6 papers
Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models
Wonje Jeung, Sangyeon Yoon, Hyesoo Hong +6
Vision-language models are increasingly used as reward functions for robotic learning, but this role requires paraphrase invariance: the same trajectory should receive the same rew…
Memorization In Stable Diffusion Is Unexpectedly Driven by CLIP Embeddings
Bumjun Kim, Albert No
Understanding how textual embeddings contribute to memorization in text-to-image diffusion models is crucial for both interpretability and safety. This paper investigates an unexpe…
DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
Bumjun Kim, Dongjae Jeon, Moongyu Jeon +1
Parallel decoding for Diffusion LLMs (dLLMs) is difficult because each denoising step provides only token-wise marginal distributions, while unmasking multiple tokens simultaneousl…
A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
Moongyu Jeon, Sangwoo Shin, BumJun Kim +2
Autoregressive language models (ARMs) suffer from the reversal curse: after learning '' is ,'' they often fail on the reverse query '' is .'' Masked diffusion language…
Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
Bumjun Kim, Dongjae Jeon, Dueun Kim +2
Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive models, offering flexible generation orders and strong performance on complex reas…
Small Language Models are Equation Reasoners
Bumjun Kim, Kunha Lee, Juyeon Kim +1
Chain-of-Thought (CoT) reasoning has enabled Large Language Model (LLM) to achieve remarkable performance in various NLP tasks, including arithmetic problem-solving. However, this…