Deep Learning
Image2Struct: Benchmarking Structure Extraction for Vision-Language Models
We introduce Image2Struct, a benchmark to evaluate vision-language models (VLMs) on extracting structure from images.
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
The principle of multi-task learning, which encompasses concepts such as "learning to learn" and "knowledge transfer," offers an efficient paradigm that mirrors human intelligence.
Amortized Fourier Neural Operators
Fourier Neural Operators (FNOs) have shown promise for solving partial differential equations (PDEs).
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
To further verify this finding, we empirically show that these dormant backdoors can be easily re-activated during inference stage, by manipulating the original trigger with well-designed tiny perturbation using universal adversarial attack.
Calibrating Reasoning in Language Models with Internal Consistency
Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning.
Agent Planning with World Knowledge Model
Imitating humans' mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric W orld K nowledge M odel ( WKM) to facilitate agent
Large language model validity via enhanced conformal prediction methods
We develop new conformal inference methods for obtaining validity guarantees on the output of large language models (LLMs). Prior work in conformal language modeling identifies a subset of the text that satisfies a high-probability guarantee of correctness. These methods work by filtering claims from the LLM's original response if a scoring function evaluated on the claim fails to exceed a threshold calibrated via split conformal prediction. Existing methods in this area suffer from two deficiencies. First, the guarantee stated is not conditionally valid.
Supplementary Material and Datasheet: Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting Contents
This supplementary document follows the Datasheets for Datasets template of (8) to document the Global Flood Forecasting (GFF) dataset and its creation. Further resources are provided: in the accompanying publication https://arxiv.org/abs/2409.18591 in the GitHub repository https://github.com/Multihuntr/GFF
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
However, the exploration of enhancing inference efficiency during adaptation remains underexplored.