Skip to content

Author

Albert No

We have 7 of 26 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs

Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user preferences may be inappropriate to apply. We introduce BenchPreS, which evaluates wh...

Sangyeon Yoon, SunKyoung Kim, Hyesoo Hong et al. · 8 citations · ⚡2
#machine learning Preprint Oct 2026

Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following

CALIF is a lightweight method that augments verifier rewards with a calibrated likelihood-based bonus to preserve response quality and outperforms corresponding base policies in 40 of 45 model-metric comparisons across three rubric-based instruction-following benchmarks.

Sangyeon Yoon, Wooseok Seo, Hamish Ivison et al. · 0 citations
#artificial intelligence Preprint May 2026

JUMP: Efficient Membership Inference on Fine-Tuned Diffusion Language Models

JUMP is proposed, an efficient MIA that exploits the ability of dLLMs to predict masked tokens in parallel that improves mean ROC-AUC over a prior multi-mask attack and is extended to the target-only setting by replacing target-reference scoring with relative token preference.

Yeachan Jun, Albert No · 0 citations
#artificial intelligence Preprint May 2026

Diversifying RLVR Rollouts via First-Token Exploration

This work identifies the first token of the response as a structurally distinct target for diversification, largely overlooked in prior work, and finds that the first-token distribution is sharply concentrated and only weakly related to downstream correctness, as lower-probability candidates can yield similarly accurat...

Soeun Kim, Albert No · 2 citations

Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs

This work traces diversity loss to low-confidence remasking not to arbitrary-order generation itself, but largely to low-confidence remasking (LCR), a widely used decoding rule, and introduces Entropy-Guided Initialization (EGI), which samples the first token at the highest-entropy position and then follows TPP.

Moongyu Jeon, Dongjae Jeon, Bumjun Kim et al. · 1 citation
#natural language process... Preprint Sep 2026

Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models

This work shows that paraphrase robustness is a core requirement for reliable VLM-based reward modeling in robotics and introduces ROBORMBENCH, a benchmark with 2,390 real-robot trajectories, ground-truth progress labels, and 21,673 verified paraphrases spanning lexical, syntactic, and action-goal rewrites.

Wonje Jeung, Sangyeon Yoon, Hyesoo Hong et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.