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

This paper introduces Semantic Reference Frames (SemRF), an anchor-based formalism for separating semantic measurement from residual dynamics in language model computation.

This paper proposes a framework for summarizing dialogues, modeling semantic and emotion dynamics using multimodal inputs and an adapted hierarchical Chain-of-Agents approach.

The paper investigates how LLMs allocate their internal computational depth during multi-turn agentic planning, finding that agents progressively recruit deeper layers and shift toward corrective upda…

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…

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

The paper investigates whether modestly sized open-source language models can grasp the semantics of rare Paired-Focus constructions, finding that understanding emerges later in training and correlate…

This paper proposes a conceptual model for large language model workflows, represented as persistent knowledge objects with a distinction between deterministic computation and mediated judgment.

The paper introduces a distributional framework using Wasserstein distance to unify the semantic comparison of sparse autoencoder features across different layers and to automatically compress large f…

This paper proposes that populations of large language models can serve as a computational substrate for Artificial Life research due to their emergent dynamics and agentic capabilities.

This paper introduces a new way to represent finite posets as subwords of finite words in categories, and characterizes the monic categories that admit this representation.

The study demonstrates that domain adaptation primarily reshapes the linguistic explanatory framework of language models, causing shifts in cosmological stance secondarily, rather than directly modify…

This paper introduces dynamic epistemic paraconsistent logics AMLFI1, PALFI1, and UMLFI1, extending the epistemic paraconsistent logics KLFI1, KB4LFI1, and S5LFI1. It proves soundness and completeness…

The paper investigates compositional abilities in LLMs and humans using the Personal Relation Task, finding that LLMs excel at the structured (Intensional) task while humans are better at the real-wor…

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…

This paper proposes a framework for compositional semantic communication (CSC) in physical AI systems, enabling heterogeneous devices to transmit semantic representations that compose meaningfully at…

The paper introduces RUMBA, a new benchmark for long-term conversational memory in LLMs with a fine-grained taxonomy and unified methodology.

The authors introduce IVD-SSM, a model for narrative similarity that uses a hybrid State-Space Model and a Structurally Gated Alignment head to disentangle structural invariants from lexical variants.