Does the Truthfulness Signal Survive Code-Mixing? Probing Hidden States for Hallucination Detection in Hinglish
Research
Research News
New papers, breakthroughs and academic AI research
Using Composition Operators to Linearize LLM Semantic Transformations
Research
Role-Aware Morgan Fingerprints for Reaction Yield Prediction
Research
Contrastive World Models
Research
DOA-SORT: Directional Occlusion-Aware Multi-Object Tracking with Distributional Observations
Research
Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs
Research
Beyond the Stitching Assumption: A Unified Framework for Multimodal Synthetic Data Evaluation via Semantic Quantization
Research
Is Imagination Derived from Hallucination? A Cross-Taxonomy Evaluation of Imagination and Hallucination in Large Language Models
Research
MechaTerp-TRACE: A Novel Approach for Component Ablation Analysis in Language Models
Research
ZIL: Zero-shot Image-to-LiDAR Registration
Research
Towards Robust Classroom Attendance: A Comprehensive Evaluation of Face Detection and Recognition Models
Research
DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models
Research