arXiv:2605.00402v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) provide a promising framework for energy-efficient and biologically grounded computation; however, scalable learning in deep recurrent architectures with sparse connectivity remains a major challenge. In this work, we propose a structured multi-layer recurrent SNN architecture composed of locally dense recurrent layers augmented with sparse small-world long-range […]
Impact of Task Phrasing on Presumptions in Large Language Models
arXiv:2605.00436v1 Announce Type: cross Abstract: Concerns with the safety and reliability of applying large-language models (LLMs) in unpredictable real-world applications motivate this study, which examines how task phrasing can lead to presumptions in LLMs, making it difficult for them to adapt when the task deviates from these assumptions. We investigated the impact of these presumptions […]
Attention Is Where You Attack
arXiv:2605.00236v1 Announce Type: cross Abstract: Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understood. We introduce the Attention Redistribution Attack (ARA), a white-box adversarial attack that identifies safety-critical attention heads and crafts nonsemantic adversarial tokens that redirect attention away from […]
Retrieval-Augmented Reasoning for Chartered Accountancy
arXiv:2605.00257v1 Announce Type: cross Abstract: The inception of Large Language Models (LLMs) has catalyzed AI adoption in the finance sector, yet their reliability in complex, jurisdiction-specific tasks like Indian Chartered Accountancy (CA) remains limited. The models display difficulty in executing numerical tasks which require multiple steps while also needing advanced knowledge about legal regulations and […]
When Do Diffusion Models learn to Generate Multiple Objects?
arXiv:2605.00273v1 Announce Type: cross Abstract: Text-to-image diffusion models achieve impressive visual fidelity, yet they remain unreliable in multi-object generation. Despite extensive empirical evidence of these failures, the underlying causes remain unclear. We begin by asking how much of this limitation arises from the data itself. To disentangle data effects, we consider two regimes across different […]
Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis
arXiv:2605.00314v1 Announce Type: cross Abstract: An agent skill is a configuration package that equips an LLM-driven agent with a concrete capability, such as reading email, executing shell commands, or signing blockchain transactions. Each skill is a hybrid artifact-a structured half declares executable interfaces, while a prose half dictates when and how those interfaces fire-and the […]
AI Adoption Among Teachers: Insights on Concerns, Support, Confidence, and Attitudes
arXiv:2605.00343v1 Announce Type: cross Abstract: The study examines the adoption of artificial intelligence (AI) tools in education by analyzing the roles of institutional support, teacher confidence, and teacher concerns. It aims to determine whether teacher concerns moderate the relationship between institutional support and two outcomes: teacher confidence and attitudes toward AI adoption. The sample included […]
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
arXiv:2605.00356v1 Announce Type: cross Abstract: Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. We present MemRouter, a write-side memory router that decouples memory admission from the downstream answer backbone and replaces per-turn memory-management decoding with an […]
Social Bias in LLM-Generated Code: Benchmark and Mitigation
arXiv:2605.00382v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed to generate code for human-centered applications where demographic fairness is critical. However, existing evaluations focus almost exclusively on functional correctness, leaving social bias in LLM-generated code largely unexamined. Extending our prior work on Solar, we conduct a comprehensive empirical study using SocialBias-Bench, a […]
Trees to Flows and Back: Unifying Decision Trees and Diffusion Models
arXiv:2605.00414v1 Announce Type: cross Abstract: Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiting regimes. Our unification reveals a shared optimization principle: emphGlobal Trajectory […]
Feedback Lunch: Learned Feedback Codes for Secure Communications
arXiv:2510.16620v3 Announce Type: replace-cross Abstract: We consider reversely-degraded secure-communication channels, for which the secrecy capacity is zero if there is no channel feedback. Specifically, we focus on a seeded modular code design for the block-fading Gaussian wiretap channel with channel-output feedback, combining universal hash functions for security and learned feedback-based codes for reliability. The trade-off […]
Improving LLM Code Generation via Requirement-Aware Curriculum Reinforcement Learning
arXiv:2605.00433v1 Announce Type: cross Abstract: Code generation, which aims to automatically generate source code from given programming requirements, has the potential to substantially improve software development efficiency. With the rapid advancement of large language models (LLMs), LLM-based code generation has attracted widespread attention from both academia and industry. However, as programming requirements become increasingly complex, […]