Article

SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants
We introduce SplineFlow, a B-spline based flow matching algorithm for modeling complex dynamical systems.
PDF Cite Code ArXiv
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
We present the first systematic evaluation of jailbreak attacks targeting LLM safety alignment, assessing their success across the full inference pipeline, including both input and output filtering stages.
PDF Cite ArXiv
GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis
we develop a novel framework for crafting generalizable backdoors in RLHF through emotion-aware trigger synthesis
PDF Cite ArXiv
ContextFlow: Context-Aware Flow Matching For Trajectory Inference From Spatial Omics Data
We propose ContextFlow, a novel context-aware flow matching framework that incorporates prior knowledge to guide the inference of structural tissue dynamics from spatially resolved omics data.
PDF Cite Code ArXiv
Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion
We introduce MASQUE, a diffusion-based framework that generates localized adversarial makeup guided by user-defined text prompts.
PDF Cite Code ArXiv
Generalizable Targeted Data Poisoning against Varying Physical Objects
We take the first step toward understanding the real-world threats of TDP by studying its generalizability across varying physical conditions.
PDF Cite Code ArXiv
Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs
We propose a multi-agent, multi-turn jailbreak strategy that systematically bypasses LLM safety mechanisms by decomposing harmful queries into seemingly benign sub-tasks.
PDF Cite Code Source Document
DiffCAP: Diffusion-based Cumulative Adversarial Purification for Vision Language Models
This paper introduces DiffCAP, a novel diffusion-based purification strategy that can effectively neutralize adversarial corruptions in VLMs.
PDF Cite ArXiv
Predicting Time-varying Flux and Balance in Metabolic Systems using Structured Neural ODE Processes
We propose a structured neural ODE process model to estimate flux and balance samples using gene-expression time-series data
PDF Cite ArXiv OpenReview
Invisibility Cloak: Disappearance under Human Pose Estimation via Backdoor Attacks
We propose a general framework to craft invisibility cloak for human pose estimation models
PDF Cite ArXiv