arXiv:2605.20389v1 Announce Type: cross Abstract: Functional MRI data exhibit high-dimensional spatiotemporal structure, making both prediction and decoding challenging. In this work, we investigate neural integral-operator-based models for encoding and decoding tasks in fMRI, with particular emphasis on the role of nonlocal spatiotemporal context. We implement a latent neural integral operator framework that performs fixed point […]
SymbolicLight V1: Spike-Gated Dual-Path Language Modeling with High Activation Sparsity and Sub-Billion-Scale Pre-Training Evidence
arXiv:2605.21333v1 Announce Type: cross Abstract: Natively trained spiking language models struggle to combine Transformer-like language quality, stable multi-domain pre-training, and high activation sparsity. We present SymbolicLight V1, a spike-gated dual-path language model that combines binary Leaky Integrate-and-Fire spike dynamics with a continuous residual stream. Its Dual-Path SparseTCAM module replaces dense self-attention with an exponential-decay aggregation […]
Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models
arXiv:2602.16608v2 Announce Type: replace-cross Abstract: Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions, capture either local token-level attributions or global attention patterns without unification, and lack context-awareness of inter-token dependencies and structural components. They also fail […]
Towards Context-Invariant Safety Alignment for Large Language Models
arXiv:2605.20994v1 Announce Type: cross Abstract: Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when the same intent is wrapped in adversarial wording. We suggest that robust safety requires context-invariant alignment, where behavior depends on the underlying intent […]
Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
arXiv:2605.20296v1 Announce Type: cross Abstract: Fine-tuning a language model for a target task routinely degrades capabilities the training data never explicitly threatened. We study this phenomenon, known as catastrophic forgetting, and propose a post-hoc repair solution that uses only the pretrained checkpoint $W_mathrmbase$ and its fine-tuned descendant $W_mathrmft$. The goal is not merely to revert […]
Tracing the ongoing emergence of human-like reasoning in Large Language Models
arXiv:2605.21299v1 Announce Type: cross Abstract: Humans effortlessly go beyond literal meanings: If you mow the lawn, I will give you fifty dollars, is typically understood as implying that the speaker will pay only if the lawn is mowed, whereas If you are hungry, there is pizza in the oven implies that pizza is available regardless […]
Neural Estimation of Pairwise Mutual Information in Masked Discrete Sequence Models
arXiv:2605.20187v1 Announce Type: cross Abstract: Understanding dependencies between variables is critical for interpretability and efficient generation in masked diffusion models (MDMs), yet these models primarily expose marginal conditional distributions and do not explicitly represent inter-variable dependence. We propose a neural framework for estimating pairwise conditional mutual information (MI) directly from the hidden states of a […]
Pseudo-Siamese Network for Planning in Target-Oriented Proactive Dialogues
arXiv:2605.20195v1 Announce Type: cross Abstract: A target-oriented proactive dialogue system is designed to steer conversations toward predefined targets while actively providing suggestions. The core paradigm of such a system is to plan a reasonable dialogue path and subsequently guide language models (e.g., pre-trained or large language models) to generate responses, where dialogue path planning serves […]
Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
arXiv:2605.20270v1 Announce Type: cross Abstract: A local specialist LLM, fine-tuned with reinforcement learning from verifiable rewards (RLVR) on operator-local data, is installed in a regulated organization with per-deployment error budget $alpha$. The operator needs a safety certificate for this deployment’s stream at every round: no pooling across deployments, no waiting for a long-run average. Existing […]
JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QA
arXiv:2605.20284v1 Announce Type: cross Abstract: Industrial anomaly detection has been significantly advanced by Large Multimodal Models (LMMs), enabling diverse human instructions beyond detection, particularly through visually grounded reasoning for better image understanding. However, LMMs lack domain-specific knowledge, which limits their ability to generate accurate responses in complex industrial scenarios. In this work, we present JUDO, […]
Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
arXiv:2605.20241v1 Announce Type: cross Abstract: Prompt-level safety probes for large language models use hidden-state representations to separate safe from unsafe prompts, but strong average detection performance does not explain the geometry of this separation. In particular, it remains unclear how safety evidence is formed across layers, which aspects of that layer-wise geometry support low-false-positive decisions, […]
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
arXiv:2605.19503v2 Announce Type: replace-cross Abstract: Reinforcement learning for legged locomotion has matured into a stack of multi-component reward functions and physics-engine benchmarks whose morphologies are uniformly derived from real commercial hardware. Game NPCs, however, are bound by stylistic constraints absent from sim-to-real robotics and routinely take the form of creatures with no real-robot counterpart. We […]