Neural Information Processing Systems http://nips.cc/

Moreo randominitializationH( 0)conv deterministic H asthewidthNeur ker ( , ) (Equation (2)) evaluatedH(t)= H forallt, then (3) becomes du(t) dt = H (u(t) y). Suppose (z)= max ( 0,z), 1/ = poly ( 1/ ,log (n / )) and d1 = d2 = = dL = m with m poly ( 1/ , L,1/ 0,n,log ( 1/ )).

While performing abest-first search, compilation errors constitute 88.7% ofprogramfailures.

Previous ablation studies showedthatadding WD to normalized nets indeed leads to better generalization [126, 72, 125].

Inthis paper,we theoretically extend spectral-based graph convolution todigraphs and deriveasimplified form usingpersonalizedPageRank. Specifically,we present theDigraph Inception Convolutional Networks(DiGCN) whichutilizes digraph convolution andkth-order proximity to achievelarger receptivefields and learn multi-scale features in digraphs.

We derive nearly sharp bounds for the bidirectional GAN (BiGAN) estimation error under the Dudley distance between the latent joint distribution and the data joint distribution with appropriately specified architecture of the neural networks usedinthemodel.

The Multi-modal Large Language Model (MLLM) based Referring Expression Generation (REG) task has gained increasing popularity, which aims to generate an unambiguous text description that applies to exactly one object or region in the image by leveraging foundation models. We empirically found that there exists a potential trade-off between the detailedness and the correctness of the descriptions for the referring objects. On the one hand, generating sentences with more details is usually required in order to provide more precise object descriptions. On the other hand, complicated sentences could easily increase the probability of hallucinations. To address this issue, we propose a training-free framework, named ``unleash-then-eliminate'', which first elicits the latent information in the intermediate layers, and then adopts a cycle-consistency-based decoding method to alleviate the production of hallucinations. Furthermore, to reduce the computational load of cycle-consistency-based decoding, we devise a Probing-based Importance Estimation method to statistically estimate the importance weights of intermediate layers within a subset. These importance weights are then incorporated into the decoding process over the entire dataset, intervening in the next token prediction from intermediate layers.Extensive experiments conducted on the RefCOCOg and PHD benchmarks show that our proposed framework could outperform existing methods on both semantic and hallucination-related metrics.

The availability of large-scale multimodal datasets and advancements in diffusion models have significantly accelerated progress in 4D content generation. Most prior approaches rely on multiple images or video diffusion models, utilizing score distillation sampling for optimization or generating pseudo novel views for direct supervision. However, these methods are hindered by slow optimization speeds and multi-view inconsistency issues. Spatial and temporal consistency in 4D geometry has been extensively explored respectively in 3D-aware diffusion models and traditional monocular video diffusion models. Building on this foundation, we propose a strategy to migrate the temporal consistency in video diffusion models to the spatial-temporal consistency required for 4D generation.

Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen domains. In this paper, we propose a new approach that aims to explicitly remove domain-specific features for domain generalization. Following this approach, we propose a novel framework called Learning and Removing Domain-specific features for Generalization (LRDG) that learns a domain-invariant model by tactically removing domain-specific features from the input images. Specifically, we design a classifier to effectively learn the domain-specific features for each source domain, respectively. We then develop an encoder-decoder network to map each input image into a new image space where the learned domain-specific features are removed. With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification. Extensive experiments demonstrate that our framework achieves superior performance compared with state-of-the-art methods.