arXiv AI
Jul 7
Attributing Emergence in Million-Agent Systems
arXiv:2605. 11404v2 Announce Type: replace Abstract: Large language models (LLMs) can simulate human-like reasoning and decision-making in individual agents.
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jul 7
Selective Disclosure Watermarking for Large Language Models
arXiv:2607. 05353v1 Announce Type: cross Abstract: Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs).
arXiv AI
Jul 7
Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study
arXiv:2607. 04926v1 Announce Type: cross Abstract: How does the way information reaches a transformer -- as symbolic tokens, a clean per-factor "oracle" code, or an entangled perceptual vector -- shape whether it binds that information compositionally?
arXiv AI
Jul 7
How Do Diffusion Classifiers Decide? A Bias-Centric Evaluation
arXiv:2607. 03831v1 Announce Type: cross Abstract: Diffusion models have recently been repurposed for zero-shot classification, giving rise to diffusion classifiers that identify the best-matching text prompt by minimizing the noise-prediction error.
arXiv AI
Jul 7
The agent creates, we validate: A Lightweight Framework for Agentic Artifact Generation
arXiv:2607. 02615v1 Announce Type: cross Abstract: Generating structured artifacts with Large Language Models - e.
arXiv AI
Jul 7
Additive Causal Construction for Transferable and Reconfigurable Cross-System Learning in Multi-Source Image Fusion
arXiv:2607. 02572v1 Announce Type: cross Abstract: In multi-source image fusion scenarios, heterogeneous inputs are typically driven by distinct generative mechanisms and can be viewed as a composition of multiple causal systems.
arXiv AI
Jul 7
Double-Helix Active Geometry: LiDAR-Anchored Multi-View Depth with Selective Abstention
arXiv:2607. 02561v1 Announce Type: cross Abstract: Consumer depth sensors such as the LiDAR scanner on recent iPhones provide metric range, but their useful range is short and their returns are sparse.
arXiv AI
Jul 7
MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling
arXiv:2602. 17658v3 Announce Type: replace-cross Abstract: Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale.
arXiv Machine Learning
Jul 7
A Bayesian Approach for the Network Reconstruction of Interdependent Critical Infrastructure Systems from Cascading Failures
arXiv:2211. 15590v2 Announce Type: replace Abstract: Analyzing the behavior of complex interdependent networks requires complete information about the network topology and the interdependent links across networks.
arXiv Machine Learning
Jul 7
Conservative Subject Invariant EMG-based Gesture Recognition
arXiv:2607. 03783v1 Announce Type: new Abstract: Cross-subject generalization remains a fundamental challenge in surface electromyography (sEMG)-based gesture recognition.
arXiv AI
Jul 7
STELLA: Efficient Sensor-to-LLM Translation for On-Device Human Activity Recognition
arXiv:2607. 03089v1 Announce Type: cross Abstract: HAR is increasingly expected to run continuously on edge devices, yet recent LLM-based methods remain hard to deploy: raw sensor prompts are long, cloud inference adds latency and privacy risk, and fine-tuned LLM pipelines turn general-purpose models into task-specific classifiers.
arXiv AI
Jul 7
Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents
arXiv:2604. 15579v2 Announce Type: replace-cross Abstract: There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents.
arXiv Machine Learning
Jul 7
How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation
arXiv:2605. 06605v2 Announce Type: replace Abstract: Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.
arXiv Machine Learning
Jul 7
GlaBoost: A Multimodal Structured Framework for Glaucoma Risk Stratification
arXiv:2508. 03750v2 Announce Type: replace Abstract: Early and accurate glaucoma detection is critical to prevent irreversible vision loss, yet existing AI methods often rely on unimodal inputs and lack interpretability.
arXiv AI
Jul 7
One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization
arXiv:2601. 09448v3 Announce Type: replace-cross Abstract: Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.
arXiv AI
Jul 7
A Technical Survey of Reinforcement Learning Techniques for Large Language Models
arXiv:2507. 04136v2 Announce Type: replace Abstract: This survey offers a comprehensive foundation on the integration of RL with language models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning, and Actor-Critic methods.
arXiv AI
Jul 7
Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
arXiv:2605. 28865v2 Announce Type: replace-cross Abstract: What does a world model learn from physical exploration, without any linguistic supervision?
arXiv Machine Learning
Jul 7
Towards Personalized Differentially Private Learning for Decentralized Local Graphs
arXiv:2607. 04777v1 Announce Type: new Abstract: Graph-structured data is increasingly generated and stored in decentralized environments, such as social platforms, mobile applications, and edge networks, where users maintain control over their local graph data.
arXiv AI
Jul 7
ChainReaction: Causal Chain-Guided Reasoning for Modular and Explainable Causal-Why Video Question Answering
arXiv:2508. 21010v3 Announce Type: replace-cross Abstract: Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipelines that entangle video understanding, causal inference, and answer generation.
arXiv AI
Jul 7
From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips
arXiv:2603. 22770v2 Announce Type: replace-cross Abstract: The deployment of deep neural networks (DNNs) in safety-critical edge environments necessitates robustness against hardware-induced bit-flip errors.