Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
Gio Huh, Dhruv Sheth, Rayhan Zirvi +1
While Vision-Language Models (VLMs) excel in many areas, they struggle with complex spatial reasoning, which requires problem decomposition and strategic tool use. Fine-tuning smal…
cs.LG2025
Discovering Hidden Algebraic Structures via Transformers with Rank-Aware Beam GRPO
Jaeha Lee, Gio Huh, Ning Su +1
Recent efforts have extended the capabilities of transformers in logical reasoning and symbolic computations. In this work, we investigate their capacity for non-linear latent patt…