Our approach capitalizes on diffusion models and transferring their representations to denoising diffusion models [14], which are excellent representations this task, we learn a conditional diffusion model for reconstructing of the natural image manifold and capture all whole objects in challenging zero-shot cases, including different types of whole objects and their occlusions. Due examples that break natural and physical priors, to their large-scale training data, we hypothesize such pretrained such as art. As training data, we use a synthetically curated models have implicitly learned amodal representations dataset containing occluded objects paired with their whole (Figure 2), which we can reconfigure to encode object counterparts. Experiments show that our approach outperforms grouping and perform amodal completion. By learning supervised baselines on established benchmarks. Our from a synthetic dataset of occlusions and their whole counterparts, model can furthermore be used to significantly improve the we create a conditional diffusion model that, given performance of existing object recognition and 3D reconstruction an RGB image and a point prompt, generates whole objects methods in the presence of occlusions.

The lack of high-quality data for content-grounded generation tasks has been identified as a major obstacle to advancing these tasks. To address this gap, we propose Genie, a novel method for automatically generating high-quality content-grounded data. It consists of three stages: (a) Content Preparation, (b) Generation: creating task-specific examples from the content (e.g., question-answer pairs or summaries). (c) Filtering mechanism aiming to ensure the quality and faithfulness of the generated data. We showcase this methodology by generating three large-scale synthetic data, making wishes, for Long-Form Question-Answering (LFQA), summarization, and information extraction. In a human evaluation, our generated data was found to be natural and of high quality. Furthermore, we compare models trained on our data with models trained on human-written data -- ELI5 and ASQA for LFQA and CNN-DailyMail for Summarization. We show that our models are on par with or outperforming models trained on human-generated data and consistently outperforming them in faithfulness. Finally, we applied our method to create LFQA data within the medical domain and compared a model trained on it with models trained on other domains.

Research from the field of Computer-Supported Cooperative Work(CSCW), including the emergent area of Human-AI interaction, has increasingly examined the societal gaps that prevent people in need from accessing care, and analyzed how people turn to technology-mediated support to fill those gaps[14, 27, 44]. Large Language Model (LLM) chatbots have quickly become one such tool, quickly appropriated for mental health support by people experiencing severe distress and nowhere else to turn. Recent work has discussed how people in distress have turned to LLM chatbots (such as OpenAI's ChatGPT [8, 10] and Replika [28]) for mental health support, and social media users have described how LLM chatbots saved their lives[10, 47]. Following Freud and Breuer's[19] description of the beneficial nature of psychoanalysis as a "talking cure," some have called engagements with technologies for mental health a typing cure [22, 40, 51]. However, others have cautioned against the use of LLM chatbots for mental health support, noting that the outputs of LLM chatbots are less constrained than the rule-based chatbots of the past, with potential for harmful advice or recommendations. For example, the National Eating Disorder Association was forced to shut down their support chatbot in July 2023 after the chatbot provided harmful recommendations to users, including weight loss and dieting advice to users who may already have been struggling with disordered eating [10, 25, 75].

This paper presents MoE-Infinity, a cost-efficient mixture-of-expert (MoE) serving system that realizes activation-aware expert offloading. MoE-Infinity features sequence-level expert activation tracing, a new approach adept at identifying sparse activations and capturing the temporal locality of MoE inference. By analyzing these traces, MoE-Infinity performs novel activation-aware expert prefetching and caching, substantially reducing the latency overheads usually associated with offloading experts for improved cost performance. Extensive experiments in a cluster show that MoE-Infinity outperforms numerous existing systems and approaches, reducing latency by 4 - 20X and decreasing deployment costs by over 8X for various MoEs. MoE-Infinity's source code is publicly available at https://github.com/TorchMoE/MoE-Infinity

Furthermore, LLM inference latency is difficult to predict because their response time depends on the output This paper presents ServerlessLLM, a locality-enhanced length, which can vary significantly [24, 39, 77], due to iterative serverless inference system for Large Language Models output token generation. To achieve low latency, processing (LLMs). ServerlessLLM exploits the substantial capacity and an LLM request often necessitates the use of several bandwidth of storage and memory devices available on GPU GPUs for durations ranging from seconds to minutes. In practice, servers, thereby reducing costly remote checkpoint downloads LLM service providers need to host a large number of and achieving efficient checkpoint loading. ServerlessLLM LLMs catered to different developers, leading to significant achieves this through three main contributions: (i) fast LLM GPU consumption [15] and impeding the sustainability of checkpoint loading via a novel loading-optimized checkpoint LLM services [19]. As a result, LLM inference services have format design, coupled with an efficient multi-tier checkpoint to impose strict caps on the number of requests sent to their loading system; (ii) locality-driven LLM inference with live services from their users (e.g., 40 messages per 3 hours for migration, which allows ServerlessLLM to effectively achieve ChatGPT [51]), showing the provider's current inability to locality-driven server allocation while preserving the low latency satisfy the LLM inference demand. Researchers [19] project of ongoing LLM inference; and (iii) locality-aware that LLM inference costs may increase by > 50 when it server allocation, enabling ServerlessLLM to evaluate the status reaches the popularity of Google Search. of each server in a cluster and effectively schedule model To reduce GPU consumption, LLM service providers are startup time to capitalize on local checkpoint placement. Our exploring serverless inference, as seen in systems like Amazon comprehensive experiments, which include microbenchmarks SageMaker [60], Azure [46], KServe [11] and Hugging-and real-world traces, show that ServerlessLLM surpasses Face [31].

