PyTorchKR Papers

최신 논문

총 1,461편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2401.00953공식 코드 · Papers with Code

Families of costs with zero and nonnegative MTW tensor in optimal transport

We compute explicitly the MTW tensor (or cross curvature) for the optimal transport problem on $\mathbb{R}^n$ with a cost function of form $\mathsf{c}(x, y) = \mathsf{u}(x^{\mathfrak{t}}y)$, where $\mathsf{u}$ is a scalar function with inverse $\mathsf{s}$, $x^{\ft}y$ is a nondegenerate bilinear pairing of vectors $x, y$ belonging to an open subset of $\mathbb{R}^n$. The condition that the MTW-tensor vanishes on null vectors under the Kim-McCann metric is a fourth-order nonlinear ODE, which could be reduced to a linear ODE of the form $\mathsf{s}^{(2)} - S\mathsf{s}^{(1)} + P\mathsf{s} = 0$ with constant coefficients $P$ and $S$. The resulting inverse functions include {\it Lambert} and {\it generalized inverse hyperbolic\slash trigonometric} functions. The square Euclidean metric and $\log$-type costs are equivalent to instances of these solutions. The optimal map for the family is also explicit. For cost functions of a similar form on a hyperboloid model of the hyperbolic space and unit sphere, we also express this tensor in terms of algebraic expressions in derivatives of $\mathsf{s}$ using the Gauss-Codazzi equation, obtaining new families of strictly regular costs for these manifolds, including new families of {\it power function costs}. We analyze the $\sinh$-type hyperbolic cost, providing examples of $\mathsf{c}$-convex functions and divergence.

arXiv:2401.00282공식 코드 · Papers with Code

Deep Generative Symbolic Regression

Symbolic regression (SR) aims to discover concise closed-form mathematical equations from data, a task fundamental to scientific discovery. However, the problem is highly challenging because closed-form equations lie in a complex combinatorial search space. Existing methods, ranging from heuristic search to reinforcement learning, fail to scale with the number of input variables. We make the observation that closed-form equations often have structural characteristics and invariances (e.g., the commutative law) that could be further exploited to build more effective symbolic regression solutions. Motivated by this observation, our key contribution is to leverage pre-trained deep generative models to capture the intrinsic regularities of equations, thereby providing a solid foundation for subsequent optimization steps. We show that our novel formalism unifies several prominent approaches of symbolic regression and offers a new perspective to justify and improve on the previous ad hoc designs, such as the usage of cross-entropy loss during pre-training. Specifically, we propose an instantiation of our framework, Deep Generative Symbolic Regression (DGSR). In our experiments, we show that DGSR achieves a higher recovery rate of true equations in the setting of a larger number of input variables, and it is more computationally efficient at inference time than state-of-the-art RL symbolic regression solutions.

arXiv:2308.09126공식 코드 · Papers with Code

EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

We introduce EgoSchema, a very long-form video question-answering dataset, and benchmark to evaluate long video understanding capabilities of modern vision and language systems. Derived from Ego4D, EgoSchema consists of over 5000 human curated multiple choice question answer pairs, spanning over 250 hours of real video data, covering a very broad range of natural human activity and behavior. For each question, EgoSchema requires the correct answer to be selected between five given options based on a three-minute-long video clip. While some prior works have proposed video datasets with long clip lengths, we posit that merely the length of the video clip does not truly capture the temporal difficulty of the video task that is being considered. To remedy this, we introduce temporal certificate sets, a general notion for capturing the intrinsic temporal understanding length associated with a broad range of video understanding tasks & datasets. Based on this metric, we find EgoSchema to have intrinsic temporal lengths over 5.7x longer than the second closest dataset and 10x to 100x longer than any other video understanding dataset. Further, our evaluation of several current state-of-the-art video and language models shows them to be severely lacking in long-term video understanding capabilities. Even models with several billions of parameters achieve QA accuracy less than 33% (random is 20%) on the EgoSchema multi-choice question answering task, while humans achieve about 76% accuracy. We posit that \name{}{}, with its long intrinsic temporal structures and diverse complexity, would serve as a valuable evaluation probe for developing effective long-term video understanding systems in the future. Data and Zero-shot model evaluation code are open-sourced for both public and commercial use under the Ego4D license at http://egoschema.github.io

