|
- Counterfactual Debiasing for Fact Verification
579 In this paper, we have proposed a novel counter- factual framework CLEVER for debiasing fact- checking models Unlike existing works, CLEVER is augmentation-free and mitigates biases on infer- ence stage In CLEVER, the claim-evidence fusion model and the claim-only model are independently trained to capture the corresponding information
- Evaluating the Robustness of Neural Networks: An Extreme Value. . .
Our analysis yields a novel robustness metric called CLEVER, which is short for Cross Lipschitz Extreme Value for nEtwork Robustness The proposed CLEVER score is attack-agnostic and is computationally feasible for large neural networks
- Weakly-Supervised Affordance Grounding Guided by Part-Level. . .
In this work, we focus on the task of weakly supervised affordance grounding, where a model is trained to identify affordance regions on objects using human-object interaction images and egocentric
- Reasoning of Large Language Models over Knowledge Graphs with. . .
While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate This limitation reduces
- SleepSMC: Ubiquitous Sleep Staging via Supervised Multimodal . . .
Sleep staging is critical for assessing sleep quality and tracking health Polysomnography (PSG) provides comprehensive multimodal sleep-related information, but its complexity and impracticality
- Training Large Language Model to Reason in a Continuous Latent Space
Large language models are restricted to reason in the “language space”, where they typically express the reasoning process with a chain-of-thoughts (CoT) to solve a complex reasoning problem
- Semi-supervised Camouflaged Object Detection from Noisy Data
1 The Pixel-level loss reweighting method is more clever, but the integrated learning using two network fusion feature designs is too bloated 2 The paper proposes for the first time the use of semi-supervised learning to solve the problems of noisy labels and difficulty in obtaining labels in Camouflaged Object Detection 3 The paper makes a
- Cross-Embodiment Dexterous Grasping with Reinforcement Learning
Dexterous hands exhibit significant potential for complex real-world grasping tasks While recent studies have primarily focused on learning policies for specific robotic hands, the development of a universal policy that controls diverse dexterous hands remains largely unexplored In this work, we study the learning of cross-embodiment dexterous grasping policies using reinforcement learning
|
|
|