3 papers
cs.LG2026
Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation
Ingrid Petrova, Luan Vejsiu
Large autoregressive language models exhibit a self-correction blind spot: they reliably fix identical errors when attributed to an external source yet fail to fix the same errors…
cs.CL2026
Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scaling
Ardit Krasniqi, Luan Vejsiu, Elira Dervishi
Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning performance of large language models (LLMs) by investing additional compute at inference time…
cs.CL2025
Context-Enhanced Granular Edit Representation for Efficient and Accurate ASR Post-editing
Luan Vejsiu, Qianyu Zheng, Haoxuan Chen +1
Despite ASR technology being full-scale adopted by industry and for large portions of the population, ASR systems often have errors that require editors to post-edit text quality.…