human-annotated data for complex reasoning tasks, self-improvement -- where models are trained on their own outputs -- has emerged as a primary method for enhancing performance. However, the critical factors underlying the mechanism of these iterative self-improving methods remain poorly understood, such as under what conditions self-improvement is effective, and what are the bottlenecks in the current iterations. In this work, we identify and propose methods to monitor two pivotal factors in this iterative process: (1) the model's ability to generate sufficiently diverse responses (exploration); and (2) the effectiveness of external rewards in distinguishing high-quality candidates from lower-quality ones (exploitation). Using mathematical reasoning as a case study, we begin with a quantitative analysis to track the dynamics of exploration and exploitation, discovering that a model's exploratory capabilities rapidly deteriorate over iterations, and the effectiveness of exploiting external rewards diminishes as well. Motivated by these findings, we introduce B-STaR, a Self-Taught Reasoning framework that autonomously adjusts configurations across iterations to Balance exploration and exploitation, thereby optimizing the self-improving effectiveness based on the current policy model and available rewards. Our experiments on mathematical reasoning, coding, and commonsense reasoning demonstrate that B-STaR not only enhances the model's exploratory capabilities throughout training but also achieves a more effective balance between exploration and exploitation, leading to superior performance.