Related papers: ALM-MTA:Front-Door Causal Multi-Touch Attribution …

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external…

Multimodal Diffusion Transformers (MM-DiTs) have achieved remarkable progress in text-driven visual generation. However, even state-of-the-art MM-DiT models like FLUX struggle with achieving precise alignment between text prompts and…

There has been an increasing interest in multi-task learning for video understanding in recent years. In this work, we propose a generalized notion of multi-task learning by incorporating both auxiliary tasks that the model should perform…

Data quality stands at the forefront of deciding the effectiveness of video-language representation learning. However, video-text pairs in previous data typically do not align perfectly with each other, which might lead to video-language…

Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…

On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, transfer learning imposes a heavy computation burden to resource-constrained edge devices. Existing task…

End-to-end autonomous driving models generate future trajectories from multi-view inputs, improving system integration but introducing opaque decisions and hard-to-localize risks. Existing methods either rely on auxiliary monitoring models…

Diagnostic investigation has an important role in risk stratification and clinical decision making of patients with suspected and documented Coronary Artery Disease (CAD). However, the majority of existing tools are primarily focused on the…

Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide sufficient learning support, modern MTL uses annotated data with…

Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality of output videos. However, achieving the desired output often…

Continual test-time adaptation (CTTA) has recently emerged to adapt a pre-trained source model to continuously evolving target distributions, which accommodates the dynamic nature of real-world environments. To mitigate the risk of…

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current…

Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…

External reasoning systems combine language models with process reward models (PRMs) to select high-quality reasoning paths for complex tasks such as mathematical problem solving. However, these systems are prone to reward hacking, where…

Multi-agent systems (MAS) are critical for automating complex tasks, yet their practical deployment is severely hampered by the challenge of failure attribution. Current diagnostic tools, which rely on statistical correlations, are…

Causal mediation analysis in cluster-randomized trials (CRTs) is complicated by the presence of multiple mediators, intracluster correlation, and within-cluster interference. Existing mediation methods often fall short in accommodating…

Offline Multi-agent Reinforcement Learning (MARL) is valuable in scenarios where online interaction is impractical or risky. While independent learning in MARL offers flexibility and scalability, accurately assigning credit to individual…

Memory systems are critical for LLMs, mitigating context window limitations and supporting long-horizon user-LLM interactions. Such systems typically comprise multiple agents responsible for memory construction and retrieval. Existing…

Mediation analysis has traditionally focused on outcome-level summary contrasts, such as mean effects, which may obscure substantial distributional changes induced by complex and nonlinear causal mechanisms. We propose Distributional Causal…

Partial Adaptation (PDA) addresses a practical scenario in which the target domain contains only a subset of classes in the source domain. While PDA should take into account both class-level and sample-level to mitigate negative transfer,…