32 papers
Outcome-Guided Distillation: A Teacher-Student Framework to Advance VLM Reasoning in Autonomous Driving
Zeyu Dong, Yimin Zhu, Yu Wu +1
End-to-end (E2E) autonomous driving aims to learn a direct mapping from visual observations to control actions. However, these E2E models often act as black boxes and struggle with…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
Xin Cheng, Xingkai Yu, Chenze Shao +30
Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose lo…
Adam's Law: Textual Frequency Law on Large Language Models
Hongyuan Adam Lu, Z. L., Victor Wei +5
While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs) is seldom studied. We propose a novel re…
Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis
Xinyi Li, Sai Wang, Yutian Lin +1
Retrosynthesis prediction aims to infer the reactant molecules based on a given product molecule, which is a fundamental task in chemical synthesis. However, existing methods rely…
Batch Effects In Brain Foundation Model Embeddings
Ye Tao, Bradley T. Baker, Yu Wu +4
Foundation models show strong potential for large-scale, high-dimensional biomedical applications, yet their ability to capture relevant neurobiological characteristics remains und…