Silicon vs. Carbon

Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. While previous work looked into where factual associations are stored, only little is known about how they are retrieved internally during inference. We investigate this question through the lens of information flow. Given a subject-relation query, we study how the model aggregates information about the subject and relation to predict the correct attribute. With interventions on attention edges, we first identify two critical points where information propagates to the prediction: one from the relation positions followed by another from the subject positions. Next, by analyzing the information at these points, we unveil a three-step internal mechanism for attribute extraction. First, the representation at the last-subject position goes through an enrichment process, driven by the early MLP sublayers, to encode many subject-related attributes. Second, information from the relation propagates to the prediction. Third, the prediction representation "queries" the enriched subject to extract the attribute. Perhaps surprisingly, this extraction is typically done via attention heads, which often encode subject-attribute mappings in their parameters. Overall, our findings introduce a comprehensive view of how factual associations are stored and extracted internally in LMs, facilitating future research on knowledge localization and editing.

Generate embedding vectors from audio files. Contribute to IBM/MAX-Audio-Embedding-Generator development by creating an account on GitHub.

Rotational motions of organic cations may screen charge carriers from defects

Language models are increasingly attracting interest from writers. However, such models lack long-range semantic coherence, limiting their usefulness for longform creative writing. We address this limitation by applying language models hierarchically, in a system we call Dramatron. By building structural context via prompt chaining, Dramatron can generate coherent scripts and screenplays complete with title, characters, story beats, location descriptions, and dialogue. We illustrate Dramatron's usefulness as an interactive co-creative system with a user study of 15 theatre and film industry professionals. Participants co-wrote theatre scripts and screenplays with Dramatron and engaged in open-ended interviews. We report critical reflections both from our interviewees and from independent reviewers who watched stagings of the works to illustrate how both Dramatron and hierarchical text generation could be useful for human-machine co-creativity. Finally, we discuss the suitability of Dramatron for co-creativity, ethical considerations -- including plagiarism and bias -- and participatory models for the design and deployment of such tools.

While originally designed for natural language processing tasks, the self-attention mechanism has recently taken various computer vision areas by storm. However, the 2D nature of images brings three challenges for applying self-attention in computer vision. (1) Treating images as 1D sequences neglects their 2D structures. (2) The quadratic complexity is too expensive for high-resolution images. (3) It only captures spatial adaptability but ignores channel adaptability. In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings. Furthermore, we present a neural network based on LKA, namely Visual Attention Network (VAN). While extremely simple, VAN surpasses similar size vision transformers(ViTs) and convolutional neural networks(CNNs) in various tasks, including image classification, object detection, semantic segmentation, panoptic segmentation, pose estimation, etc. For example, VAN-B6 achieves 87.8% accuracy on ImageNet benchmark and set new state-of-the-art performance (58.2 PQ) for panoptic segmentation. Besides, VAN-B2 surpasses Swin-T 4% mIoU (50.1 vs. 46.1) for semantic segmentation on ADE20K benchmark, 2.6% AP (48.8 vs. 46.2) for object detection on COCO dataset. It provides a novel method and a simple yet strong baseline for the community. Code is available at https://github.com/Visual-Attention-Network.

Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted significant attention due to their ability to generate high-quality synthetic images. In this work, we show...

Human Body Communication (HBC) has come up as a promising alternative to traditional radio frequency (RF) Wireless Body Area Network (WBAN) technologies. This is essentially due to HBC providing a broadband communication channel with enhanced signal security in the physical layer due to lower radiation from the human body as compared to its RF counterparts. An in-depth understanding of the mechanism for the channel loss variability and associated biophysical model needs to be developed before EQS-HBC can be used more frequently in WBAN consumer and medical applications. Biophysical models characterizing the human body as a communication channel didn't exist in literature for a long time. Recent developments have shown models that capture the channel response for fixed transmitter and receiver positions on the human body. These biophysical models do not capture the variability in the HBC channel for varying positions of the devices with respect to the human body. In this study, we provide a detailed analysis of the change in path loss in a capacitive-HBC channel in the electroquasistatic (EQS) domain. Causes of channel loss variability namely: inter-device coupling and effects of fringe fields due to body's shadowing effects are investigated. FEM based simulation results are used to analyze the channel response of human body for different positions and sizes of the device which are further verified using measurement results to validate the developed biophysical model. Using the bio-physical model, we develop a closed form equation for the path loss in a capacitive HBC channel which is then analyzed as a function of the geometric properties of the device and the position with respect to the human body which will help pave the path towards future EQSHBC WBAN design.