arXiv:2312.15272공식 코드 · Papers with Code

Detecting anxiety from short clips of free-form speech

Barriers to accessing mental health assessments including cost and stigma continues to be an impediment in mental health diagnosis and treatment. Machine learning approaches based on speech samples could help in this direction. In this work, we develop machine learning solutions to diagnose anxiety disorders from audio journals of patients. We work on a novel anxiety dataset (provided through collaboration with Kintsugi Mindful Wellness Inc.) and experiment with several models of varying complexity utilizing audio, text and a combination of multiple modalities. We show that the multi-modal and audio embeddings based approaches achieve good performance in the task achieving an AUC ROC score of 0.68-0.69.

arXiv:2312.12726공식 코드 · Papers with Code

Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method

Neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view images of a 3D scene. It includes density and color fields to model the shape and radiance of a scene, respectively. Supervised by the photometric loss in an end-to-end training manner, NeRF inherently suffers from the shape-radiance ambiguity problem, i.e., it can perfectly fit training views but does not guarantee decoupling the two fields correctly. To deal with this issue, existing works have incorporated prior knowledge to provide an independent supervision signal for the density field, including total variation loss, sparsity loss, distortion loss, etc. These losses are based on general assumptions about the density field, e.g., it should be smooth, sparse, or compact, which are not adaptive to a specific scene. In this paper, we propose a more adaptive method to reduce the shape-radiance ambiguity. The key is a rendering method that is only based on the density field. Specifically, we first estimate the color field based on the density field and posed images in a closed form. Then NeRF's rendering process can proceed. We address the problems in estimating the color field, including occlusion and non-uniformly distributed views. Afterward, it is applied to regularize NeRF's density field. As our regularization is guided by photometric loss, it is more adaptive compared to existing ones. Experimental results show that our method improves the density field of NeRF both qualitatively and quantitatively. Our code is available at https://github.com/qihangGH/Closed-form-color-field.

arXiv:2312.11897

Text-Conditioned Resampler For Long Form Video Understanding

In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task. TCR localises relevant visual features from the video given a text condition and provides them to a LLM to generate a text response. Due to its lightweight design and use of cross-attention, TCR can process more than 100 frames at a time with plain attention and without optimised implementations. We make the following contributions: (i) we design a transformer-based sampling architecture that can process long videos conditioned on a task, together with a training method that enables it to bridge pre-trained visual and language models; (ii) we identify tasks that could benefit from longer video perception; and (iii) we empirically validate its efficacy on a wide variety of evaluation tasks including NextQA, EgoSchema, and the EGO4D-LTA challenge.

arXiv:2312.11123

Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers

ASR models often suffer from a long-form deletion problem where the model predicts sequential blanks instead of words when transcribing a lengthy audio (in the order of minutes or hours). From the perspective of a user or downstream system consuming the ASR results, this behavior can be perceived as the model "being stuck", and potentially make the product hard to use. One of the culprits for long-form deletion is training-test data mismatch, which can happen even when the model is trained on diverse and large-scale data collected from multiple application domains. In this work, we introduce a novel technique to simultaneously model different groups of speakers in the audio along with the standard transcript tokens. Speakers are grouped as primary and non-primary, which connects the application domains and significantly alleviates the long-form deletion problem. This improved model neither needs any additional training data nor incurs additional training or inference cost.

arXiv:2312.11063

A survey on algorithms for Nash equilibria in finite normal-form games

Nash equilibrium is one of the most influential solution concepts in game theory. With the development of computer science and artificial intelligence, there is an increasing demand on Nash equilibrium computation, especially for Internet economics and multi-agent learning. This paper reviews various algorithms computing the Nash equilibrium and its approximation solutions in finite normal-form games from both theoretical and empirical perspectives. For the theoretical part, we classify algorithms in the literature and present basic ideas on algorithm design and analysis. For the empirical part, we present a comprehensive comparison on the algorithms in the literature over different kinds of games. Based on these results, we provide practical suggestions on implementations and uses of these algorithms. Finally, we present a series of open problems from both theoretical and practical considerations.

