亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Neural radiance fields (NeRFs) have emerged as an effective method for novel-view synthesis and 3D scene reconstruction. However, conventional training methods require access to all training views during scene optimization. This assumption may be prohibitive in continual learning scenarios, where new data is acquired in a sequential manner and a continuous update of the NeRF is desired, as in automotive or remote sensing applications. When naively trained in such a continual setting, traditional scene representation frameworks suffer from catastrophic forgetting, where previously learned knowledge is corrupted after training on new data. Prior works in alleviating forgetting with NeRFs suffer from low reconstruction quality and high latency, making them impractical for real-world application. We propose a continual learning framework for training NeRFs that leverages replay-based methods combined with a hybrid explicit--implicit scene representation. Our method outperforms previous methods in reconstruction quality when trained in a continual setting, while having the additional benefit of being an order of magnitude faster.

We show that the eigenpolytopes of graphs are universal in the sense that every polytope, up to affine equivalence, appears as the eigenpolytope of some positively weighted graph. We next extend the theory of graphical designs, which are quadrature rules for graphs, to positively weighted graphs. Through Gale duality for polytopes, we show a bijection between graphical designs and the faces of eigenpolytopes. This bijection proves the existence of graphical designs with positive quadrature weights, and upper bounds the size of a minimal graphical design. Connecting this bijection with the universality of eigenpolytopes, we establish three complexity results: it is strongly NP-complete to determine if there is a graphical design smaller than the mentioned upper bound, it is NP-hard to find a smallest graphical design, and it is #P-complete to count the number of minimal graphical designs.

Recent efforts have incorporated large language models (LLMs) with external resources (e.g., the Internet) or internal control flows (e.g., prompt chaining) for tasks requiring grounding or reasoning. However, these efforts have largely been piecemeal, lacking a systematic framework for constructing a fully-fledged language agent. To address this challenge, we draw on the rich history of agent design in symbolic artificial intelligence to develop a blueprint for a new wave of cognitive language agents. We first show that LLMs have many of the same properties as production systems, and recent efforts to improve their grounding or reasoning mirror the development of cognitive architectures built around production systems. We then propose Cognitive Architectures for Language Agents (CoALA), a conceptual framework to systematize diverse methods for LLM-based reasoning, grounding, learning, and decision making as instantiations of language agents in the framework. Finally, we use the CoALA framework to highlight gaps and propose actionable directions toward more capable language agents in the future.

Lookup tables (finite maps) are a ubiquitous data structure. In pure functional languages they are best represented using trees instead of hash tables. In pure functional languages within constructive logic, without a primitive integer type, they are well represented using binary tries instead of search trees. In this work, we introduce canonical binary tries, an improved binary-trie data structure that enjoys a natural extensionality property, quite useful in proofs, and supports sparseness more efficiently. We provide full proofs of correctness in Coq. We provide microbenchmark measurements of canonical binary tries versus several other data structures for finite maps, in a variety of application contexts; as well as measurement of canonical versus original tries in two big, real systems. The application context of data structures contained in theorem statements imposes unusual requirements for which canonical tries are particularly well suited.

Cycle consistency has long been exploited as a powerful prior for jointly optimizing maps within a collection of shapes. In this paper, we investigate its utility in the approaches of Deep Functional Maps, which are considered state-of-the-art in non-rigid shape matching. We first justify that under certain conditions, the learned maps, when represented in the spectral domain, are already cycle consistent. Furthermore, we identify the discrepancy that spectrally consistent maps are not necessarily spatially, or point-wise, consistent. In light of this, we present a novel design of unsupervised Deep Functional Maps, which effectively enforces the harmony of learned maps under the spectral and the point-wise representation. By taking advantage of cycle consistency, our framework produces state-of-the-art results in mapping shapes even under significant distortions. Beyond that, by independently estimating maps in both spectral and spatial domains, our method naturally alleviates over-fitting in network training, yielding superior generalization performance and accuracy within an array of challenging tests for both near-isometric and non-isometric datasets. Codes are available at //github.com/rqhuang88/Spatiallyand-Spectrally-Consistent-Deep-Functional-Maps.

