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…

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

The paper theoretically analyzes the properties that optimal sparse autoencoder (SAE) dictionaries must satisfy, deriving constraints that explain observed SAE behaviors like hierarchical splitting an…

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.

This paper argues for the importance of modularity and heterogeneity in AI architectures, contrasting the Transformer model with the structure of the cortex.

While backpropagated gradients can predict human brain activity in the visual cortex, their spatial and temporal organization fundamentally diverges from the expected patterns of a biologically plausi…

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…

This paper compares different decoding pipelines for motor imagery tasks using EEG data and finds that no single pipeline dominates, emphasizing the need for participant-aware model selection.

This paper compares the cost-performance trade-off of Hebbian learning, Dense Difference Target Propagation (DDTP), and backpropagation (BP) using mutual-information-based measures.

The paper introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alig…

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 introduces HOPE, a mathematical framework for network compression that shifts representation deconstruction from the discrete domain to a Hilbert space, enabling unbiased architectural decis…

The authors show that an explicit information bottleneck in a recurrent neural network is necessary for rotational and out-of-distribution generalization in a time-series prediction task, and that the…

The paper introduces Dual-Spectral Flow Matching (DSFM), a novel generative framework that uses wavelet and cosine transforms to synthesize highly realistic, non-stationary fMRI time series for improv…

This paper investigates whether deep learning models retain the phase/sign asymmetry of natural images in their hidden layers and tests it causally.

The paper proposes Alignment-Guided Score Matching (AGSM), a lightweight, reward-free post-training method that integrates contrastive alignment guidance directly into the score-matching objective of…

The paper proposes Resonant Context Anchoring (RCA), a lightweight, training-free method that enhances factual faithfulness in LLMs by dynamically amplifying the signal of external context evidence du…