arXiv:2312.11281공식 코드 · Papers with Code

Human mobility is well described by closed-form gravity-like models learned automatically from data

Modeling of human mobility is critical to address questions in urban planning and transportation, as well as global challenges in sustainability, public health, and economic development. However, our understanding and ability to model mobility flows within and between urban areas are still incomplete. At one end of the modeling spectrum we have simple so-called gravity models, which are easy to interpret and provide modestly accurate predictions of mobility flows. At the other end, we have complex machine learning and deep learning models, with tens of features and thousands of parameters, which predict mobility more accurately than gravity models at the cost of not being interpretable and not providing insight on human behavior. Here, we show that simple machine-learned, closed-form models of mobility are able to predict mobility flows more accurately, overall, than either gravity or complex machine and deep learning models. At the same time, these models are simple and gravity-like, and can be interpreted in terms similar to standard gravity models. Furthermore, these models work for different datasets and at different scales, suggesting that they may capture the fundamental universal features of human mobility.

arXiv:2312.09852공식 코드 · Papers with Code

Learning Distributions on Manifolds with Free-Form Flows

We propose Manifold Free-Form Flows (M-FFF), a simple new generative model for data on manifolds. The existing approaches to learning a distribution on arbitrary manifolds are expensive at inference time, since sampling requires solving a differential equation. Our method overcomes this limitation by sampling in a single function evaluation. The key innovation is to optimize a neural network via maximum likelihood on the manifold, possible by adapting the free-form flow framework to Riemannian manifolds. M-FFF is straightforwardly adapted to any manifold with a known projection. It consistently matches or outperforms previous single-step methods specialized to specific manifolds. It is typically two orders of magnitude faster than multi-step methods based on diffusion or flow matching, achieving better likelihoods in several experiments. We provide our code at https://github.com/vislearn/FFF.

arXiv:2312.09222

Mosaic-SDF for 3D Generative Models

Current diffusion or flow-based generative models for 3D shapes divide to two: distilling pre-trained 2D image diffusion models, and training directly on 3D shapes. When training a diffusion or flow models on 3D shapes a crucial design choice is the shape representation. An effective shape representation needs to adhere three design principles: it should allow an efficient conversion of large 3D datasets to the representation form; it should provide a good tradeoff of approximation power versus number of parameters; and it should have a simple tensorial form that is compatible with existing powerful neural architectures. While standard 3D shape representations such as volumetric grids and point clouds do not adhere to all these principles simultaneously, we advocate in this paper a new representation that does. We introduce Mosaic-SDF (M-SDF): a simple 3D shape representation that approximates the Signed Distance Function (SDF) of a given shape by using a set of local grids spread near the shape's boundary. The M-SDF representation is fast to compute for each shape individually making it readily parallelizable; it is parameter efficient as it only covers the space around the shape's boundary; and it has a simple matrix form, compatible with Transformer-based architectures. We demonstrate the efficacy of the M-SDF representation by using it to train a 3D generative flow model including class-conditioned generation with the 3D Warehouse dataset, and text-to-3D generation using a dataset of about 600k caption-shape pairs.

arXiv:2312.07637

Responsibility in Extensive Form Games

Two different forms of responsibility, counterfactual and seeing-to-it, have been extensively discussed in the philosophy and AI in the context of a single agent or multiple agents acting simultaneously. Although the generalisation of counterfactual responsibility to a setting where multiple agents act in some order is relatively straightforward, the same cannot be said about seeing-to-it responsibility. Two versions of seeing-to-it modality applicable to such settings have been proposed in the literature. Neither of them perfectly captures the intuition of responsibility. This paper proposes a definition of seeing-to-it responsibility for such settings that amalgamate the two modalities. This paper shows that the newly proposed notion of responsibility and counterfactual responsibility are not definable through each other and studies the responsibility gap for these two forms of responsibility. It shows that although these two forms of responsibility are not enough to ascribe responsibility in each possible situation, this gap does not exist if higher-order responsibility is taken into account.

