collaborators

7 papers

cs.CV2026

WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark

Yida Yin, Harish Krishnakumar, Chung Peng Lee +9

In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual…

cs.LG2026

Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization

Yung-Chin Chen, Chung Peng Lee, Ze-Wei Liou +1

Massive activation spikes in Large Language Models (LLMs) severely degrade quantization by stretching dynamic ranges. While prior hypotheses characterize these as high-level scalar…

cs.RO2026

The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space

Bing-Cheng Chuang, I-Hsuan Chu, Bor-Jiun Lin +3

Diffusion-based Vision-Language-Action policies achieve remarkable success in robotic manipulation, yet commit a fundamental geometric error we term the $\textbf{Euclidean Fallacy}…

cs.RO2026

ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning

Byung-ju Kim, Jinu Pahk, Chungwoo Lee +6

Behavior-cloning based visuomotor policies enable precise manipulation but often inherit the slow, cautious tempo of human demonstrations, limiting practical deployment. However, p…

cs.CY2026

How Do Data Owners Say No? A Case Study of Data Consent Mechanisms in Web-Scraped Vision-Language AI Training Datasets

Chung Peng Lee, Rachel Hong, Harry H. Jiang +3

The internet has become the main source of data to train modern text-to-image or vision-language models, yet it is increasingly unclear whether web-scale data collection practices…

cs.LG2026

The Geometry of Alignment Collapse: When Fine-Tuning Breaks Safety

Max Springer, Chung Peng Lee, Blossom Metevier +5

Fine-tuning aligned language models on benign tasks unpredictably degrades safety guardrails, even when training data contains no harmful content and developers have no adversarial…