|
Poster
|
Wed 11:00
|
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
Mingli Zhu · Siyuan Liang · Baoyuan Wu
|
|
|
Poster
|
Wed 11:00
|
Active Learning of General Halfspaces: Label Queries vs Membership Queries
Ilias Diakonikolas · Daniel Kane · Mingchen Ma
|
|
|
Poster
|
Thu 11:00
|
Universal Rates for Active Learning
Steve Hanneke · Amin Karbasi · Shay Moran · Grigoris Velegkas
|
|
|
Poster
|
Thu 16:30
|
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
Zhenfeng Tu · Santiago Tomas Aranguri Diaz · Arthur Jacot
|
|
|
Poster
|
Wed 11:00
|
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
Yijun Dong · Viet Hoang Phan · Xiang Pan · Qi Lei
|
|
|
Poster
|
Fri 11:00
|
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
Luckeciano Carvalho Melo · Panagiotis Tigas · Alessandro Abate · Yarin Gal
|
|
|
Poster
|
Thu 16:30
|
ESPACE: Dimensionality Reduction of Activations for Model Compression
Charbel Sakr · Brucek Khailany
|
|
|
Poster
|
Wed 11:00
|
Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity
Dayou Yu · Minghao Li · Weishi Shi · Qi Yu
|
|
|
Poster
|
Wed 16:30
|
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
Zhihao Xu · Ruixuan HUANG · Changyu Chen · Xiting Wang
|
|
|
Poster
|
Fri 11:00
|
Activating Self-Attention for Multi-Scene Absolute Pose Regression
Miso Lee · Jihwan Kim · Jae-Pil Heo
|
|
|
Workshop
|
|
Exploring and Addressing Reward Confusion in Offline Preference Learning
Xin Chen, Cynthia · Sam Toyer · Florian Shkurti
|
|
|
Poster
|
Fri 11:00
|
Is O(log N) practical? Near-Equivalence Between Delay Robustness and Bounded Regret in Bandits and RL
Enoch H. Kang · P. R. Kumar
|
|
