The paper introduces Brain-IT-VQA, a novel framework that significantly improves visual question answering from fMRI signals, and presents NSD-VQA, a new, highly controlled dataset for this task.

The paper demonstrates that the location and nature of state encoding in sequence models are not fixed architectural traits but are highly dependent on the specific task, showing that the encoding pro…

The paper proposes MindDiffuser, a two-stage framework that significantly improves image reconstruction from brain activity by combining semantic guidance from text-to-image models with structural ref…

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…

The study demonstrates that robust, domain-invariant representations of synthetic deception can be rapidly entrenched in LLMs using modest fine-tuning, detectable by linear probes even in early layers…

The paper demonstrates that quadratic integrate-and-fire (QIF) neurons are superior to leaky integrate-and-fire (LIF) neurons for gradient descent training in spiking neural networks because their con…

This paper demonstrates that large language models spontaneously develop geometric structures corresponding to human perceptual domains (like color or pitch) within their internal layers, suggesting t…

BayesNCL introduces a probabilistic gating mechanism to resolve the optimization conflict in Contrastive Learning, leading to highly disentangled and semantically consistent representations.

Incorporating short-term synaptic plasticity (STP) into a PFC-inspired reservoir model significantly stabilizes goal-conditioned dynamics, particularly under state noise, suggesting STP dynamically mo…

The paper demonstrates that the valence structure learned by modern LLMs aligns with human EEG emotional representations, but finds that further supervised alignment is ineffective due to a phenomenon…

The paper demonstrates that Transformers trained on local comparisons implicitly learn a global, one-dimensional ordinal structure, mirroring the human ability to perform transitive inference.

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 analyzes the distinct computational roles of positional versus symbolic attention heads in Transformers, demonstrating that symbolic mechanisms generalize more reliably to longer sequences 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…

The scaling exponent in neural scaling laws is not fixed but systematically depends on the optimizer used, with preconditioned optimizers generally yielding steeper scaling.

Mind-Omni introduces a unified multi-task framework that models the interplay between brain, vision, and language signals using a discrete diffusion paradigm, achieving state-of-the-art performance ac…

The paper deconstructs latent visual reasoning tokens into components and finds that the performance gains are primarily due to boundary markers and attention patterns, not the tokens' ability to enco…

CORE-MTL proposes a representation-centric framework that uses causal orthogonal representations to disentangle task-relevant structure from nuisance variation in multi-task learning, achieving superi…

This paper analyzes multi-model self-consuming training, showing that while human curation helps individual models, cross-model interactions can degrade long-term alignment by dampening or inverting t…