arXiv:2603.05414v2 Announce Type: replace Abstract: Introspection is a foundational cognitive ability, but its mechanism is not well understood. Recent work has shown that AI models can introspect. We study the mechanism of this introspection. We first extensively replicate Lindsey (2025)’s thought injection detection paradigm in large open-source models. We show that introspection in these models […]
LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents
arXiv:2507.10610v3 Announce Type: replace-cross Abstract: Graphical user interface (GUI) agents built on multimodal large language models (MLLMs) have recently demonstrated strong decision-making abilities in screen-based interaction tasks. However, they remain highly vulnerable to pop-up-based environmental injection attacks, where malicious visual elements divert model attention and lead to unsafe or incorrect actions. Existing defense methods either […]
Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
arXiv:2603.16105v2 Announce Type: replace-cross Abstract: Post-training model compression is essential for enhancing the portability of Large Language Models (LLMs) while preserving their performance. While several compression approaches have been proposed, less emphasis has been placed on selecting the most suitable set of data (the so-called emphcalibration data) for finding the compressed model configuration. The choice […]
INTERACT: An AI-Driven Extended Reality Framework for Accesible Communication Featuring Real-Time Sign Language Interpretation and Emotion Recognition
arXiv:2604.05605v1 Announce Type: cross Abstract: Video conferencing has become central to professional collaboration, yet most platforms offer limited support for deaf, hard-of-hearing, and multilingual users. The World Health Organisation estimates that over 430 million people worldwide require rehabilitation for disabling hearing loss, a figure projected to exceed 700 million by 2050. Conventional accessibility measures remain […]
MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control
arXiv:2604.06156v1 Announce Type: cross Abstract: MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental challenges. First, structural misalignment between instance-level reasoning and pairwise contrastive supervision may lead to shortcut behavior, where the model merely learns the superficial format […]
TS-Agent: Understanding and Reasoning Over Raw Time Series via Iterative Insight Gathering
arXiv:2510.07432v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit strong symbolic and compositional reasoning, yet they struggle with time series question answering as the data is typically transformed into an LLM-compatible modality, e.g., serialized text, plotted images, or compressed time series embeddings. Such conversions impose representation bottlenecks, often require cross-modal alignment or finetuning, and […]
Gradual Cognitive Externalization: From Modeling Cognition to Constituting It
arXiv:2604.04387v2 Announce Type: replace Abstract: Developers are publishing AI agent skills that replicate a colleague’s communication style, encode a supervisor’s mentoring heuristics, or preserve a person’s behavioral repertoire beyond biological death. To explain why, we propose Gradual Cognitive Externalization (GCE), a framework arguing that ambient AI systems, through sustained causal coupling with users, transition from […]
NativQA Framework: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge
arXiv:2504.05995v3 Announce Type: replace-cross Abstract: The rapid progress of large language models (LLMs) raises concerns about cultural bias, fairness, and performance in diverse languages and underrepresented regions. Addressing these gaps requires large-scale resources grounded in multilingual, local, and cultural contexts. We systematize and extend the earlier NativQA framework to multimodality by adding image, audio, and […]
StateX: Enhancing RNN Recall via Post-training State Expansion
arXiv:2509.22630v2 Announce Type: replace-cross Abstract: Recurrent neural networks (RNNs), such as linear attention and state-space models, have gained popularity due to their constant per-token complexity when processing long contexts. However, these recurrent models struggle with tasks that require accurate recall of contextual information from long contexts, because all contextual information is compressed into a fixed-size […]
Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders
arXiv:2601.02978v2 Announce Type: replace-cross Abstract: Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable control of complex, behavior-level semantic attributes in language generation. In this paper, we propose a Sparse Autoencoder-based […]
Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
arXiv:2512.16251v4 Announce Type: replace-cross Abstract: We introduce the Consensus-Bottleneck Asset Pricing Model (CB-APM), which embeds aggregate analyst consensus as a structural bottleneck, treating professional beliefs as a sufficient statistic for the market’s high-dimensional information set. Unlike post-hoc explainability approaches, CB-APM achieves interpretability-by-design: the bottleneck constraint functions as an endogenous regularizer that simultaneously improves out-of-sample predictive […]
Graph-Theoretic Analysis of Phase Optimization Complexity in Variational Wave Functions for Heisenberg Antiferromagnets
arXiv:2602.04943v3 Announce Type: replace-cross Abstract: We study the computational complexity of learning the ground state phase structure of Heisenberg antiferromagnets. Representing Hilbert space as a weighted graph, the variational energy defines a weighted XY model that, for $mathbbZ_2$ phases, reduces to a classical antiferromagnetic Ising model on that graph. For fixed amplitudes, reconstructing the signs […]