Importance sampling is one of the most widely used variance reduction strategies in Monte Carlo rendering. In this paper, we propose a novel importance sampling technique that uses a neural network to learn how to sample from a desired density represented by a set of samples. Our approach considers an existing Monte Carlo rendering algorithm as a black box. During a scene-dependent training phase, we learn to generate samples with a desired density in the primary sample space of the rendering algorithm using maximum likelihood estimation. We leverage a recent neural network architecture that was designed to represent real-valued non-volume preserving ('Real NVP') transformations in high dimensional spaces. We use Real NVP to non-linearly warp primary sample space and obtain desired densities. In addition, Real NVP efficiently computes the determinant of the Jacobian of the warp, which is required to implement the change of integration variables implied by the warp. A main advantage of our approach is that it is agnostic of underlying light transport effects, and can be combined with many existing rendering techniques by treating them as a black box. We show that our approach leads to effective variance reduction in several practical scenarios.
相關內容
In this paper, we demonstrate how Large Language Models (LLMs) can effectively learn to use an off-the-shelf information retrieval (IR) system specifically when additional context is required to answer a given question. Given the performance of IR systems, the optimal strategy for question answering does not always entail external information retrieval; rather, it often involves leveraging the parametric memory of the LLM itself. Prior research has identified this phenomenon in the PopQA dataset, wherein the most popular questions are effectively addressed using the LLM's parametric memory, while less popular ones require IR system usage. Following this, we propose a tailored training approach for LLMs, leveraging existing open-domain question answering datasets. Here, LLMs are trained to generate a special token, <RET>, when they do not know the answer to a question. Our evaluation of the Adaptive Retrieval LLM (Adapt-LLM) on the PopQA dataset showcases improvements over the same LLM under three configurations: (i) retrieving information for all the questions, (ii) using always the parametric memory of the LLM, and (iii) using a popularity threshold to decide when to use a retriever. Through our analysis, we demonstrate that Adapt-LLM is able to generate the <RET> token when it determines that it does not know how to answer a question, indicating the need for IR, while it achieves notably high accuracy levels when it chooses to rely only on its parametric memory.
Inspired by the great potential of Large Language Models (LLMs) for solving complex coding tasks, in this paper, we propose a novel approach, named Code2API, to automatically perform APIzation for Stack Overflow code snippets. Code2API does not require additional model training or any manual crafting rules and can be easily deployed on personal computers without relying on other external tools. Specifically, Code2API guides the LLMs through well-designed prompts to generate well-formed APIs for given code snippets. To elicit knowledge and logical reasoning from LLMs, we used chain-of-thought (CoT) reasoning and few-shot in-context learning, which can help the LLMs fully understand the APIzation task and solve it step by step in a manner similar to a developer. Our evaluations show that Code2API achieves a remarkable accuracy in identifying method parameters (65%) and return statements (66%) equivalent to human-generated ones, surpassing the current state-of-the-art approach, APIzator, by 15.0% and 16.5% respectively. Moreover, compared with APIzator, our user study demonstrates that Code2API exhibits superior performance in generating meaningful method names, even surpassing the human-level performance, and developers are more willing to use APIs generated by our approach, highlighting the applicability of our tool in practice. Finally, we successfully extend our framework to the Python dataset, achieving a comparable performance with Java, which verifies the generalizability of our tool.
In this paper, we explore an efficient uncoupled unsourced random access (UURA) scheme for 6G massive communication. UURA is a typical framework of unsourced random access that addresses the problems of codeword detection and message stitching, without the use of check bits. Firstly, we establish a framework for UURA, allowing for immediate decoding of sub-messages upon arrival. Thus, the processing delay is effectively reduced due to the decreasing waiting time. Next, we propose an integrated decoding algorithm for sub-messages by leveraging matrix information geometry (MIG) theory. Specifically, MIG is applied to measure the feature similarities of codewords belonging to the same user equipment, and thus sub-message can be stitched once it is received. This enables the timely recovery of a portion of the original message by simultaneously detecting and stitching codewords within the current sub-slot. Furthermore, we analyze the performance of the proposed integrated decoding-based UURA scheme in terms of computational complexity and convergence rate. Finally, we present extensive simulation results to validate the effectiveness of the proposed scheme in 6G wireless networks.
In this paper, we propose modelling human translation production as a hierarchy of three embedded translation processes. The proposed architecture replicates the temporal dynamics of keystroke production across sensorimotor, cognitive, and phenomenal layers. Utilizing data from the CRITT TPR-DB, the Task Segment Framework, and the HOF taxonomy, we demonstrate the temporal breakdown of the typing flow on distinct timelines within these three layers.