The field of natural language processing (NLP) has witnessed significant progress in recent years, with a notable focus on improving large language models' (LLM) performance through innovative prompting techniques. Among these, prompt engineering coupled with structures has emerged as a promising paradigm, with designs such as Chain-of-Thought, Tree of Thoughts, or Graph of Thoughts, in which the overall LLM reasoning is guided by a structure such as a graph. As illustrated with numerous examples, this paradigm significantly enhances the LLM's capability to solve numerous tasks, ranging from logical or mathematical reasoning to planning or creative writing. To facilitate the understanding of this growing field and pave the way for future developments, we devise a general blueprint for effective and efficient LLM reasoning schemes. For this, we conduct an in-depth analysis of the prompt execution pipeline, clarifying and clearly defining different concepts. We then build the first taxonomy of structure-enhanced LLM reasoning schemes. We focus on identifying fundamental classes of harnessed structures, and we analyze the representations of these structures, algorithms executed with these structures, and many others. We refer to these structures as reasoning topologies, because their representation becomes to a degree spatial, as they are contained within the LLM context. Our study compares existing prompting schemes using the proposed taxonomy, discussing how certain design choices lead to different patterns in performance and cost. We also outline theoretical underpinnings, relationships between prompting and others parts of the LLM ecosystem such as knowledge bases, and the associated research challenges. Our work will help to advance future prompt engineering techniques.

This study addresses the challenge of extending Large Language Models (LLMs) to non-English languages, specifically those using non-Latin scripts. We propose an innovative approach that utilizes the romanized form of text as an interface for LLMs, hypothesizing that its frequent informal use and shared tokens with English enhance cross-lingual alignment. Focusing on Hindi, we demonstrate through Hindi-to-English translation and sentiment analysis tasks that romanized text not only significantly improves inference efficiency due to its lower fertility compared to native text but also achieves competitive performance with limited pre-training. Additionally, our novel multi-script prompting approach, which combines romanized and native texts, shows promise in further enhancing task performance. These findings suggest the potential of romanization in bridging the language gap for LLM applications, with future work aimed at expanding this approach to more languages and tasks.

Technical question and answering (Q&A) sites such as Stack Overflow have become an important source for software developers to seek knowledge. However, code snippets on Q&A sites are usually uncompilable and semantically incomplete for compilation due to unresolved types and missing dependent libraries, which raises the obstacle for users to reuse or analyze Q&A code snippets. Prior approaches either are not designed for synthesizing compilable code or suffer from a low compilation success rate. To address this problem, we propose ZS4C, a lightweight approach to perform zero-shot synthesis of compilable code from incomplete code snippets using Large Language Model (LLM). ZS4C operates in two stages. In the first stage, ZS4C utilizes an LLM, i.e., ChatGPT, to identify missing import statements for a given code snippet, leveraging our designed task-specific prompt template. In the second stage, ZS4C fixes compilation errors caused by incorrect import statements and syntax errors through collaborative work between ChatGPT and a compiler. We thoroughly evaluated ZS4C on a widely used benchmark called StatType-SO against the SOTA approach SnR. Compared with SnR, ZS4C improves the compilation rate from 63% to 87.6%, with a 39.3% improvement. On average, ZS4C can infer more accurate import statements than SnR, with an improvement of 6.6% in the F1.

The capabilities of transformer networks such as ChatGPT and other Large Language Models (LLMs) have captured the world's attention. The crucial computational mechanism underlying their performance relies on transforming a complete input sequence - for example, all the words in a sentence into a long "encoding vector" - that allows transformers to learn long-range temporal dependencies in naturalistic sequences. Specifically, "self-attention" applied to this encoding vector enhances temporal context in transformers by computing associations between pairs of words in the input sequence. We suggest that waves of neural activity, traveling across single cortical regions or across multiple regions at the whole-brain scale, could implement a similar encoding principle. By encapsulating recent input history into a single spatial pattern at each moment in time, cortical waves may enable temporal context to be extracted from sequences of sensory inputs, the same computational principle used in transformers.

Code large language models (Code LLMs) have demonstrated remarkable performance in code generation. Nonetheless, most existing works focus on boosting code LLMs from the perspective of programming capabilities, while their natural language capabilities receive less attention. To fill this gap, we thus propose a novel framework, comprising two modules: AttentionExtractor, which is responsible for extracting key phrases from the user's natural language requirements, and AttentionCoder, which leverages these extracted phrases to generate target code to solve the requirement. This framework pioneers an innovative idea by seamlessly integrating code LLMs with traditional natural language processing tools. To validate the effectiveness of the framework, we craft a new code generation benchmark, called MultiNL-H, covering five natural languages. Extensive experimental results demonstrate the effectiveness of our proposed framework.