arXiv:2312.05269공식 코드 · Papers with Code

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity descriptions of the camera wearer and leverages the zero-shot capabilities of pretrained large language models to perform reasoning over long-form video context. Furthermore, LifelongMemory uses a confidence and explanation module to produce confident, high-quality, and interpretable answers. Our approach achieves state-of-the-art performance on the EgoSchema benchmark for question answering and is highly competitive on the natural language query (NLQ) challenge of Ego4D. Code is available at https://github.com/agentic-learning-ai-lab/lifelong-memory.

arXiv:2312.04817

MoVQA: A Benchmark of Versatile Question-Answering for Long-Form Movie Understanding

While several long-form VideoQA datasets have been introduced, the length of both videos used to curate questions and sub-clips of clues leveraged to answer those questions have not yet reached the criteria for genuine long-form video understanding. Moreover, their QAs are unduly narrow and modality-biased, lacking a wider view of understanding long-term video content with rich dynamics and complex narratives. To remedy this, we introduce MoVQA, a long-form movie question-answering dataset, and benchmark to assess the diverse cognitive capabilities of multimodal systems rely on multi-level temporal lengths, with considering both video length and clue length. Additionally, to take a step towards human-level understanding in long-form video, versatile and multimodal question-answering is designed from the moviegoer-perspective to assess the model capabilities on various perceptual and cognitive axes.Through analysis involving various baselines reveals a consistent trend: the performance of all methods significantly deteriorate with increasing video and clue length. Meanwhile, our established baseline method has shown some improvements, but there is still ample scope for enhancement on our challenging MoVQA dataset. We expect our MoVQA to provide a new perspective and encourage inspiring works on long-form video understanding research.

arXiv:2312.03391공식 코드 · Papers with Code

Action Scene Graphs for Long-Form Understanding of Egocentric Videos

We present Egocentric Action Scene Graphs (EASGs), a new representation for long-form understanding of egocentric videos. EASGs extend standard manually-annotated representations of egocentric videos, such as verb-noun action labels, by providing a temporally evolving graph-based description of the actions performed by the camera wearer, including interacted objects, their relationships, and how actions unfold in time. Through a novel annotation procedure, we extend the Ego4D dataset by adding manually labeled Egocentric Action Scene Graphs offering a rich set of annotations designed for long-from egocentric video understanding. We hence define the EASG generation task and provide a baseline approach, establishing preliminary benchmarks. Experiments on two downstream tasks, egocentric action anticipation and egocentric activity summarization, highlight the effectiveness of EASGs for long-form egocentric video understanding. We will release the dataset and the code to replicate experiments and annotations.

arXiv:2312.01785

Closed-Form Solutions for Grid-Forming Converters: A Design-Oriented Study

This paper derives closed-form solutions for grid-forming converters with power synchronization control (PSC) by subtly simplifying and factorizing the complex closed-loop models. The solutions can offer clear analytical insights into control-loop interactions, enabling guidelines for robust controller design. It is proved that 1) the proportional gains of PSC and alternating voltage control (AVC) can introduce negative resistance, which aggravates synchronous resonance (SR) of power control, 2) the integral gain of AVC is the cause of sub-synchronous resonance (SSR) in stiff-grid interconnections, albeit the proportional gain of AVC can help dampen the SSR, and 3) surprisingly, the current controller that dampens SR actually exacerbates SSR. Controller design guidelines are given based on analytical insights. The findings are verified by simulations and experimental results.

arXiv:2312.02804

Score-Aware Policy-Gradient Methods and Performance Guarantees using Local Lyapunov Conditions: Applications to Product-Form Stochastic Networks and Queueing Systems

