Latest AI research papers from arXiv — helucino

1d
Project2Task: Graph-Guided Project-Level Planning for Autonomous Research
arXiv cs.AI
1d
Matrix Zonotopic Attention: A Context-Adaptive Value Projection for Set Transformers
arXiv cs.AI
1d
Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots
arXiv cs.AI
1d
Continual Learning in Transition
arXiv cs.AI
1d
Comparative Approaches to Agent Retrieval over Large Skill Libraries
arXiv cs.AI
1d
Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation
arXiv cs.AI
1d
EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents
arXiv cs.AI
1d
Training a Conditioned Video Game Agent on a VLM Annotated Dataset
arXiv cs.AI
1d
Nonvisual Classification of Ground-Condition by Artificial Proprioception in an Amoeba-Inspired Autonomous Walking Robot
arXiv cs.AI
1d
VLMs for Videogame Data Annotation
arXiv cs.AI
1d
GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification
arXiv cs.AI
1d
BlockPython: A Process-Aware Agent-Supported Platform for the Transition from Block-Based to Python Programming
arXiv cs.AI
1d
When History Lies: Evaluating and Improving Tool Use under Misleading Multi-Turn Histories
arXiv cs.AI
1d
A Study of ASR Adaptation and Representation Dimensionality Reduction in Persian Speech Emotion Recognition Using Whisper
arXiv cs.AI
1d
MameLoshnLM: Yiddish Language Model and Evaluation Benchmark
arXiv cs.AI
1d
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
arXiv cs.AI
1d
Subliminal Learning is Non-Semantic Distillation
arXiv cs.AI
1d
FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India
arXiv cs.AI
1d
Why the Third Axis Is Freedom
arXiv cs.AI
1d
Learning Context-Free Grammars for Grammar-Constrained Decoding via Declarative Agentic Programming with Guarantees
arXiv cs.AI
1d
Unified Agent: Managing Interactions across Devices
arXiv cs.AI
1d
Innocent Panels, Hateful Stories: Evaluating and Detecting Hateful Intent in Multi-Turn Visual Story Generation
arXiv cs.AI
1d
Spectral Aliasing Pretext: A novel task for Self-Supervised fault diagnosis in rotating machinery
arXiv cs.AI
1d
CASCADE: An Agentic Regulatory Network Framework for Patient-Data-Validated Downstream Perturbation Prediction
arXiv cs.AI
1d
Challenges for Musical Education in the Age of AI and Digital Transformation
arXiv cs.AI
1d
CodeGrep: An RL-Trained Retrieval Agent for LLM Coding Agents
arXiv cs.AI
1d
A Two-Tier Perspective on Inference-Time Parallelism in Multi-Agent LLM Systems
arXiv cs.AI
1d
When Do Prompt-Side Agent Playbooks Transfer? Accuracy, Cost, and Runtime Shift in Agent Deployment
arXiv cs.AI
1d
From Passive Mirrors to Active Agents: Holonic Digital Twins for Physical AI over Networks
arXiv cs.AI
1d
MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration
arXiv cs.AI