41 accepted papers
As tropical cyclones intensify and track forecasts become increasingly uncertain, U.S. ports face heightened supply-chain risk under extreme weather conditions. Port operators need to rapidly synthesize diverse multimodal forecast products, such as probabilistic wind maps, track cones, and official
Spiking Neural Networks (SNNs) draw inspiration from biological neurons to enable brain-like computation, demonstrating effectiveness in processing temporal information with energy efficiency and biological realism. Most existing SNNs are based on neural dynamics such as the (leaky) integrate-and-fi…
Accurate 6-DoF pose estimation of objects is critical for robots to perform precise manipulation tasks. However, for dynamic object pose estimation, conventional camera-based approaches face several major challenges, such as motion blur, sensor noise, and low-light limitation. To address these issue…
While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving contextual textual information, remains in its infancy. With recent progress in large language models and time series learning, we revisit the integration o…
Real-world out-of-distribution (OOD) data exhibit broad, continually evolving distributions, rendering reliance solely on in-distribution (ID) data insufficient for robust detection. Consequently, methods leveraging auxiliary Outlier Exposure (OE) data have emerged, substantially enhancing generaliz…
Graph structured data is commonly used to represent complex relationships such as transactions between accounts, communications between devices, and dependencies among machines or processes. Correspondingly, graph anomaly detection (GAD) plays a critical role in identifying anomalies across various…
Combinatorial optimization (CO) problems have widespread applications in science and engineering, but they present significant computational challenges. Recent advancements in generative models, particularly diffusion models, have shown promise in bypassing traditional optimization solvers by direct
Hyperspectral image (HSI) clustering facilitates the unsupervised discrimination of complex surface materials but traditionally relies on the idealized assumption of centralized data availability. In real-world scenarios, however, this assumption clashes with data privacy regulations and the physica
While video-to-audio generation has achieved remarkable progress in semantic and temporal alignment, most existing studies focus solely on these aspects, paying limited attention to the spatial perception and immersive quality of the synthesized audio. This limitation stems largely from current mode
Class-imbalanced learning (CIL) on tabular data is important in many real-world applications where the minority class holds the critical but rare outcomes. In this paper, we present CLIMB, a comprehensive benchmark for class-imbalanced learning on tabular data. CLIMB includes 73 real-world dataset…
While great success has been achieved in building vision models with Contrastive Language-Image Pre-training (CLIP) over Internet-scale image-text pairs, building transferable Graph Neural Networks (GNNs) with CLIP pipeline is challenging because of the scarcity of labeled data and text supervision,…
In this paper, we propose a novel learning paradigm, termed *Chain-of-Model* (CoM), which incorporates the causal relationship into the hidden states of each layer as a chain style. thereby introducing great scaling efficiency in model training and inference flexibility in deployment.We introduce th…
Recent advancements in large language models (LLMs) have given rise to the emergence of role-playing agents (RPAs). The development of high-quality dialogue datasets is critical for advancing RPAs. However, existing datasets have two main issues: (1) the bias between query distributions and real-wor
Large Language Models (LLMs) demonstrate the ability to solve reasoning and mathematical problems using the Chain-of-Thought (CoT) technique. Expanding CoT length, as seen in models such as DeepSeek-R1, significantly enhances this reasoning for complex problems, but requires costly and high-quality
The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resourc…
Accurate predictions rely on the expressiveness power of graph deep learning frameworks like graph neural networks and graph transformers, where a positional encoding mechanism has become much more indispensable in recent state-of-the-art (SOTA) works to record the canonical position information. Ho…
Negative pressure (NP) therapy with sliding suction is an effective method for limb lymphedema. Due to the caregiver shortage and the patients increase, the robotic NP therapeutic system with a variable-sized suction head can be used to help the lymphedema therapy. However, the varying complexity of
Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieved by true reasoning capability or memorization. To investigate this question, prior work has constructed mathematical be…
Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based fine-tuning and model editing to sparse autoencoder (SAE) steering, e
The advancement of Large Language Models (LLMs) has made ensuring their trustworthiness increasingly critical, especially in terms of fairness across diverse human groups. While modern LLMs are aligned with user preferences through Reinforcement Learning from Human Feedback (RLHF), the reward models
Multi-style outline controllable generation is crucial for multiple applications, including document semantic structuring and retrieval-augmented generation.The great success of preference alignment approaches encourages their application in controllable generation tasks.However, these attempts enco…
