Paper and LLMs AI Tools

This paper describes the systems submitted by team6 for ChatEval, the DSTC 11 Track 4 competition.

One of the challenges in learning to perform abstract reasoning is that problems are often posed as monolithic tasks, with no intermediate subgoals.

Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, which is very successful in multi-class single-label learning.

In this paper, we propose a novel task, Proactive News Grounded Conversation, in which a dialogue system can proactively lead the conversation based on some key topics of the news.

We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.

Physics-Informed Neural Networks (PINNs) have gained popularity in solving nonlinear partial differential equations (PDEs) via integrating physical laws into the training of neural networks, making them superior in many scientific and engineering applications.

Recent leading zero-shot video object segmentation (ZVOS) works devote to integrating appearance and motion information by elaborately designing feature fusion modules and identically applying them in multiple feature stages.

It motivates us to develop a technique to evaluate true loss changes without retraining, with which channels to prune can be selected more reliably and confidently.

The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem.

Note that we use LDCT images based on the noisy-as-clean strategy for corruption instead of NDCT images.

Although unsupervised approaches based on generative adversarial networks offer a promising solution for denoising without paired datasets, they are difficult in surpassing the performance limitations of conventional GAN-based unsupervised frameworks without significantly modifying existing structures or increasing the computational complexity of denoisers.

Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor.

Experimental results on benchmark datasets demonstrate that our method achieves the State-Of-The-Art (SOTA) performance in terms of both image quality and inter-frame brightness consistency.

Therefore, this study aims to explore the potential of FMs in the field of smart agriculture.

However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test set.

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.

We explore a setup for performing classification on labeled classical datasets, consisting of a classical neural network connected to a quantum annealer.

In the pursuit of promoting the expressiveness of GNNs for tail nodes, we explore how the deficiency of structural information deteriorates the performance of tail nodes and propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes.

To enable the deep graph clustering algorithms to work without the guidance of the predefined cluster number, we propose a new deep graph clustering method termed Reinforcement Graph Clustering (RGC).

Graph Neural Networks (GNNs) are state-of-the-art models for performing prediction tasks on graphs.

Nevertheless, existing methods emphasize the design of elegant KGC models to facilitate modality interaction, neglecting the real-life problem of missing modalities in KGs.

Spiking Neural Networks (SNNs) as one of the biology-inspired models have received much attention recently.

To mitigate potentially incorrect pseudo labels, recent frameworks mostly set a fixed confidence threshold to discard uncertain samples.

Bayesian Neural Networks (BayesNNs) have demonstrated their capability of providing calibrated prediction for safety-critical applications such as medical imaging and autonomous driving.

This paper presents an ensemble data assimilation method using the pseudo ensembles generated by denoising diffusion probabilistic model.

Vision transformers are effective deep learning models for vision tasks, including medical image segmentation.

We extend object tracking and 3D reconstruction algorithms to support continuous segmentation labels to leverage the advances in the 2D image segmentation, especially the Segment-Anything Model (SAM) which uses the pretrained neural network without additional training for new scenes, for 3D object segmentation.

Two metrics are proposed to evaluate AER performance with automatic segmentation based on time-weighted emotion and speaker classification errors.

Based on the modeling method, we present FocusFlow, a framework consisting of 1) a mix loss function combined with a classic photometric loss function and our proposed Conditional Point Control Loss (CPCL) function for diverse point-wise supervision; 2) a conditioned controlling model which substitutes the conventional feature encoder by our proposed Condition Control Encoder (CCE).

Many machine translation toolkits make use of a data preparation step wherein raw data is transformed into a tensor format that can be used directly by the trainer.