196 citations · 543 across the 22 of their papers we have counts for
24 papers
Longitudinal Brain Aging in Covariance Space: Temporally Calibrated Bayesian Inference for Adaptive Covariance Operators
Montserrat Fuentes, Yi Zhao
Functional brain aging is often characterized by differences between people of different ages, although aging unfolds within individuals. This distinction is especially important f…
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
Liyan Tang, Cyrus Rashtchian, Chun-Sung Ferng +3
Agent skills package specialized knowledge and workflows into reusable resources that extend AI agent capabilities. Recent work automatically discovers such skills from agent exper…
On the Generalization Gap in Self-Evolving Language Model Reasoning
Zhenting Qi, Susanna Maria Baby, Stefanie Anna Baby +5
Recent work suggests that large language models (LLMs) can improve through self-evolution (SE), using supervision signals generated by the model itself. In this work, we ask: under…
Neuron-Level Differentiation of Memorization and Generalization in Large Language Models
Ko-Wei Huang, Yi-Fu Fu, Ching-Yu Tsai +8
We investigate how Large Language Models (LLMs) distinguish between memorization and generalization at the neuron level. Through carefully designed tasks, we identify distinct neur…
Sufficient Context: A New Lens on Retrieval Augmented Generation Systems
Hailey Joren, Jianyi Zhang, Chun-Sung Ferng +3
Augmenting LLMs with context leads to improved performance across many applications. Despite much research on Retrieval Augmented Generation (RAG) systems, an open question is whet…
SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models
Jianyi Zhang, Da-Cheng Juan, Cyrus Rashtchian +3
Large language models (LLMs) have demonstrated remarkable capabilities, but their outputs can sometimes be unreliable or factually incorrect. To address this, we introduce Self Log…
DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback
Jiao Sun, Deqing Fu, Yushi Hu +8
Despite their wide-spread success, Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user's input text. We introd…
Substance or Style: What Does Your Image Embedding Know?
Cyrus Rashtchian, Charles Herrmann, Chun-Sung Ferng +5
Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddin…
LayerNAS: Neural Architecture Search in Polynomial Complexity
Yicheng Fan, Dana Alon, Jingyue Shen +7
Neural Architecture Search (NAS) has become a popular method for discovering effective model architectures, especially for target hardware. As such, NAS methods that find optimal a…
RARR: Researching and Revising What Language Models Say, Using Language Models
Luyu Gao, Zhuyun Dai, Panupong Pasupat +8
Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading conte…
Representative Image Feature Extraction via Contrastive Learning Pretraining for Chest X-ray Report Generation
Yu-Jen Chen, Wei-Hsiang Shen, Hao-Wei Chung +6
Medical report generation is a challenging task since it is time-consuming and requires expertise from experienced radiologists. The goal of medical report generation is to accurat…
CARLS: Cross-platform Asynchronous Representation Learning System
Chun-Ta Lu, Yun Zeng, Da-Cheng Juan +13
In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge make…
Switch Spaces: Learning Product Spaces with Sparse Gating
Shuai Zhang, Yi Tay, Wenqi Jiang +2
Learning embedding spaces of suitable geometry is critical for representation learning. In order for learned representations to be effective and efficient, it is ideal that the geo…
OmniNet: Omnidirectional Representations from Transformers
Yi Tay, Mostafa Dehghani, Vamsi Aribandi +6
This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to…
Graph Autoencoders with Deconvolutional Networks
Jia Li, Tomas Yu, Da-Cheng Juan +3
Recent studies have indicated that Graph Convolutional Networks (GCNs) act as a \emph{low pass} filter in spectral domain and encode smoothed node representations. In this paper, w…
Adversarial Robustness Across Representation Spaces
Pranjal Awasthi, George Yu, Chun-Sung Ferng +2
Adversarial robustness corresponds to the susceptibility of deep neural networks to imperceptible perturbations made at test time. In the context of image tasks, many algorithms ha…
HyperGrid: Efficient Multi-Task Transformers with Grid-wise Decomposable Hyper Projections
Yi Tay, Zhe Zhao, Dara Bahri +2
Achieving state-of-the-art performance on natural language understanding tasks typically relies on fine-tuning a fresh model for every task. Consequently, this approach leads to a…
Remix: Rebalanced Mixup
Hsin-Ping Chou, Shih-Chieh Chang, Jia-Yu Pan +2
Deep image classifiers often perform poorly when training data are heavily class-imbalanced. In this work, we propose a new regularization technique, Remix, that relaxes Mixup's fo…
Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization
Li-Huang Tsai, Shih-Chieh Chang, Yu-Ting Chen +3
Analog computing hardwares, such as Processing-in-memory (PIM) accelerators, have gradually received more attention for accelerating the neural network computations. However, PIM a…
Synthesizer: Rethinking Self-Attention in Transformer Models
Yi Tay, Dara Bahri, Donald Metzler +3
The dot product self-attention is known to be central and indispensable to state-of-the-art Transformer models. But is it really required? This paper investigates the true importan…
Low-Dimensional Hyperbolic Knowledge Graph Embeddings
Ines Chami, Adva Wolf, Da-Cheng Juan +3
Knowledge graph (KG) embeddings learn low-dimensional representations of entities and relations to predict missing facts. KGs often exhibit hierarchical and logical patterns which…
Sparse Sinkhorn Attention
Yi Tay, Dara Bahri, Liu Yang +2
We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations. Concretel…
MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
Chi-Hung Hsu, Shu-Huan Chang, Jhao-Hong Liang +7
Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures. While most existing works aim a…
Task Transfer by Preference-Based Cost Learning
Mingxuan Jing, Xiaojian Ma, Wenbing Huang +2
The goal of task transfer in reinforcement learning is migrating the action policy of an agent to the target task from the source task. Given their successes on robotic action plan…