Large language models are typically adapted to downstream tasks through supervised fine-tuning on domain-specific data. While standard fine-tuning focuses on minimizing generation loss to optimize model parameters, we take a deeper step by retaining and leveraging the model’s own learning signals, a…
Negative pressure (NP) therapy is effective in managing chronic lymphedema of the extremities. However, the seal formation of the general head (GH) can fail due to the interspace between the lip and the irregular skin surface on limbs before suction, resulting in the inefficiency of therapy, prolong
Pretrained language models (PLMs) display impressive performances and have captured the attention of the NLP community.Establishing best practices in pretraining has, therefore, become a major focus of NLP research, especially since insights gained from monolingual English models may not necessarily…
We consider the problem of fairly allocating a combination of divisible and indivisible goods. While fairness criteria like envy-freeness (EF) and proportionality (PROP) can always be achieved for divisible goods, only their relaxed versions, such as the “up to one” relaxations EF1 and PROP1, can be…
Industrial robots are essential for modern production but often struggle to adapt to new tasks. Modular (reconfigurable) robots can overcome this challenge by eliminating the need to replace the whole robot. However, finding the optimal assembly for a task remains difficult because a valid path has…
Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously analyzes the convergence properties of gradient flow in training Transformers with weight decay regularization. First, we…
A key challenge in Meta-Reinforcement Learning (meta-RL) is the task distribution shift, since the generalization ability of most current meta-RL methods is limited to tasks sampled from the training distribution. In this paper, we propose Posterior Sampling Bayesian Lifelong In-Context Reinforcemen…
Transformers have achieved great success in recent years. Interestingly, transformers have shown particularly strong in-context learning capability -- even without fine-tuning, they are still able to solve unseen tasks well purely based on task-specific prompts. In this paper, we study the capabilit…
Link prediction is a critical problem in graph learning with broad applications such as recommender systems and knowledge graph completion. Numerous research efforts have been directed at solving this problem, including approaches based on similarity metrics and Graph Neural Networks (GNN). However,…
Hyperspectral image (HSI) clustering is gaining considerable attention owing to recent methods that overcome the inefficiency and misleading results from the absence of supervised information. Contrastive learning methods excel at existing pixel-level and superpixel-level HSI clustering tasks. The p…
A recently popular approach to solving reinforcement learning is with data from human preferences. In fact, human preference data are now used with classic reinforcement learning algorithms such as actor-critic methods, which involve evaluating an intermediate policy over a reward learned from human…
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text input is encoded as guidance to generate semantically align…
We consider the fair division problem of indivisible items. It is well-known that an envy-free allocation may not exist, and a relaxed version of envy-freeness, envy-freeness up to one item (EF1), has been widely considered. In an EF1 allocation, an agent may envy others' allocated shares, but only…
We study a fully online matching problem with stochastic arrivals and departures. In this model, each online arrival follows a known identical and independent distribution over a fixed set of agent types. Its sojourn time is unknown in advance and follows type-specific distributions with known expec…
In this paper, we study representation learning in partially observable Markov Decision Processes (POMDPs), where the agent learns a decoder function that maps a series of high-dimensional raw observations to a compact representation and uses it for more efficient exploration and planning. We focus…
Fine-Grained Image Classification (FGIC) aims to classify images into specific subordinate classes of a superclass. Due to insufficient training data and confusing data samples, FGIC may produce uncertain classification results that are untrusted for data applications. In fact, FGIC can be viewed as…
We study the problem of designing truthful and fair mechanisms when allocating a mixture of divisible and indivisible goods. We first show that there does not exist an EFM (envy-free for mixed goods) and truthful mechanism in general. This impossibility result holds even if there is only one indivis…
We study a fair resource allocation problem with indivisible items. The agents’ preferences over items are assumed to be ordinal and have uncertainties. We adopt stochastic dominance proportionality as our fairness notion and study a sequence of problems related to finding allocations that are fair…
The Stackelberg prediction game (SPG) has been extensively used to model the interactions between the learner and data provider in the training process of various machine learning algorithms. Particularly, SPGs played prominent roles in cybersecurity applications, such as intrusion detection, bankin…
Transformer-based detector is a new paradigm in object detection, which aims to achieve pretty-well performance while eliminates the priori knowledge driven components, e.g., anchors, proposals and the NMS. DETR, the state-of-the-art model among them, is composed of three sub-modules, i.e., a CNN-ba…