The paper introduces MeRa, a metric-space bias module, demonstrating that latent reasoning only improves spatial prediction when it is explicitly grounded in the underlying metric space.

This paper introduces the Bridge, a lightweight interface that enables distillation between Teachers and Students with different latent resolutions and VAE spaces in Cross-Space Distillation.

This paper proposes methods to improve the encoding capacity and disentanglement of Variational Autoencoders (VAE) by imposing entropy-based constraints and a weight-filter method.

The paper introduces Geometric Latent Reasoning (GLR), a method that models reasoning as continuous paths in the embedding space, showing that this continuous approach allows LLMs to solve problems us…

This paper introduces LVCG, a novel self-supervised framework that learns unified, view-invariant latent representations of cardiac electrical activity directly in the physically grounded Vectorcardio…

ElasticMem introduces a novel framework that treats memory as an elastic latent resource, allowing LLM agents to adaptively manage and inject variable-budget memories for improved performance in long-…

This paper introduces a latent attack framework demonstrating that attacks can be embedded into the hidden representations of multi-agent systems, causing performance degradation even during clean, no…

The paper introduces BRo-JEPA, a latent world model that successfully learns modular arithmetic (like addition modulo 10) by explicitly imposing the circular structure of the problem into the latent s…

VITAL introduces a novel latent-space reasoning framework for medical MLLMs, utilizing visual-semantic dual supervision to enhance reasoning capabilities and provide crucial interpretability without s…

The paper introduces LatentFlow, a system for analyzing latent spaces in molecular graph neural networks using clustering and visualization.

The paper introduces Latent Terms, a method that shows dense retrieval models implicitly learn sparse, Zipfian vocabularies that can be used for classical BM25-style sparse scoring without requiring s…

The paper introduces C$^2$R (Cross-sample Consistency Regularization) to address feature splitting and absorption issues in Sparse Autoencoders by encouraging consistent latent assignment across sampl…

The paper introduces the Vector Network (VN), a novel recurrent architecture that replaces fixed weight matrices with reusable weight atoms, enabling superior compositional generalization by making st…

This paper proposes IntuRec, a two-stage framework for LLM-based recommendation that anchors latent reasoning with recommendation intuition.

DiffuSent proposes a non-auto-regressive diffusion framework to unify Aspect-Based Sentiment Analysis (ABSA), significantly improving boundary detection for multi-word aspect and opinion terms.

This paper proposes ReChannel, a method for dense prediction using a pretrained DiT model, which keeps the encoder but removes the decoder and adapts it with task LoRA. ReChannel maps each token to it…

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…