Olapa-MCoT: Enhancing the Chinese Mathematical Reasoning Capability of LLMs
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement Le…
SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infill…
Comparing Explanations is Not Enough, Explain the Change: New Standards are Needed to Exp…
Fuzzy Segmentations of a String
Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations
Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budge…
Automatic Model Card Generation Using an LLM
Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objec…
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretrai…
PROOF-Gen: From Optimized Data to Better Distillation
Luce: Relightable Gaussians for 3D Asset Generation
Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned…
Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses
Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learni…
BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
Former Google Researchers Want to Keep Humans in AI Driver’s Seat
CAFE: Self-Improving Search Agents Need Co-Evolving Feedback
Image Difference Quantification Using Autoencoder-Based Latent Representations
Linear Probing Provides Robust and Efficient Detection of Machine-Generated Text
Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnost…
RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
The RAT: A Unified Bayesian Model for RAG Evaluation
SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents
$(\text{DNN})^2$: Doubly Non-Negative Relaxations for Deep Neural Networks
MIT AI forecasts extreme weather without historical data
Interpretable Fundus Image Classification via Ring-Based Retinal Vasculature Features
Lost in Speech: Trilingual Spoken Hallucination Detection Across Audio and Transcripts