In this paper, we introduce a policy-gradient method for model-based reinforcement learning (RL) that exploits a type of stationary distributions commonly obtained from Markov decision processes (MDPs) in stochastic networks, queueing systems, and statistical mechanics. Specifically, when the stationary distribution of the MDP belongs to an exponential family that is parametrized by policy parameters, we can improve existing policy gradient methods for average-reward RL. Our key identification is a family of gradient estimators, called score-aware gradient estimators (SAGEs), that enable policy gradient estimation without relying on value-function approximation in the aforementioned setting. This contrasts with other common policy-gradient algorithms such as actor-critic methods. We first show that policy-gradient with SAGE locally converges, including in cases when the objective function is nonconvex, presents multiple maximizers, and the state space of the MDP is not finite. Under appropriate assumptions such as starting sufficiently close to a maximizer, the policy under stochastic gradient ascent with SAGE has an overwhelming probability of converging to the associated optimal policy. Other key assumptions are that a local Lyapunov function exists, and a nondegeneracy property of the Hessian of the objective function holds locally around a maximizer. Furthermore, we conduct a numerical comparison between a SAGE-based policy-gradient method and an actor-critic method. We specifically focus on several examples inspired from stochastic networks, queueing systems, and models derived from statistical physics, where parametrizable exponential families are commonplace. Our results demonstrate that a SAGE-based method finds close-to-optimal policies faster than an actor-critic method.

arXiv:2312.00645

Hashmarks: Privacy-Preserving Benchmarks for High-Stakes AI Evaluation

There is a growing need to gain insight into language model capabilities that relate to sensitive topics, such as bioterrorism or cyberwarfare. However, traditional open source benchmarks are not fit for the task, due to the associated practice of publishing the correct answers in human-readable form. At the same time, enforcing mandatory closed-quarters evaluations might stifle development and erode trust. In this context, we propose hashmarking, a protocol for evaluating language models in the open without having to disclose the correct answers. In its simplest form, a hashmark is a benchmark whose reference solutions have been cryptographically hashed prior to publication. Following an overview of the proposed evaluation protocol, we go on to assess its resilience against traditional attack vectors (e.g. rainbow table attacks), as well as against failure modes unique to increasingly capable generative models.

arXiv:2311.18773

Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding

Learning from videos is an emerging research area that enables robots to acquire skills from human demonstrations, such as procedural videos. To do this, video-language models must be able to obtain structured understandings, such as the temporal segmentation of a demonstration into sequences of actions and skills, and to generalize the understandings to novel domains. In pursuit of this goal, we introduce Spacewalk-18, a benchmark containing two tasks: (1) step recognition and (2) intra-video retrieval over a dataset of temporally segmented and labeled tasks in International Space Station spacewalk recordings. In tandem, the two tasks quantify a model's ability to make use of: (1) out-of-domain visual information; (2) a high temporal context window; and (3) multimodal (e.g. visual and speech) domains. This departs from existing benchmarks for procedural video understanding, which typically deal with short context lengths and can be solved with a single modality. Spacewalk-18, with its inherent multimodal and long-form complexity, exposes the high difficulty of task recognition and segmentation. We find that state-of-the-art methods perform poorly on our benchmark, but improvements can be obtained by incorporating information from longer-range temporal context across different modalities. Our experiments underscore the need to develop new approaches to these tasks. Data, model, and code will be released at https://brown-palm.github.io/Spacewalk-18/.

arXiv:2306.07174

Augmenting Language Models with Long-Term Memory

Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history. We design a novel decoupled network architecture with the original backbone LLM frozen as a memory encoder and an adaptive residual side-network as a memory retriever and reader. Such a decoupled memory design can easily cache and update long-term past contexts for memory retrieval without suffering from memory staleness. Enhanced with memory-augmented adaptation training, LongMem can thus memorize long past context and use long-term memory for language modeling. The proposed memory retrieval module can handle unlimited-length context in its memory bank to benefit various downstream tasks. Typically, LongMem can enlarge the long-form memory to 65k tokens and thus cache many-shot extra demonstration examples as long-form memory for in-context learning. Experiments show that our method outperforms strong long-context models on ChapterBreak, a challenging long-context modeling benchmark, and achieves remarkable improvements on memory-augmented in-context learning over LLMs. The results demonstrate that the proposed method is effective in helping language models to memorize and utilize long-form contents. Our code is open-sourced at https://aka.ms/LongMem.