30 papers
How Can Driving World Models Do Counterfactual Prediction?
Jiaru Zhang, Can Cui, Yi Xu +3
Driving world models are often interpreted as counterfactual simulators for observed driving episodes: given a factual driving log, they are asked what would have happened under an…
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
Yikun Bai, Binghang Lu, Yikai Liu +7
The paper presents SE(3)-MeanFlow, a generative model that creates protein backbone structures directly on the SE(3) Lie group using a few inference steps, avoiding costly ODE inte…
Sticky Jump Diffusions: A Unifying View of Masked, Continuous, and Hybrid Diffusion
Pascal Jutras-Dubé, Patrick Pynadath, Jeremy Lu +2
We introduce Sticky Jump Diffusions (SJDs), continuous-time Markov processes on whose discrete anchors are token embeddings. In forward time, anchors release their ma…
Gradient-Guided Reward Optimization for Inference-time Alignment
Hankun Lin, Ruqi Zhang
Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation. While inference-time alignment methods such as Best-of- and…
VERA: Variational Inference Framework for Jailbreaking Large Language Models
Anamika Lochab, Lu Yan, Patrick Pynadath +2
The rise of API-only access to state-of-the-art LLMs highlights the need for effective black-box jailbreak methods to identify model vulnerabilities in real-world settings. Without…
VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
Qilin Liao, Anamika Lochab, Ruqi Zhang
Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimoda…