collaborators

5 papers

cs.AI2026

Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT

Cen Lu, Yung-Chen Tang, Andrea Cavallaro

Developers judge a model checkpoint by how it behaves. After supervised fine-tuning (SFT), two checkpoints that perform about the same across relevant benchmarks are treated as int…

cs.AI2026

Sparse Neuron Ablation Triggers Catastrophic Collapse of the Language Core in Large Vision-Language Models

Cen Lu, Yung-Chen Tang, Andrea Cavallaro

Large Vision-Language Models (LVLMs) have shown impressive multimodal understanding capabilities, yet the structures that sustain their functionality remain poorly understood from…

cs.CL2026

Geometric Latent Reasoning Induces Shorter Generations in LLMs

Shashi Kumar, Yacouba Kaloga, Petr Motlicek +2

Large language models solve complex problems by generating lengthy chains of explicit reasoning tokens. While effective, this makes reasoning expensive, length-sensitive, and const…

cs.CV2026

FlowOVD: Learning Generative Latent Flows for Zero-shot Open-vocabulary Detection

Yao Wei, Andrea Cavallaro, Changjae Oh

Open-vocabulary object detection (OVD) has achieved remarkable progress through large-scale vision-language pre-training. Existing methods, however, typically formulate OVD as a di…

cs.LG2025

CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning

Yung-Chen Tang, Pin-Yu Chen, Andrea Cavallaro

Allocating more computation during inference time (test-time scaling) improves language model performance, especially for reasoning tasks. However, popular methods like Best-of-