Related papers: MELCOT: A Hybrid Learning Architecture with Margin…
Symbolic regression aims to discover human-interpretable equations that explain observational data. However, existing approaches rely heavily on discrete structure search (e.g., genetic programming), which often leads to high computational…
Surgical triplet recognition, which involves identifying instrument, verb, target, and their combinations, is a complex surgical scene understanding challenge plagued by long-tailed data distribution. The mainstream multi-task learning…
Scientific simulations and experimental measurements produce vast amounts of spatio-temporal data, yet extracting meaningful insights remains challenging due to high dimensionality, complex structures, and missing information. Traditional…
Representation learning for high-dimensional, complex physical systems aims to identify a low-dimensional intrinsic latent space, which is crucial for reduced-order modeling and modal analysis. To overcome the well-known Kolmogorov barrier,…
Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, these representations are hand-engineered using domain…
Unsupervised learning aims at the discovery of hidden structure that drives the observations in the real world. It is essential for success in modern machine learning. Latent variable models are versatile in unsupervised learning and have…
We investigate nonlinear prediction in an online setting and introduce a hybrid model that effectively mitigates, via an end-to-end architecture, the need for hand-designed features and manual model selection issues of conventional…
Offline model-based optimization (MBO) aims to identify a design that maximizes a black-box function using only a fixed, pre-collected dataset of designs and their corresponding scores. A common approach in offline MBO is to train a…
Multimodal representation learning is commonly built on a shared-private decomposition, treating latent information as either common to all modalities or specific to one. This binary view is often inadequate: many factors are shared by only…
Cloud computing is a reliable solution to provide distributed computation power. However, real-time response is still challenging regarding the enormous amount of data generated by the IoT devices in 5G and 6G networks. Thus, multi-access…
Grokking -- the abrupt transition from memorization to generalization after extended training -- has been linked to the emergence of low-dimensional structure in learning dynamics. Yet neural network parameters inhabit extremely…
We study a challenging form of Smoothed Online Convex Optimization, a.k.a. SOCO, including multi-step nonlinear switching costs and feedback delay. We propose a novel machine learning (ML) augmented online algorithm, Robustness-Constrained…
Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, thereby making inference computationally inefficient for…
Multimodal Continual Instruction Tuning (MCIT) aims to finetune Multimodal Large Language Models (MLLMs) to continually align with human intent across sequential tasks. Existing approaches often rely on the Mixture-of-Experts (MoE) LoRA…
Large sequence model (SM) such as GPT series and BERT has displayed outstanding performance and generalization capabilities on vision, language, and recently reinforcement learning tasks. A natural follow-up question is how to abstract…
Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…
Accurately predicting spatio-temporal network traffic is essential for dynamically managing computing resources in modern communication systems and minimizing energy consumption. Although spatio-temporal traffic prediction has received…
Vision-Language Models (VLMs) have made significant strides in static image understanding but continue to face critical hurdles in spatiotemporal reasoning. A major bottleneck is "multi-image reasoning hallucination", where a massive…
Matrix approximations are a key element in large-scale algebraic machine learning approaches. The recently proposed method MEKA (Si et al., 2014) effectively employs two common assumptions in Hilbert spaces: the low-rank property of an…
The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…