Bo Liu
3 papers · Latest:
Computer Vision
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture
SenseNova-U1 introduces a unified architecture (NEO-unify) that seamlessly integrates multimodal understanding and generation, outperforming specialized VLMs.
2605.12500
Cryptography & SecurityCSC: Turning the Adversary's Poison against Itself
CSC neutralizes backdoor attacks by identifying and relabeling poisoned data clusters, achieving near-zero attack success with minimal accuracy loss.
2604.21416
Machine LearningFrom $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
PreRL and DSRL enhance LLM reasoning by applying reward-driven updates in the pre-train space, effectively pruning incorrect reasoning paths.
2604.14142
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.