11 papers
CHASM: Cross-frequency Harmonized Axis-Separable Mixing for Spectral Token Operators
Pengcheng Fang, Hongli Chen, Yuxia Chen +3
Spectral token mixers based on Fourier transforms provide an efficient way to model global interactions in visual feature maps. Existing designs often either apply filter-wise spec…
Dual-Pathway Circuits of Object Hallucination in Vision-Language Models
Jiaxin Liu, Ding Zhong, Yue Wang +6
Vision-language models (VLMs) have demonstrated remarkable capabilities in bridging visual perception and natural language understanding, enabling a wide range of multimodal reason…
Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning
Jiaxin Liu, Anzhe Cheng, Paul Bogdan
When an RL agent's observations contain distractors driven by the same confounders as its true state, observational data alone cannot identify which dimensions the agent controls.…
A Tale of Two Variances: When Single-Seed Benchmarks Fail in Bayesian Deep Learning
Qishi Zhan, Minxuan Hu, Liang He +2
In limited-data settings, a single endpoint mean of an evaluation metric such as the Continuous Ranked Probability Score (CRPS) is itself a random variable, yet it is routinely rep…
Unstable Rankings in Bayesian Deep Learning Evaluation
Qishi Zhan, Minxuan Hu, Guansu Wang +2
Standard evaluations of Bayesian deep learning methods assume that metric estimates are reliable, but we show this assumption fails under data scarcity. Method rankings are not onl…
Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts
Wenhao Li, Daohai Yu, Gen Luo +7
Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whos…