This paper demonstrates that Concept Bottleneck Models (CBMs), despite their interpretability, are highly vulnerable to targeted adversarial attacks that manipulate semantic concepts, and proposes SPE…

This paper formalizes the binding problem using information theory and develops a probing method to measure binding information in deep learning representations, demonstrating that binding is crucial…

The paper argues that the standard FID metric is unreliable because its performance depends significantly on the geometric structure and density of the reference dataset, not just the sample quality.

The paper proposes an extended version of Hypencoder, a retrieval approach that encodes queries as shallow neural networks, achieving comparable effectiveness with fewer active parameters and higher s…

The paper demonstrates that the phenomenon of 'subliminal learning,' where behavioral traits are transmitted between language models, is not a fundamental learning mechanism but rather a fragile artif…

The paper introduces a novel, non-deep neural network architecture that achieves the performance of LLMs by finding the global optimum of the loss function in a single, closed-form iteration, eliminat…

This paper addresses the vulnerability of DNNs used in robotic semantic segmentation to adversarial attacks by proposing specialized detection strategies to enhance safety in robotic perception system…

This paper explains how discarded norms in contrastive embedding models correlate with semantic properties and provides a theoretical framework.

This paper challenges the claim that neural networks have met the challenge of systematicity in language and thought as proposed by Fodor and Pylyshyn, demonstrating limitations in a recent neural net…

This paper explores how different components of the Transformer feedforward block architecture impact rank preservation across depth during initialization.

The paper demonstrates that content suppression techniques used in language models only mask prohibited content at the output level, failing to eliminate the underlying concepts from the model's inter…

This paper discusses the current understanding of Large Language Models (LLMs), their capabilities, and their relationship to human cognition, with a focus on emerging capabilities and mechanistic imp…

The paper tracks the developmental emergence of attention circuits in 1B-class language models, finding that the formation of induction and attention-sink circuits are distinct, temporally separated t…

Vision-language models (VLMs) exhibit an asymmetric bias, suppressing female representations and defaulting to male outputs when presented with ambiguous visual inputs, even when internal representati…