Imagen de Portada

Stream: Scaling up Mechanistic Interpretability to Long Context in LLMs via Sparse Attention

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rosser, J, García, José Luis Redondo, Penha, Gustavo, Palla, Konstantina, Bouchard, Hugues
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence 68T40 I.2.11
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Gradient Atoms: Unsupervised Discovery, Attribution and Steering of Model Behaviors via Sparse Decomposition of Training Gradients
por: Rosser, J
Publicado: (2026)

PathFormer: A Transformer with 3D Grid Constraints for Digital Twin Robot-Arm Trajectory Generation
por: Alanazi, Ahmed, et al.
Publicado: (2025)

AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
por: Rosser, J, et al.
Publicado: (2025)

LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding
por: Jiang, Yichen, et al.
Publicado: (2026)

Infusion: Shaping Model Behavior by Editing Training Data via Influence Functions
por: Rosser, J, et al.
Publicado: (2026)

Improving Local Training in Federated Learning via Temperature Scaling
por: Lee, Kichang, et al.
Publicado: (2024)

Making High-Level AI Design Decisions Explicit Using a Binary Stream System-Designation Approach
por: Mossbridge, Julia
Publicado: (2024)

Agentic UAVs: LLM-Driven Autonomy with Integrated Tool-Calling and Cognitive Reasoning
por: Koubaa, Anis, et al.
Publicado: (2025)

Cooperative Task Execution in Multi-Agent Systems
por: Karishma, et al.
Publicado: (2024)

Vertical Federated Graph Neural Network for Recommender System
por: Mai, Peihua, et al.
Publicado: (2023)

Improving Generalization in Heterogeneous Federated Continual Learning via Spatio-Temporal Gradient Matching with Prototypical Coreset
por: Nguyen, Minh-Duong, et al.
Publicado: (2025)

ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents
por: Huo, Dongjie, et al.
Publicado: (2026)

ARISE: Agentic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper Generation
por: Wang, Zi, et al.
Publicado: (2025)

Client-Conditional Federated Learning via Local Training Data Statistics
por: Brännvall, Rickard
Publicado: (2026)

Federated k-Means over Networks
por: Yang, Xu, et al.
Publicado: (2025)

Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
por: Pepe, Alberto, et al.
Publicado: (2026)

Territory Paint Wars: Diagnosing and Mitigating Failure Modes in Competitive Multi-Agent PPO
por: Singh, Diyansha
Publicado: (2026)

Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
por: Jing, Yuheng, et al.
Publicado: (2026)

Reservoir Computing with Evolved Critical Neural Cellular Automata
por: Pontes-Filho, Sidney, et al.
Publicado: (2025)

Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics
por: Subaharan, Sukesh
Publicado: (2026)

Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Control
por: Luu, Minh Ngoc, et al.
Publicado: (2023)

Your Data, My Model: Learning Who Really Helps in Federated Learning
por: Abdurakhmanova, Shamsiiat, et al.
Publicado: (2024)

Dynamic Dual-Granularity Skill Bank for Agentic RL
por: Tu, Songjun, et al.
Publicado: (2026)

Emergent Collective Memory in Decentralized Multi-Agent AI Systems
por: Khushiyant
Publicado: (2025)

Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted Communication
por: Feng, Zikai, et al.
Publicado: (2024)

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
por: Tang, Wenjie, et al.
Publicado: (2026)

DeepPersona: A Generative Engine for Scaling Deep Synthetic Personas
por: Wang, Zhen, et al.
Publicado: (2025)

When the Agent Is the Adversary: Architectural Requirements for Agentic AI Containment After the April 2026 Frontier Model Escape
por: Mitchell, Richard Joseph
Publicado: (2026)

MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation
por: Qi, Dekang, et al.
Publicado: (2026)

Go Big or Go Home: Simulating Mobbing Behavior with Braitenbergian Robots
por: Sanoubari, Elaheh
Publicado: (2026)

AI Agents: Evolution, Architecture, and Real-World Applications
por: Krishnan, Naveen
Publicado: (2025)

Adaptive Minds: Empowering Agents with LoRA-as-Tools
por: Shekar, Pavan C, et al.
Publicado: (2025)

Fairness Dynamics in Digital Economy Platforms with Biased Ratings
por: Smit, J. Martin, et al.
Publicado: (2026)

The Provenance Paradox in Multi-Agent LLM Routing: Delegation Contracts and Attested Identity in LDP
por: Prakash, Sunil
Publicado: (2026)

A survey of multi-agent geosimulation methodologies: from ABM to LLM
por: Padilla, Virginia, et al.
Publicado: (2025)

Tazza: Shuffling Neural Network Parameters for Secure and Private Federated Learning
por: Lee, Kichang, et al.
Publicado: (2024)

Understanding Endogenous Data Drift in Adaptive Models with Recourse-Seeking Users
por: Liu, Bo-Yi, et al.
Publicado: (2025)

Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
por: Xu, Renjun, et al.
Publicado: (2026)

NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles
por: Jia, Xiao
Publicado: (2026)

Temperature Scaling Attack Disrupting Model Confidence in Federated Learning
por: Lee, Kichang, et al.
Publicado: (2026)