2 citations · 4 across the 13 of their papers we have counts for
4 papers · 1 filter
Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards
Qirun Zeng, Manhin Poon, Xiangxiang Dai +2
Adversarial attacks on bandits aim to mislead a learner toward a target arm while keeping the attack cost small. Existing attacks typically achieve this by suppressing non-target a…
Quality-Aware Cross-Model Computation Reuse
Jin Cheng, Xiangxiang Dai, Maoli Liu +3
An intermediate result computed by one model can be reused by other models to perform their tasks. Existing work mainly focuses on practical execution, leaving a theoretical gap in…
Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens
Yizhen Yao, Qinglin Zhu, Runcong Zhao +4
Diffusion Large Language Models (dLLMs) offer a promising avenue for parallel generation but face a trade-off between decoding speed and quality. While revocable decoding strategie…
Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
Zeyu Zhang, Xiangxiang Dai, Ziyi Han +2
Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, r…