AI
Lexical Perturbations Disrupt LLM Reasoning: An Empirical Study of Attention Diversion
Researchers studied how large language models (LLMs) perform when their input text is intentionally ...
AI
Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints
Researchers from Meta and its collaborators have developed a new framework called Meta-Ctrl that gen...
AI
Why Does Robustness Reduce Superposition?
Researchers have been trying to understand why adversarial training reduces the phenomenon of superp...
AI
Joint Causal Structure and Cluster Discovery Using Variational Inference
Researchers have developed a new approach to understand relationships between groups of variables in...
AI
Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARN
Researchers from the A4/LEARN study have developed a method to optimize the use ...
AI
FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization
Researchers have proposed a new framework called FreKoo++, which aims to improve...
AI
Improving Few-Step Language Flows with Untied Self-Conditioning
Researchers have proposed a new approach called Untied Self-Conditioning to impr...
AI
Training-Free VLM Personalization via Calibrated Residual Decoding
Researchers have proposed a method to personalize vision-language models without...