Deep Learning
Learning Large-scale Neural Fields via Context Pruned Meta-Learning
We introduce an efficient optimization-based meta-learning technique for large-scale neural field training by realizing significant memory savings through automated online context point selection.
Supplementary File for ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Evaluation Capability for Large Vision-Language Models
We calculate the agreement of human judgment and our automatic evaluation (i.e., ConvBenchEval()) and find it reaches 81.83% (seeing Table 3 - 6 for detailed agreement of each turn of overall). It demonstrates the effectiveness of ConvBenchEval(), which uses ChatGPT. The agreement between ChatGPT and GPT4 is very high at 87.38%. It demonstrates that using different LLMs as judges slightly influences the evaluation results. ConvBenchEval() armed with ChatGPT can is reliable and low-cost. From the above tables, we also observe that though GPT4V is expensive and can capture images, its judgment performs worse than GPT4's judgment.
Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
Much of the promise of these models relies on learned concepts being high quality .
Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack using Public Data
First, we define distributionally equivalent and Max-Information model extraction attacks, and reduce them into a variational optimisation problem.
Geometry of naturalistic object representations in recurrent neural network models of working memory
Working memory is a central cognitive ability crucial for intelligent decision-making. Recent experimental and computational work studying working memory has primarily used categorical (i.e., one-hot) inputs, rather than ecologically-relevant, multidimensional naturalistic ones.