Inspired by Federated Learning, in this paper, we propose personal large models that are distilled from traditional large language models but more adaptive to local users' personal information such as education background and hobbies. We classify the large language models into three levels: the personal level, expert level and traditional level. The personal level models are adaptive to users' personal information. They encrypt the users' input and protect their privacy. The expert level models focus on merging specific knowledge such as finance, IT and art. The traditional models focus on the universal knowledge discovery and upgrading the expert models. In such classifications, the personal models directly interact with the user. For the whole system, the personal models have users' (encrypted) personal information. Moreover, such models must be small enough to be performed on personal computers or mobile devices. Finally, they also have to response in real-time for better user experience and produce high quality results. The proposed personal large models can be applied in a wide range of applications such as language and vision tasks.
In this paper, we present new algorithms for approximating All-Pairs Shortest Paths (APSP) in the Congested Clique model. We present randomized algorithms for weighted undirected graphs. Our first contribution is an $O(1)$-approximate APSP algorithm taking just $O(\log \log \log n)$ rounds. Prior to our work, the fastest algorithms that give an $O(1)$-approximation for APSP take $\operatorname{poly}(\log{n})$ rounds in weighted undirected graphs, and $\operatorname{poly}(\log \log n)$ rounds in unweighted undirected graphs. If we terminate the execution of the algorithm early, we obtain an $O(t)$-round algorithm that yields an $O \big( (\log n)^{1/2^t} \big) $ distance approximation for a parameter $t$. The trade-off between $t$ and the approximation quality provides flexibility for different scenarios, allowing the algorithm to adapt to specific requirements. In particular, we can get an $O \big( (\log n)^{1/2^t} \big) $-approximation for any constant $t$ in $O(1)$-rounds. Such result was previously known only for the special case that $t=0$. A key ingredient in our algorithm is a lemma that allows to improve an $O(a)$-approximation for APSP to an $O(\sqrt{a})$-approximation for APSP in $O(1)$ rounds. To prove the lemma, we develop several new tools, including $O(1)$-round algorithms for computing the $k$ closest nodes, a certain type of hopset, and skeleton graphs.
In this paper we look at $k$-stroll, point-to-point orienteering, as well as the deadline TSP problem on graphs with bounded doubling dimension and bounded treewidth and present approximation schemes for them. Given a weighted graph $G=(V,E)$, start node $s\in V$, distances $d:E\rightarrow \mathbb{Q}^+$ and integer $k$. In the $k$-stroll problem the goal is to find a path starting at $s$ of minimum length that visits at least $k$ vertices. The dual problem to $k$-stroll is the rooted orienteering in which instead of $k$ we are given a budget $B$ and the goal is to find a walk of length at most $B$ starting at $s$ that visits as many vertices as possible. In the P2P orienteering we are given start and end nodes $s,t$ for the path. In the deadline TSP we are given a deadline $D(v)$ for each $v\in V$ and the goal is to find a walk starting at $s$ that visits as many vertices as possible before their deadline. The best approximation for rooted or P2P orienteering is $(2+\epsilon)$-approximation [12] and $O(\log n)$-approximation for deadline TSP [3]. There is no known approximation scheme for deadline TSP for any metric (not even trees). Our main result is the first approximation scheme for deadline TSP on metrics with bounded doubling dimension. To do so we first show if $G$ is a metric with doubling dimension $\kappa$ and aspect ratio $\Delta$, there is a $(1+\epsilon)$-approximation that runs in time $n^{O\left(\left(\log\Delta/\epsilon\right)^{2\kappa+1}\right)}$. We then extend these to obtain an approximation scheme for deadline TSP when the distances and deadlines are integer which runs in time $n^{O\left(\left(\log \Delta/\epsilon\right)^{2\kappa+2}\right)}$. For graphs with treewidth $\omega$ we show how to solve $k$-stroll and P2P orienteering exactly in polynomial time and a $(1+\epsilon)$-approximation for deadline TSP in time $n^{O((\omega\log\Delta/\epsilon)^2)}$.
In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many pretraining languages to achieve fast adaptation on unseen target language, via recently proposed model-agnostic meta learning algorithm (MAML). We evaluated the proposed approach using six languages as pretraining tasks and four languages as target tasks. Preliminary results showed that the proposed method, MetaASR, significantly outperforms the state-of-the-art multitask pretraining approach on all target languages with different combinations of pretraining languages. In addition, since MAML's model-agnostic property, this paper also opens new research direction of applying meta learning to more speech-related applications.
BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks. In this paper, we describe BERTSUM, a simple variant of BERT, for extractive summarization. Our system is the state of the art on the CNN/Dailymail dataset, outperforming the previous best-performed system by 1.65 on ROUGE-L. The codes to reproduce our results are available at //github.com/nlpyang/BertSum
In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth. Three new protocols of varying difficulty are introduced. The protocols allow fair comparison between different methods, including those using a dataset pre-processing stage. For each dataset, 15 new challenging queries are introduced. Finally, a new set of 1M hard, semi-automatically cleaned distractors is selected. An extensive comparison of the state-of-the-art methods is performed on the new benchmark. Different types of methods are evaluated, ranging from local-feature-based to modern CNN based methods. The best results are achieved by taking the best of the two worlds. Most importantly, image retrieval appears far from being solved.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191