12 papers · 1 filter
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…
JUMP: Single-Pass Membership Inference on Fine-Tuned Diffusion Language Models
Yeachan Jun, Albert No
Public open-weight language models are often fine-tuned on private or domain-specific data before deployment, creating a need to audit whether individual records were used during a…
Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR
Soeun Kim, Albert No
Reinforcement Learning with Verifiable Rewards (RLVR) trains reasoning models without labeled trajectories, relying on grouped rollouts to expose the policy to alternative reasonin…
VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
Hyesoo Hong, Minsoo Kim, Wonje Jeung +3
Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lack robust control over basic visual operations. We study \textit{line tracing}, w…
Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning
Shin So, Kyelim Lee, Albert No
Critical-data-size accounts of grokking suggest a natural post-threshold intuition: once training data is sufficient to identify the underlying rule, additional data should acceler…
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
Sangyeon Yoon, Wonje Jeung, Yoonjun Cho +2
Fine-tuning APIs make frontier LLMs easy to customize, but they can also weaken safety alignment during fine-tuning. While prior work shows that benign supervised fine-tuning (SFT)…