Artificial intelligence (AI) has the potential to greatly improve society, but as with any powerful technology, it comes with heightened risks and responsibilities. Current AI research lacks a systematic discussion of how to manage long-tail risks from AI systems, including speculative long-term risks. Keeping in mind the potential benefits of AI, there is some concern that building ever more intelligent and powerful AI systems could eventually result in systems that are more powerful than us; some say this is like playing with fire and speculate that this could create existential risks (x-risks). To add precision and ground these discussions, we provide a guide for how to analyze AI x-risk, which consists of three parts: First, we review how systems can be made safer today, drawing on time-tested concepts from hazard analysis and systems safety that have been designed to steer large processes in safer directions. Next, we discuss strategies for having long-term impacts on the safety of future systems. Finally, we discuss a crucial concept in making AI systems safer by improving the balance between safety and general capabilities. We hope this document and the presented concepts and tools serve as a useful guide for understanding how to analyze AI x-risk.

“More and more researchers think that building AIs smarter than us could pose existential risks. But what might these risks look like, and how can we manage them? We provide a guide to help analyze how research can reduce these risks. Paper: https://t.co/SHCwaClRHA (🧵below)”

null

Recent advancements in decision-making large language model (LLM) agents have demonstrated impressive performance across various benchmarks. However, these state-of-the-art approaches typically...

In this work, we establish dense correspondences between RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We first gather dense...

Generative AI can be used in libraries in databases, in the chat systems librarians use, and in cataloging.

Why we need to understand how our models make predictions

Setting the right course and steering responsibly

If software ate the world, models will run it. But are we ready to be controlled by blackbox intelligent softwares?

null

Card et al.'s classic paper "The Design Space of Input Devices" established the value of design spaces as a tool for HCI analysis and invention. We posit that developing design spaces for emerging pre-trained, generative AI models is necessary for supporting their integration into human-centered systems and practices. We explore what it means to develop an AI model design space by proposing two design spaces relating to generative AI models: the first considers how HCI can impact generative models (i.e., interfaces for models) and the second considers how generative models can impact HCI (i.e., models as an HCI prototyping material).

The Hyena code is able to handle amounts of data that make GPT-style technology run out of memory and fail.

Increased capabilities such as recognition and self-adaptability are now required from IoT applications. While IoT node power consumption is a major concern for these applications, cloud-based processing is becoming unsustainable due to continuous sensor or image data transmission over the wireless network. Thus optimized ML capabilities and data transfers should be integrated in the IoT node. Moreover, IoT applications are torn between sporadic data-logging and energy-hungry data processing (e.g. image classification). Thus, the versatility of the node is key in addressing this wide diversity of energy and processing needs. This paper presents SamurAI, a versatile IoT node bridging this gap in processing and in energy by leveraging two on-chip sub-systems: a low power, clock-less, event-driven Always-Responsive (AR) part and an energy-efficient On-Demand (OD) part. AR contains a 1.7MOPS event-driven, asynchronous Wake-up Controller (WuC) with a 207ns wake-up time optimized for sporadic computing, while OD combines a deep-sleep RISC-V CPU and 1.3TOPS/W Machine Learning (ML) for more complex tasks up to 36GOPS. This architecture partitioning achieves best in class versatility metrics such as peak performance to idle power ratio. On an applicative classification scenario, it demonstrates system power gains, up to 3.5x compared to cloud-based processing, and thus extended battery lifetime.

Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators and revise our interpretations as listeners. As language models (LMs) are increasingly employed as dialogue interfaces and writing aids, handling ambiguous language is critical to their success. We characterize ambiguity in a sentence by its effect on entailment relations with another sentence, and collect AmbiEnt, a linguist-annotated benchmark of 1,645 examples with diverse kinds of ambiguity. We design a suite of tests based on AmbiEnt, presenting the first evaluation of pretrained LMs to recognize ambiguity and disentangle possible meanings. We find that the task remains extremely challenging, including for the recent GPT-4, whose generated disambiguations are considered correct only 32% of the time in human evaluation, compared to 90% for disambiguations in our dataset. Finally, to illustrate the value of ambiguity-sensitive tools, we show that a multilabel NLI model can flag political claims in the wild that are misleading due to ambiguity. We encourage the field to rediscover the importance of ambiguity for NLP.

Many RL problems have hierarchical tree-like nature. Hyperbolic geometry offers a powerful prior for such problems.

In a large class of deep learning models, including vector embedding models such as word and database embeddings, we observe that floating point exponent values cluster around a few unique values, permitting entropy based data compression. Entropy coding compresses fixed-length values with variable-length codes, encoding most probable values with fewer bits. We propose the EFloat compressed floating point number format that uses a variable field boundary between the exponent and significand fields. EFloat uses entropy coding on exponent values and signs to minimize the average width of the exponent and sign fields, while preserving the original FP32 exponent range unchanged. Saved bits become part of the significand field increasing the EFloat numeric precision by 4.3 bits on average compared to other reduced-precision floating point formats. EFloat makes 8-bit and even smaller floats practical without sacrificing the exponent range of a 32-bit floating point representation. We currently use the EFloat format for saving memory capacity and bandwidth consumption of large vector embedding models such as those used for database embeddings. Using the RMS error as metric, we demonstrate that EFloat provides higher accuracy than other floating point formats with equal bit budget. The EF12 format with 12-bit budget has less end-to-end application error than the 16-bit BFloat16. EF16 with 16-bit budget has an RMS-error 17 to 35 times less than BF16 RMS-error for a diverse set of embedding models. When making similarity and dissimilarity queries, using the NDCG ranking metric, EFloat matches the result quality of prior floating point representations with larger bit budgets.

Like in many other research areas, deep learning (DL) is increasingly adopted in music recommendation systems (MRS). Deep neural networks are used in this domain particularly for extracting latent factors of music items from audio signals or metadata and for learning sequential patterns of music items (tracks or artists) from music playlists or listening sessions. Latent item factors are commonly integrated into content-based filtering and hybrid MRS, whereas sequence models of music items are used for sequential music recommendation, e.g., automatic playlist continuation. This review article explains particularities of the music domain in RS research. It gives an overview of the state of the art that employs deep learning for music recommendation. The discussion is structured according to the dimensions of neural network type, input data, recommendation approach (content-based filtering, collaborative filtering, or both), and task (standard or sequential music recommendation). In addition, we discuss major challenges faced in MRS, in particular in the context of the current research on deep learning.

Model compression, such as pruning and quantization, has been widely applied to optimize neural networks on resource-limited classical devices. Recently, there are growing interest in variational quantum circuits (VQC), that is, a type of neural network on quantum computers (a.k.a., quantum neural networks). It is well known that the near-term quantum devices have high noise and limited resources (i.e., quantum bits, qubits); yet, how to compress quantum neural networks has not been thoroughly studied. One might think it is straightforward to apply the classical compression techniques to quantum scenarios. However, this paper reveals that there exist differences between the compression of quantum and classical neural networks. Based on our observations, we claim that the compilation/traspilation has to be involved in the compression process. On top of this, we propose the very first systematical framework, namely CompVQC, to compress quantum neural networks (QNNs).In CompVQC, the key component is a novel compression algorithm, which is based on the alternating direction method of multipliers (ADMM) approach. Experiments demonstrate the advantage of the CompVQC, reducing the circuit depth (almost over 2.5 %) with a negligible accuracy drop (1%), which outperforms other competitors. Another promising truth is our CompVQC can indeed promote the robustness of the QNN on the near-term noisy quantum devices.