Related papers: Symbol Preference Aware Generative Models for Reco…

In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional…

Graph Neural Networks (GNNs) are effective tools for graph representation learning. Most GNNs rely on a recursive neighborhood aggregation scheme, named message passing, thereby their theoretical expressive power is limited to the…

The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametric Decoding (Np…

Obfuscation poses a persistent challenge for software engineering tasks such as program comprehension, maintenance, testing, and vulnerability detection. While compiler optimizations and third-party code often introduce transformations that…

Non-negative signals form an important class of sparse signals. Many algorithms have already beenproposed to recover such non-negative representations, where greedy and convex relaxed algorithms are among the most popular methods. One fast…

Neural language models can be successfully trained on source code, leading to applications such as code completion. However, their versatile autoregressive self-supervision objective overlooks important global sequence-level features that…

A technique named Feature Learning from Image Markers (FLIM) was recently proposed to estimate convolutional filters, with no backpropagation, from strokes drawn by a user on very few images (e.g., 1-3) per class, and demonstrated for…

Verifiers or reward models are often used to enhance the reasoning performance of large language models (LLMs). A common approach is the Best-of-N method, where N candidate solutions generated by the LLM are ranked by a verifier, and the…

Graph neural networks (GNN) have recently emerged as a vehicle for applying deep network architectures to graph and relational data. However, given the increasing size of industrial datasets, in many practical situations the message passing…

Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names is often overlooked…

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention from both systems and…

Neural network models of real-world systems, such as industrial processes, made from sensor data must often rely on incomplete data. System states may not all be known, sensor data may be biased or noisy, and it is not often known which…

This paper proposes a straightforward and cost-effective approach to assess whether a deep neural network (DNN) relies on the primary concepts of training samples or simply learns discriminative, yet simple and irrelevant features that can…

Biomedical research increasingly relies on integrating diverse data modalities, including gene expression profiles, medical images, and clinical metadata. While medical images and clinical metadata are routinely collected in clinical…

Large language models~(LLMs) are expected to be helpful, harmless, and honest. In different alignment scenarios, such as safety, confidence, and general preference alignment, binary preference data collection and reward modeling are…

Reference-guided instance editing is fundamentally limited by semantic entanglement, where a reference's intrinsic appearance is intertwined with its extrinsic attributes. The key challenge lies in disentangling what information should be…

Natural language to code generation is an important application area of LLMs and has received wide attention from the community. The majority of relevant studies have exclusively concentrated on increasing the quantity and functional…

Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions…

Training 1-bit deep convolutional neural networks (DCNNs) is one of the most challenging problems in computer vision, because it is much easier to get trapped into local minima than conventional DCNNs. The reason lies in that the binarized…

Generative Sequential Recommendation (GSR) has emerged as a promising paradigm, reframing recommendation as an autoregressive sequence generation task over discrete Semantic IDs (SIDs), typically derived via codebook-based quantization.…