About
Research & Development
Unmasking and Escaping the OOD Trap in AI Knowledge Transfer
TLDR: This research paper investigates the 'Out-of-Distribution (OOD) trap effect' in Data-Free Knowledge Distillation (DFKD) when learning from Non-Transferable Learning (NTL) teachers. NTL teachers,...
Research & Development
Enhancing Autonomous Vehicle Safety: How Vision-Language Models Predict Pedestrian Intentions
TLDR: A new study demonstrates how Vision-Language Foundation Models (VLFMs) significantly improve pedestrian crossing intention prediction for autonomous vehicles. By integrating multimodal data through...
Research & Development
Optimizing Clinical Reasoning in Language Models: The Role of Prompts and Efficient Fine-Tuning
TLDR: A study on clinical natural language inference (NLI) found that prompt structure significantly drives LLM performance (up to 44% variance). It showed that...
Research & Development
Learning Permutations to Optimize Traveling Salesman Tours
TLDR: A new unsupervised, non-autoregressive framework for the Traveling Salesman Problem (TSP) learns solutions directly from permutations without explicit search. By transforming Hamiltonian cycles,...
Research & Development
Unveiling Prediction Confidence in Tsetlin Machines: A New Probability Score for Explainable AI
TLDR: This research introduces a novel probability score for Tsetlin Machines (TMs) that quantifies the certainty of their predictions. Derived from the TM's learning...
Research & Development
Breaking Free from Pronunciation Lexicons: A New Approach to Crosslingual Speech Recognition
TLDR: A new method, JSA-SPG, enables pronunciation-lexicon free training for phoneme-based crosslingual ASR. It uses a latent variable model (S2P, P2G) and an auxiliary...