AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation
Research
Research News
New papers, breakthroughs and academic AI research
Active Feature Acquisition for Cost-Efficient Temporal Prediction with Reduced Participant Burden
Research
The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception
Research
RACE-FPP: A Robust AI-assisted Characterisation Enhancement for Fringe Projection Profilometry
Research
View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing
Research
MacJEPA: Missingness-Robust Audio-Visual Recognition from Untrimmed Egocentric Videos
Research
Catastrophic Forgetting in Sequential Thermal Anti-UAV Detection: The Role of Scale-Conditioned Gradient Imbalance
Research
PIE-PS: Photometric Stereo from Physical Irradiance Event Streams
Research
Structure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-Bandits
Research
Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment
Research
SEAL: Mixture-Closed Additive Reconstruction and Refinement-Aware Expert Routing for Efficient Speech Separation
Research
Jailbreaking Open-Weight LLMs via Random Embedding Perturbations
Research