· ai
[Paper] Model Merging via Multi-Teacher Knowledge Distillation
Model merging has emerged as a lightweight alternative to joint multi-task learning (MTL), yet the generalization properties of merged models remain largely une...
-
- · ai
[Paper] SMART SLM: Structured Memory and Reasoning Transformer, A Small Language Model for Accurate Document Assistance
The user of Engineering Manuals (EM) finds it difficult to read EM s because they are long, have a dense format which includes written documents, step by step p...
- · ai
[Paper] Learning Factors in AI-Augmented Education: A Comparative Study of Middle and High School Students
The increasing integration of AI tools in education has led prior research to explore their impact on learning processes. Nevertheless, most existing studies fo...
- · ai
[Paper] LookPlanGraph: Embodied Instruction Following Method with VLM Graph Augmentation
Methods that use Large Language Models (LLM) as planners for embodied instruction following tasks have become widespread. To successfully complete tasks, the LL...
- · ai
[Paper] Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks
In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to prac...
- · ai
[Paper] Assessing the Software Security Comprehension of Large Language Models
Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematic...
- · ai
[Paper] Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking
Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise t...
- · ai
Is Your Model Time-Blind? The Case for Cyclical Feature Encoding
How cyclical encoding improves machine learning prediction The post Is Your Model Time-Blind? The Case for Cyclical Feature Encoding appeared first on Towards D...
- · ai
[Paper] SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation
Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the da...
- · ai
[Paper] Beyond Context: Large Language Models Failure to Grasp Users Intent
Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understa...
- · ai
AlphaFold Changed Science. After 5 Years, It’s Still Evolving
WIRED spoke with DeepMind’s Pushmeet Kohli about the recent past—and promising future—of the Nobel Prize-winning research project that changed biology and chemi...
- · ai
[Paper] zkFL-Health: Blockchain-Enabled Zero-Knowledge Federated Learning for Medical AI Privacy
Healthcare AI needs large, diverse datasets, yet strict privacy and governance constraints prevent raw data sharing across institutions. Federated learning (FL)...