Recent progress in deep learning and natural language processing has given rise to powerful models that are primarily trained on a cloze-like task and show some evidence of having access to substantial linguistic information, including some constructional knowledge. This groundbreaking discovery presents an exciting opportunity for a synergistic relationship between computational methods and Construction Grammar research. In this chapter, we explore three distinct approaches to the interplay between computational methods and Construction Grammar: (i) computational methods for text analysis, (ii) computational Construction Grammar, and (iii) deep learning models, with a particular focus on language models. We touch upon the first two approaches as a contextual foundation for the use of computational methods before providing an accessible, yet comprehensive overview of deep learning models, which also addresses reservations construction grammarians may have. Additionally, we delve into experiments that explore the emergence of constructionally relevant information within these models while also examining the aspects of Construction Grammar that may pose challenges for these models. This chapter aims to foster collaboration between researchers in the fields of natural language processing and Construction Grammar. By doing so, we hope to pave the way for new insights and advancements in both these fields.

Counterfactual Regret Minimization (CFR) and its variants are the best algorithms so far for solving large-scale incomplete information games. Building upon CFR, this paper proposes a new algorithm named Pure CFR (PCFR) for achieving better performance. PCFR can be seen as a combination of CFR and Fictitious Play (FP), inheriting the concept of counterfactual regret (value) from CFR, and using the best response strategy instead of the regret matching strategy for the next iteration. Our theoretical proof that PCFR can achieve Blackwell approachability enables PCFR's ability to combine with any CFR variant including Monte Carlo CFR (MCCFR). The resultant Pure MCCFR (PMCCFR) can significantly reduce time and space complexity. Particularly, the convergence speed of PMCCFR is at least three times more than that of MCCFR. In addition, since PMCCFR does not pass through the path of strictly dominated strategies, we developed a new warm-start algorithm inspired by the strictly dominated strategies elimination method. Consequently, the PMCCFR with new warm start algorithm can converge by two orders of magnitude faster than the CFR+ algorithm.

We identify multirole logic as a new form of logic in which conjunction/disjunction is interpreted as an ultrafilter on some underlying set of roles and the notion of negation is generalized to endomorphisms on this set. We formulate both multirole logic (MRL) and linear multirole logic (LMRL) as natural generalizations of classical logic (CL) and classical linear logic (CLL), respectively. Among various meta-properties established for MRL and LMRL, we obtain one named multiparty cut-elimination stating that every cut involving one or more sequents (as a generalization of a binary cut involving exactly two sequents) can be eliminated, thus extending the celebrated result of cut-elimination by Gentzen. As a side note, we also give an ultrafilter-based interpretation for intuitionism, formulating MRLJ as a natural generalization of intuitionistic logic (IL). An immediate application of LMRL can be found in a formulation of session types for channels that support multiparty communication in distributed programming. We present a multi-threaded lambda-calculus (MTLC) where threads communicate on linearly typed multiparty channels that are directly rooted in LMRL, establishing for MTLC both type preservation and global progress. The primary contribution of the paper consists of both identifying multirole logic as a new form of logic and establishing a theoretical foundation for it, and the secondary contribution lies in applying multirole logic to the practical domain of distributed programming.

We describe a generic JSON based file format which is suitable for computations in computer algebra. This is implemented in the computer algebra system OSCAR, but we also indicate how it can be used in a different context.

Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the original combinatorial problem, and turns a broad class of DP algorithms into differentiable operators. Theoretically, we provide a new probabilistic perspective on backpropagating through these DP operators, and relate them to inference in graphical models. We derive two particular instantiations of our framework, a smoothed Viterbi algorithm for sequence prediction and a smoothed DTW algorithm for time-series alignment. We showcase these instantiations on two structured prediction tasks and on structured and sparse attention for neural machine translation.