Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Mode…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
EGT-KG: Evidence-Grounded Typed KG Retrieval for Practical Scientific QA with Small Langu…
Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents
Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs
MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries
Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE App…
Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architec…
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell…
Verifiable Disaster Storylines and Causal Knowledge Graphs: A Citation-Grounded Pipeline …
S^3martCirc: Self-supervised Smart Circuit Discovery
A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System…
Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segme…
Can machines think efficiently?
Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Har…
Socrates went Nuclear: Comparing Interaction Strategies for AI systems in a Learning Cont…
KV Cache Offloading for Context-Intensive Tasks
ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning
Towards Effective Structured Context Modeling for Conversational Recommender Systems via …
Auditing Harness Tampering in Self-Improving Agents
EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target …
WiseSpec: Requirements-Driven Agents for Code Generation
GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel …
LLM-Driven Autonomous Vehicles Inherit Human Driver Biases in Pedestrian Yielding: Result…
The Safeguard Worked. Is the LLM System Safer?
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Cla…
The Alexander-Hirschowitz theorem for neurovarieties
User Representation via Cross Multi-source Behavior Pre-training for Mobile Games
ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation