GRACE: Grounded Adversarial Reasoning over Canadian Law
Research
Research News
New papers, breakthroughs and academic AI research
Evaluating the Generalization of Neuroimaging Foundation Models on African Brain MRI
Research
Why Ghost Outputs Teach: A Kernel-Based Understanding of Subliminal Learning
Research
Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap
Research
WebMRIQC: A Web-Based Implementation of MRIQC for Accessible MRI Image Quality Assessment in Resource-Constrained Settings
Research
STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification
Research
Optimal No-Regret Learning for Repeated Prophet Inequality
Research
ValueDiff: Value-Geometric KV Cache Eviction for Sink-Suppressed LLMs
Research
CSC: Calibrated Simplicity for Conflict-Aware Social Bot Detection in the LLM Era
Research
HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing
Research
Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities
Research
Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter?
Research