Search Results for author:
Found 12 papers, 3 papers with code
On the Robustness of Transformers against Context Hijacking for Linear Classification
Then, we develop a general theoretical analysis on the robustness of the linear transformers, which is formulated as a function of the model depth, training context lengths, and number of hijacking context tokens.
Adaptive Caching for Faster Video Generation with Diffusion Transformers
Generating temporally-consistent high-fidelity videos can be computationally expensive, especially over longer temporal spans.
AdaptGCD: Multi-Expert Adapter Tuning for Generalized Category Discovery
Different from the traditional semi-supervised learning paradigm that is constrained by the close-world assumption, Generalized Category Discovery (GCD) presumes that the unlabeled dataset contains new categories not appearing in the labeled set, and aims to not only classify old categories but also discover new categories in the unlabeled data.
Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method
Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question.
A Lightweight Multi Aspect Controlled Text Generation Solution For Large Language Models
Augmented datasets are feasible for instruction tuning.
Probing Causality Manipulation of Large Language Models
Large language models (LLMs) have shown various ability on natural language processing, including problems about causality.
The Implicit Bias of Adam on Separable Data
Adam has become one of the most favored optimizers in deep learning problems.
RNG: Reducing Multi-level Noise and Multi-grained Semantic Gap for Joint Multimodal Aspect-Sentiment Analysis
As an important multimodal sentiment analysis task, Joint Multimodal Aspect-Sentiment Analysis (JMASA), aiming to jointly extract aspect terms and their associated sentiment polarities from the given text-image pairs, has gained increasing concerns.
Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint
Solving image inverse problems (e. g., super-resolution and inpainting) requires generating a high fidelity image that matches the given input (the low-resolution image or the masked image).
STW-MD: A Novel Spatio-Temporal Weighting and Multi-Step Decision Tree Method for Considering Spatial Heterogeneity in Brain Gene Expression Data
Motivation: Gene expression during brain development or abnormal development is a biological process that is highly dynamic in spatio and temporal.
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization
And the other introduces a new metric based on mutual information between adjacent action proposals and evaluates the informativeness of video samples, named Temporal Context Inconsistency (TCI).
The iMet Collection 2019 Challenge Dataset
Existing computer vision technologies in artwork recognition focus mainly on instance retrieval or coarse-grained attribute classification.
