|
Poster
|
Thu 16:30
|
How to Boost Any Loss Function
Richard Nock · Yishay Mansour
|
|
|
Poster
|
Wed 11:00
|
Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
Alliot Nagle · Adway Girish · Marco Bondaschi · Michael Gastpar · Ashok Vardhan Makkuva · Hyeji Kim
|
|
|
Poster
|
Wed 16:30
|
Stopping Bayesian Optimization with Probabilistic Regret Bounds
James Wilson
|
|
|
Workshop
|
Sat 15:45
|
A Watermark for Black-Box Language Models
Dara Bahri · John Wieting · Dana Alon · Donald Metzler
|
|
|
Workshop
|
|
How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?
Saeid Asgari · Joseph G Lambourne · Alana Mongkhounsavath
|
|
|
Workshop
|
|
A Black-Box Watermarking Modulation for Semantic Segmentation Models
Mohammed Lansari · Lucas Mattioli · Boussad ADDAD · Paul-Marie RAFFI · Martin Gonzalez · Katarzyna Kapusta
|
|
|
Poster
|
Wed 16:30
|
Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal
Juliusz Ziomek · Masaki Adachi · Michael A Osborne
|
|
|
Workshop
|
|
Diff-BBO: Diffusion-Based Inverse Modeling for Black-Box Optimization
Dongxia Wu · Nikki Lijing Kuang · Ruijia Niu · Yian Ma · Rose Yu
|
|
|
Workshop
|
|
Finding Interior Optimum of Black-box Constrained Objective with Bayesian Optimization
Fengxue Zhang · Zejie Zhu · Yuxin Chen
|
|
|
Workshop
|
Sat 12:00
|
Cannot or Should Not? Automatic Analysis of Refusal Composition in IFT/RLHF Datasets and Refusal Behavior of Black-Box LLMs
Alexander von Recum · Christoph Schnabl · Gabor Hollbeck · Marvin von Hagen · Silas Alberti · Philip Blinde
|
|
|
Workshop
|
|
Zer0-Jack: A memory-efficient gradient-based jailbreaking method for black box Multi-modal Large Language Models
Tiejin Chen · Kaishen Wang · Hua Wei
|
|
|
Workshop
|
|
Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System
Julian Collado · Kevin Stangl
|
|
