BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR
Research
Research News
New papers, breakthroughs and academic AI research
Latency and accuracy tradeoffs in Spiking Neural Networks
Research
On the spectral properties of generative denoiser Jacobians
Research
ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models
Research
Multi-Attractor GNNs: Set-Valued Expressivity Beyond Unique Equilibria
Research
One-Step Next-Latent Prediction Is Not a World Model
Research
Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment
Research
CAMEO: A Class-Activation-Mapped Equitable Overlay Framework for Fair and Robust Deep Learning-based Skin Condition Diagnosis
Research
Abductive World Modeling via Causal Representation Learning
Research
LionMuon: Alternating Spectral and Sign Descent for Efficient Training
Research
Cross-Organizational SysML Model Integration: A Survey of Challenges and AI-Supported Tasks
Research
Losing the name before the box: measuring and repairing what narrow fine-tuning costs a detector outside its deployment vocabulary
Research