Decomposing Wrong-Consensus Agreement in LLM Self-Consistency: A GPT-4.1 Case Study
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation
Beyond Predictive Fairness: Quantifying Attribution Consistency Across Demographic Groups…
Flama: a Python framework for development and deployment of production-ready APIs, machin…
A strengthening of the MCFL-ness of $O_2$
Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit …
A Few Cases Are All You Need: An Empirical Study of Annotation-Efficient LoRA Fine-Tuning…
Do Large Language Models Hallucinate Electric Fata Morganas?
Change Point--Aware Evaluation and Re-Calibration of PPG-Based Blood Pressure Estimation
Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings
Orienteering Problem with Uncertain Time-Varying Rewards: Framework and Benchmark for Eve…
Europe's Climate Ambition Under Scrutiny: Evidence from Deep Learning Emission Projections
CentaurBench: Benchmarking LLM Capabilities on Augmenting vs. Automating Real-World Work …
Performance Drift Detection in Machine Learning as a Service (MLaaS) for IoT Environments
OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic …
GCNO: Gramian Chebyshev Neural Operator for Physics-Based Compression of Wireless Channels
The Role of Grid Cells in Reducing Spatial Aliasing in Hippocampal Place Representations
DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn …
Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video…
Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in …
Science Done on a Machine by a Machine: AI Agents in Computational Chemistry
TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modali…
Composed Historical Image Retrieval by Modeling Temporal Representations
Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck
TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving
A systematic review of machine learning techniques to address diagnosis and treatment of …
From Storage to Access: Verifiable Activation of Parametric Knowledge in LLMs via Explici…
Mechanistic Interpretability of Structure-Aware Numerical Reasoning in LLaMA 3.1 8B
Coverage-Driven RTL Assertion Generation with Formal Exploration and Neuro-Symbolic Refin…
Abliteration Mitigation via Refusal Aliases