EEG-AS: Instance-Level Foundation Model Selection for EEG Foundation Models via Behavior …
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
The Safeguard Worked. Is the LLM System Safer?
Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Hete…
EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target …
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
Intelligent Edge Computing
Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy
WiseSpec: Requirements-Driven Agents for Code Generation
AI Should Not Only Be Helpful. It Should Be Contingent. Artificial Intimacy, Sycophancy, …
Assessing Alignment and Stability of Feature Importance Explanations via Weight of Eviden…
Provably Efficient Federated Reinforcement Learning with Linear Function Approximation an…
Visual Framing for News Stance Detection via Image Generation
HyperWorld: Hypergraph-Structured State Serialization Improves Learned Textual World Mode…
RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks
RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces
I-CARE: Analysis of interference-related phenomena in a controllable, diverse and represe…
VOIM: Training-Free Open-Vocabulary 3D Instance Mapping for RGB-D and Monocular SLAM
A Formal Analysis of Agent Payment Protocols
TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data
REAL-Q: E2E LLM Quantization via Dynamic Gradient Descent
Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation
RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Pro…
Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
Confess What You Know: Forget-Set Misalignment with Model Knowledge in LLM Unlearning
ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthet…
GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments
EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematica…
EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems